From ea570af409f3f3cf990508925ec2caccac55771a Mon Sep 17 00:00:00 2001
From: David Ibia <github@boxpositron.dev>
Date: Sat, 10 Oct 2026 14:56:27 +0100
Subject: [PATCH] feat(omo): retire opencode and move its skills and commands
 to omo

- Move the vendored skills from .config/opencode/skills to
  .config/omo/skills, with provenance and local changes in its README
- Rewrite Impeccable's script paths to ~/.omo/agent/skills/impeccable so
  its detector and live-server verbs resolve under omo
- frontend-workflow hands screenshots to a visual-engineering task
  instead of opencode run
- Move the notes commands and /impeccable to .config/omo/prompts as omo
  prompt templates; setup-mcp stays behind because it writes
  opencode.json
- Archive DEVELOPMENT-WORKFLOW.md and UI-WORKFLOW.md under
  .config/omo/archive; nothing loads them
- link-ai-configs.sh links the skills into omo and Claude Code only and
  stops linking OpenCode's config, TUI, plugins and workflow docs
- setup-mac.sh and Brewfile.apps stop installing OpenCode; README and
  .withcontextconfig.jsonc follow the new layout

~/.config/opencode/AGENTS.md stays linked: omo's rules engine reads it
before ~/.claude/CLAUDE.md and stops at the first hit, so it carries the
shared preferences and keeps OMC's instructions out of omo.
---
 .../archive}/DEVELOPMENT-WORKFLOW.md          |  0
 .../{opencode => omo/archive}/UI-WORKFLOW.md  |  0
 .../command => omo/prompts}/analyze-vault.md  |  2 -
 .config/omo/prompts/impeccable.md             |  6 ++
 .../command => omo/prompts}/ingest-notes.md   |  2 -
 .../prompts}/preview-notes-delegation.md      |  2 -
 .../prompts}/reorganize-notes.md              |  2 -
 .../command => omo/prompts}/setup-notes.md    |  2 -
 .../command => omo/prompts}/sync-notes.md     |  2 -
 .../command => omo/prompts}/teleport-notes.md |  2 -
 .../prompts}/validate-notes-config.md         |  2 -
 .config/omo/skills/README.md                  | 52 +++++++++++++++
 .../{opencode => omo}/skills/ai-seo/LICENSE   |  0
 .../{opencode => omo}/skills/ai-seo/SKILL.md  |  0
 .../skills/ai-seo/evals/evals.json            |  0
 .../ai-seo/references/agent-readiness.md      |  0
 .../citations-vs-recommendations.md           |  0
 .../ai-seo/references/content-patterns.md     |  0
 .../skills/ai-seo/references/content-types.md |  0
 .../ai-seo/references/format-volatility.md    |  0
 .../references/linkedin-ai-citations.md       |  0
 .../skills/ai-seo/references/okf.md           |  0
 .../references/platform-ranking-factors.md    |  0
 .../references/positioning-and-consensus.md   |  0
 .../ai-seo/references/youtube-ai-citations.md |  0
 .../skills/cold-email/LICENSE                 |  0
 .../skills/cold-email/SKILL.md                |  0
 .../skills/cold-email/evals/evals.json        |  0
 .../cold-email/references/benchmarks.md       |  0
 .../cold-email/references/deliverability.md   |  0
 .../references/follow-up-sequences.md         |  0
 .../cold-email/references/frameworks.md       |  0
 .../references/linkedin-outreach.md           |  0
 .../references/multichannel-cadence.md        |  0
 .../cold-email/references/outbound-plays.md   |  0
 .../cold-email/references/personalization.md  |  0
 .../cold-email/references/reply-handling.md   |  0
 .../cold-email/references/subject-lines.md    |  0
 .../skills/content-strategy/LICENSE           |  0
 .../skills/content-strategy/SKILL.md          |  0
 .../skills/content-strategy/evals/evals.json  |  0
 .../references/content-distribution.md        |  0
 .../references/headless-cms.md                |  0
 .../skills/copy-editing/LICENSE               |  0
 .../skills/copy-editing/SKILL.md              |  0
 .../skills/copy-editing/evals/evals.json      |  0
 .../copy-editing/references/checklist.md      |  0
 .../references/content-refresh.md             |  0
 .../references/plain-english-alternatives.md  |  0
 .../skills/copywriting/LICENSE                |  0
 .../skills/copywriting/SKILL.md               |  0
 .../skills/copywriting/evals/evals.json       |  0
 .../skills/copywriting/references/ai-tells.md |  0
 .../copywriting/references/copy-frameworks.md |  0
 .../references/natural-transitions.md         |  0
 .../{opencode => omo}/skills/emails/LICENSE   |  0
 .../{opencode => omo}/skills/emails/SKILL.md  |  0
 .../skills/emails/evals/evals.json            |  0
 .../emails/references/copy-guidelines.md      |  0
 .../skills/emails/references/email-types.md   |  0
 .../emails/references/sequence-templates.md   |  0
 .../skills/frontend-workflow/SKILL.md         |  2 +-
 .../references/dotfiles-workbench.md          |  0
 .../skills/impeccable/LICENSE                 |  0
 .../skills/impeccable/SKILL.md                |  6 +-
 .../skills/impeccable/reference/adapt.md      |  0
 .../impeccable/reference/adapt.native.md      |  0
 .../skills/impeccable/reference/android.md    |  0
 .../skills/impeccable/reference/animate.md    |  0
 .../skills/impeccable/reference/audit.md      |  0
 .../impeccable/reference/audit.native.md      |  0
 .../skills/impeccable/reference/bolder.md     |  0
 .../skills/impeccable/reference/clarify.md    |  0
 .../skills/impeccable/reference/colorize.md   |  0
 .../impeccable/reference/craft-floor.md       |  0
 .../skills/impeccable/reference/craft.md      |  0
 .../skills/impeccable/reference/critique.md   | 10 +--
 .../reference/degraded/asset-producer.md      |  6 +-
 .../reference/degraded/documenter.md          |  0
 .../reference/degraded/finish-reviewer.md     |  0
 .../reference/degraded/manual-edit-applier.md |  0
 .../skills/impeccable/reference/delight.md    |  0
 .../skills/impeccable/reference/distill.md    |  0
 .../skills/impeccable/reference/doctor.md     |  4 +-
 .../skills/impeccable/reference/document.md   |  0
 .../skills/impeccable/reference/extract.md    |  0
 .../skills/impeccable/reference/generate.md   | 12 ++--
 .../skills/impeccable/reference/harden.md     |  0
 .../skills/impeccable/reference/hooks.md      | 12 ++--
 .../skills/impeccable/reference/init.md       |  0
 .../skills/impeccable/reference/ios.md        |  0
 .../skills/impeccable/reference/layout.md     |  2 +-
 .../skills/impeccable/reference/live-setup.md |  2 +-
 .../skills/impeccable/reference/live.md       | 28 ++++----
 .../skills/impeccable/reference/new-work.md   | 20 +++---
 .../skills/impeccable/reference/onboard.md    |  0
 .../skills/impeccable/reference/operate.md    |  0
 .../skills/impeccable/reference/optimize.md   |  0
 .../skills/impeccable/reference/overdrive.md  |  0
 .../skills/impeccable/reference/polish.md     |  4 +-
 .../skills/impeccable/reference/quieter.md    |  0
 .../skills/impeccable/reference/routing.md    |  4 +-
 .../skills/impeccable/reference/shape.md      |  0
 .../skills/impeccable/reference/typeset.md    |  2 +-
 .../skills/impeccable/reference/visualize.md  |  2 +-
 .../skills/impeccable/scripts/VERSION         |  0
 .../impeccable/scripts/command-metadata.json  |  0
 .../scripts/data/font-index-failures.json     |  0
 .../impeccable/scripts/data/font-index.json   |  0
 .../skills/impeccable/scripts/impeccable      |  0
 .../skills/impeccable/scripts/impeccable.cmd  |  0
 .../impeccable/scripts/live-browser-dom.js    |  0
 .../scripts/live-browser-ignores.js           |  0
 .../scripts/live-browser-session.js           |  0
 .../skills/impeccable/scripts/live-browser.js |  0
 .../scripts/modern-screenshot.umd.js          |  0
 .../{opencode => omo}/skills/launch/LICENSE   |  0
 .../{opencode => omo}/skills/launch/SKILL.md  |  0
 .../skills/launch/evals/evals.json            |  0
 .../launch/references/shipped-changes.md      |  0
 .../launch/references/site-launch-qa.md       |  0
 .../skills/product-marketing/LICENSE          |  0
 .../skills/product-marketing/SKILL.md         |  0
 .../skills/product-marketing/evals/evals.json |  0
 .../skills/seo-audit/LICENSE                  |  0
 .../skills/seo-audit/SKILL.md                 |  0
 .../skills/seo-audit/evals/evals.json         |  0
 .../references/ai-writing-detection.md        |  0
 .../seo-audit/references/international-seo.md |  0
 .../seo-audit/references/rankings-push.md     |  0
 .../skills/seo-audit/references/title-tags.md |  0
 .../{opencode => omo}/skills/social/LICENSE   |  0
 .../{opencode => omo}/skills/social/SKILL.md  |  0
 .../skills/social/evals/evals.json            |  0
 .../social/references/carousel-frameworks.md  |  0
 .../references/listening-sources-template.md  |  0
 .../skills/social/references/listening.md     |  0
 .../social/references/platform-limits.md      |  0
 .../skills/social/references/platforms.md     |  0
 .../social/references/post-templates.md       |  0
 .../social/references/reverse-engineering.md  |  0
 .../social/references/short-form-video.md     |  0
 .../skills/social/references/x-algorithm.md   |  0
 .../skills/web-design-guidelines/SKILL.md     |  0
 .config/opencode/command/impeccable.md        |  6 --
 .withcontextconfig.jsonc                      |  6 +-
 Brewfile.apps                                 |  1 -
 README.md                                     | 66 +++++++------------
 link-ai-configs.sh                            | 46 +++++--------
 setup-mac.sh                                  | 11 +---
 150 files changed, 165 insertions(+), 161 deletions(-)
 rename .config/{opencode => omo/archive}/DEVELOPMENT-WORKFLOW.md (100%)
 rename .config/{opencode => omo/archive}/UI-WORKFLOW.md (100%)
 rename .config/{opencode/command => omo/prompts}/analyze-vault.md (99%)
 create mode 100644 .config/omo/prompts/impeccable.md
 rename .config/{opencode/command => omo/prompts}/ingest-notes.md (99%)
 rename .config/{opencode/command => omo/prompts}/preview-notes-delegation.md (99%)
 rename .config/{opencode/command => omo/prompts}/reorganize-notes.md (99%)
 rename .config/{opencode/command => omo/prompts}/setup-notes.md (99%)
 rename .config/{opencode/command => omo/prompts}/sync-notes.md (99%)
 rename .config/{opencode/command => omo/prompts}/teleport-notes.md (99%)
 rename .config/{opencode/command => omo/prompts}/validate-notes-config.md (99%)
 create mode 100644 .config/omo/skills/README.md
 rename .config/{opencode => omo}/skills/ai-seo/LICENSE (100%)
 rename .config/{opencode => omo}/skills/ai-seo/SKILL.md (100%)
 rename .config/{opencode => omo}/skills/ai-seo/evals/evals.json (100%)
 rename .config/{opencode => omo}/skills/ai-seo/references/agent-readiness.md (100%)
 rename .config/{opencode => omo}/skills/ai-seo/references/citations-vs-recommendations.md (100%)
 rename .config/{opencode => omo}/skills/ai-seo/references/content-patterns.md (100%)
 rename .config/{opencode => omo}/skills/ai-seo/references/content-types.md (100%)
 rename .config/{opencode => omo}/skills/ai-seo/references/format-volatility.md (100%)
 rename .config/{opencode => omo}/skills/ai-seo/references/linkedin-ai-citations.md (100%)
 rename .config/{opencode => omo}/skills/ai-seo/references/okf.md (100%)
 rename .config/{opencode => omo}/skills/ai-seo/references/platform-ranking-factors.md (100%)
 rename .config/{opencode => omo}/skills/ai-seo/references/positioning-and-consensus.md (100%)
 rename .config/{opencode => omo}/skills/ai-seo/references/youtube-ai-citations.md (100%)
 rename .config/{opencode => omo}/skills/cold-email/LICENSE (100%)
 rename .config/{opencode => omo}/skills/cold-email/SKILL.md (100%)
 rename .config/{opencode => omo}/skills/cold-email/evals/evals.json (100%)
 rename .config/{opencode => omo}/skills/cold-email/references/benchmarks.md (100%)
 rename .config/{opencode => omo}/skills/cold-email/references/deliverability.md (100%)
 rename .config/{opencode => omo}/skills/cold-email/references/follow-up-sequences.md (100%)
 rename .config/{opencode => omo}/skills/cold-email/references/frameworks.md (100%)
 rename .config/{opencode => omo}/skills/cold-email/references/linkedin-outreach.md (100%)
 rename .config/{opencode => omo}/skills/cold-email/references/multichannel-cadence.md (100%)
 rename .config/{opencode => omo}/skills/cold-email/references/outbound-plays.md (100%)
 rename .config/{opencode => omo}/skills/cold-email/references/personalization.md (100%)
 rename .config/{opencode => omo}/skills/cold-email/references/reply-handling.md (100%)
 rename .config/{opencode => omo}/skills/cold-email/references/subject-lines.md (100%)
 rename .config/{opencode => omo}/skills/content-strategy/LICENSE (100%)
 rename .config/{opencode => omo}/skills/content-strategy/SKILL.md (100%)
 rename .config/{opencode => omo}/skills/content-strategy/evals/evals.json (100%)
 rename .config/{opencode => omo}/skills/content-strategy/references/content-distribution.md (100%)
 rename .config/{opencode => omo}/skills/content-strategy/references/headless-cms.md (100%)
 rename .config/{opencode => omo}/skills/copy-editing/LICENSE (100%)
 rename .config/{opencode => omo}/skills/copy-editing/SKILL.md (100%)
 rename .config/{opencode => omo}/skills/copy-editing/evals/evals.json (100%)
 rename .config/{opencode => omo}/skills/copy-editing/references/checklist.md (100%)
 rename .config/{opencode => omo}/skills/copy-editing/references/content-refresh.md (100%)
 rename .config/{opencode => omo}/skills/copy-editing/references/plain-english-alternatives.md (100%)
 rename .config/{opencode => omo}/skills/copywriting/LICENSE (100%)
 rename .config/{opencode => omo}/skills/copywriting/SKILL.md (100%)
 rename .config/{opencode => omo}/skills/copywriting/evals/evals.json (100%)
 rename .config/{opencode => omo}/skills/copywriting/references/ai-tells.md (100%)
 rename .config/{opencode => omo}/skills/copywriting/references/copy-frameworks.md (100%)
 rename .config/{opencode => omo}/skills/copywriting/references/natural-transitions.md (100%)
 rename .config/{opencode => omo}/skills/emails/LICENSE (100%)
 rename .config/{opencode => omo}/skills/emails/SKILL.md (100%)
 rename .config/{opencode => omo}/skills/emails/evals/evals.json (100%)
 rename .config/{opencode => omo}/skills/emails/references/copy-guidelines.md (100%)
 rename .config/{opencode => omo}/skills/emails/references/email-types.md (100%)
 rename .config/{opencode => omo}/skills/emails/references/sequence-templates.md (100%)
 rename .config/{opencode => omo}/skills/frontend-workflow/SKILL.md (92%)
 rename .config/{opencode => omo}/skills/frontend-workflow/references/dotfiles-workbench.md (100%)
 rename .config/{opencode => omo}/skills/impeccable/LICENSE (100%)
 rename .config/{opencode => omo}/skills/impeccable/SKILL.md (92%)
 rename .config/{opencode => omo}/skills/impeccable/reference/adapt.md (100%)
 rename .config/{opencode => omo}/skills/impeccable/reference/adapt.native.md (100%)
 rename .config/{opencode => omo}/skills/impeccable/reference/android.md (100%)
 rename .config/{opencode => omo}/skills/impeccable/reference/animate.md (100%)
 rename .config/{opencode => omo}/skills/impeccable/reference/audit.md (100%)
 rename .config/{opencode => omo}/skills/impeccable/reference/audit.native.md (100%)
 rename .config/{opencode => omo}/skills/impeccable/reference/bolder.md (100%)
 rename .config/{opencode => omo}/skills/impeccable/reference/clarify.md (100%)
 rename .config/{opencode => omo}/skills/impeccable/reference/colorize.md (100%)
 rename .config/{opencode => omo}/skills/impeccable/reference/craft-floor.md (100%)
 rename .config/{opencode => omo}/skills/impeccable/reference/craft.md (100%)
 rename .config/{opencode => omo}/skills/impeccable/reference/critique.md (98%)
 rename .config/{opencode => omo}/skills/impeccable/reference/degraded/asset-producer.md (84%)
 rename .config/{opencode => omo}/skills/impeccable/reference/degraded/documenter.md (100%)
 rename .config/{opencode => omo}/skills/impeccable/reference/degraded/finish-reviewer.md (100%)
 rename .config/{opencode => omo}/skills/impeccable/reference/degraded/manual-edit-applier.md (100%)
 rename .config/{opencode => omo}/skills/impeccable/reference/delight.md (100%)
 rename .config/{opencode => omo}/skills/impeccable/reference/distill.md (100%)
 rename .config/{opencode => omo}/skills/impeccable/reference/doctor.md (94%)
 rename .config/{opencode => omo}/skills/impeccable/reference/document.md (100%)
 rename .config/{opencode => omo}/skills/impeccable/reference/extract.md (100%)
 rename .config/{opencode => omo}/skills/impeccable/reference/generate.md (92%)
 rename .config/{opencode => omo}/skills/impeccable/reference/harden.md (100%)
 rename .config/{opencode => omo}/skills/impeccable/reference/hooks.md (93%)
 rename .config/{opencode => omo}/skills/impeccable/reference/init.md (100%)
 rename .config/{opencode => omo}/skills/impeccable/reference/ios.md (100%)
 rename .config/{opencode => omo}/skills/impeccable/reference/layout.md (98%)
 rename .config/{opencode => omo}/skills/impeccable/reference/live-setup.md (99%)
 rename .config/{opencode => omo}/skills/impeccable/reference/live.md (92%)
 rename .config/{opencode => omo}/skills/impeccable/reference/new-work.md (88%)
 rename .config/{opencode => omo}/skills/impeccable/reference/onboard.md (100%)
 rename .config/{opencode => omo}/skills/impeccable/reference/operate.md (100%)
 rename .config/{opencode => omo}/skills/impeccable/reference/optimize.md (100%)
 rename .config/{opencode => omo}/skills/impeccable/reference/overdrive.md (100%)
 rename .config/{opencode => omo}/skills/impeccable/reference/polish.md (96%)
 rename .config/{opencode => omo}/skills/impeccable/reference/quieter.md (100%)
 rename .config/{opencode => omo}/skills/impeccable/reference/routing.md (63%)
 rename .config/{opencode => omo}/skills/impeccable/reference/shape.md (100%)
 rename .config/{opencode => omo}/skills/impeccable/reference/typeset.md (98%)
 rename .config/{opencode => omo}/skills/impeccable/reference/visualize.md (94%)
 rename .config/{opencode => omo}/skills/impeccable/scripts/VERSION (100%)
 rename .config/{opencode => omo}/skills/impeccable/scripts/command-metadata.json (100%)
 rename .config/{opencode => omo}/skills/impeccable/scripts/data/font-index-failures.json (100%)
 rename .config/{opencode => omo}/skills/impeccable/scripts/data/font-index.json (100%)
 rename .config/{opencode => omo}/skills/impeccable/scripts/impeccable (100%)
 rename .config/{opencode => omo}/skills/impeccable/scripts/impeccable.cmd (100%)
 rename .config/{opencode => omo}/skills/impeccable/scripts/live-browser-dom.js (100%)
 rename .config/{opencode => omo}/skills/impeccable/scripts/live-browser-ignores.js (100%)
 rename .config/{opencode => omo}/skills/impeccable/scripts/live-browser-session.js (100%)
 rename .config/{opencode => omo}/skills/impeccable/scripts/live-browser.js (100%)
 rename .config/{opencode => omo}/skills/impeccable/scripts/modern-screenshot.umd.js (100%)
 rename .config/{opencode => omo}/skills/launch/LICENSE (100%)
 rename .config/{opencode => omo}/skills/launch/SKILL.md (100%)
 rename .config/{opencode => omo}/skills/launch/evals/evals.json (100%)
 rename .config/{opencode => omo}/skills/launch/references/shipped-changes.md (100%)
 rename .config/{opencode => omo}/skills/launch/references/site-launch-qa.md (100%)
 rename .config/{opencode => omo}/skills/product-marketing/LICENSE (100%)
 rename .config/{opencode => omo}/skills/product-marketing/SKILL.md (100%)
 rename .config/{opencode => omo}/skills/product-marketing/evals/evals.json (100%)
 rename .config/{opencode => omo}/skills/seo-audit/LICENSE (100%)
 rename .config/{opencode => omo}/skills/seo-audit/SKILL.md (100%)
 rename .config/{opencode => omo}/skills/seo-audit/evals/evals.json (100%)
 rename .config/{opencode => omo}/skills/seo-audit/references/ai-writing-detection.md (100%)
 rename .config/{opencode => omo}/skills/seo-audit/references/international-seo.md (100%)
 rename .config/{opencode => omo}/skills/seo-audit/references/rankings-push.md (100%)
 rename .config/{opencode => omo}/skills/seo-audit/references/title-tags.md (100%)
 rename .config/{opencode => omo}/skills/social/LICENSE (100%)
 rename .config/{opencode => omo}/skills/social/SKILL.md (100%)
 rename .config/{opencode => omo}/skills/social/evals/evals.json (100%)
 rename .config/{opencode => omo}/skills/social/references/carousel-frameworks.md (100%)
 rename .config/{opencode => omo}/skills/social/references/listening-sources-template.md (100%)
 rename .config/{opencode => omo}/skills/social/references/listening.md (100%)
 rename .config/{opencode => omo}/skills/social/references/platform-limits.md (100%)
 rename .config/{opencode => omo}/skills/social/references/platforms.md (100%)
 rename .config/{opencode => omo}/skills/social/references/post-templates.md (100%)
 rename .config/{opencode => omo}/skills/social/references/reverse-engineering.md (100%)
 rename .config/{opencode => omo}/skills/social/references/short-form-video.md (100%)
 rename .config/{opencode => omo}/skills/social/references/x-algorithm.md (100%)
 rename .config/{opencode => omo}/skills/web-design-guidelines/SKILL.md (100%)
 delete mode 100644 .config/opencode/command/impeccable.md

diff --git a/.config/opencode/DEVELOPMENT-WORKFLOW.md b/.config/omo/archive/DEVELOPMENT-WORKFLOW.md
similarity index 100%
rename from .config/opencode/DEVELOPMENT-WORKFLOW.md
rename to .config/omo/archive/DEVELOPMENT-WORKFLOW.md
diff --git a/.config/opencode/UI-WORKFLOW.md b/.config/omo/archive/UI-WORKFLOW.md
similarity index 100%
rename from .config/opencode/UI-WORKFLOW.md
rename to .config/omo/archive/UI-WORKFLOW.md
diff --git a/.config/opencode/command/analyze-vault.md b/.config/omo/prompts/analyze-vault.md
similarity index 99%
rename from .config/opencode/command/analyze-vault.md
rename to .config/omo/prompts/analyze-vault.md
index b7168ce..b0b2fc7 100644
--- a/.config/opencode/command/analyze-vault.md
+++ b/.config/omo/prompts/analyze-vault.md
@@ -1,7 +1,5 @@
 ---
 description: Analyze vault structure and organization
-agent: general
-subtask: true
 ---
 
 # Analyze Vault Structure
diff --git a/.config/omo/prompts/impeccable.md b/.config/omo/prompts/impeccable.md
new file mode 100644
index 0000000..0990c9a
--- /dev/null
+++ b/.config/omo/prompts/impeccable.md
@@ -0,0 +1,6 @@
+---
+description: Design, critique, audit, or polish a frontend interface with the impeccable skill
+argument-hint: "[shape · audit|critique · animate|bolder|colorize|delight|layout|overdrive|quieter|typeset · adapt|clarify|distill · harden|onboard|optimize|polish · init|document|extract|live|generate] [target]"
+requires-arguments: false
+---
+Read the impeccable skill at `~/.omo/agent/skills/impeccable/SKILL.md` and follow its `Setup` and `Commands` sections to handle: $ARGUMENTS
diff --git a/.config/opencode/command/ingest-notes.md b/.config/omo/prompts/ingest-notes.md
similarity index 99%
rename from .config/opencode/command/ingest-notes.md
rename to .config/omo/prompts/ingest-notes.md
index b40e7ae..73e144f 100644
--- a/.config/opencode/command/ingest-notes.md
+++ b/.config/omo/prompts/ingest-notes.md
@@ -1,7 +1,5 @@
 ---
 description: Ingest local documentation files to Obsidian vault
-agent: general
-subtask: true
 ---
 
 # Ingest Notes
diff --git a/.config/opencode/command/preview-notes-delegation.md b/.config/omo/prompts/preview-notes-delegation.md
similarity index 99%
rename from .config/opencode/command/preview-notes-delegation.md
rename to .config/omo/prompts/preview-notes-delegation.md
index 564af07..3427d2f 100644
--- a/.config/opencode/command/preview-notes-delegation.md
+++ b/.config/omo/prompts/preview-notes-delegation.md
@@ -1,7 +1,5 @@
 ---
 description: Preview which documentation files will be delegated to vault vs local
-agent: general
-subtask: true
 ---
 
 # Preview Notes Delegation
diff --git a/.config/opencode/command/reorganize-notes.md b/.config/omo/prompts/reorganize-notes.md
similarity index 99%
rename from .config/opencode/command/reorganize-notes.md
rename to .config/omo/prompts/reorganize-notes.md
index 5f7c9c6..811b57a 100644
--- a/.config/opencode/command/reorganize-notes.md
+++ b/.config/omo/prompts/reorganize-notes.md
@@ -1,7 +1,5 @@
 ---
 description: Reorganize vault with AI-assisted suggestions
-agent: general
-subtask: true
 ---
 
 # Reorganize Notes
diff --git a/.config/opencode/command/setup-notes.md b/.config/omo/prompts/setup-notes.md
similarity index 99%
rename from .config/opencode/command/setup-notes.md
rename to .config/omo/prompts/setup-notes.md
index 7a2774c..35b58cb 100644
--- a/.config/opencode/command/setup-notes.md
+++ b/.config/omo/prompts/setup-notes.md
@@ -1,7 +1,5 @@
 ---
 description: Intelligently analyze and setup documentation architecture for the project
-agent: general
-subtask: true
 ---
 
 # Intelligent Documentation Setup
diff --git a/.config/opencode/command/sync-notes.md b/.config/omo/prompts/sync-notes.md
similarity index 99%
rename from .config/opencode/command/sync-notes.md
rename to .config/omo/prompts/sync-notes.md
index 46f4798..2b92fc5 100644
--- a/.config/opencode/command/sync-notes.md
+++ b/.config/omo/prompts/sync-notes.md
@@ -1,7 +1,5 @@
 ---
 description: Bidirectionally sync documentation files between local project and Obsidian vault
-agent: general
-subtask: true
 ---
 
 # Sync Notes
diff --git a/.config/opencode/command/teleport-notes.md b/.config/omo/prompts/teleport-notes.md
similarity index 99%
rename from .config/opencode/command/teleport-notes.md
rename to .config/omo/prompts/teleport-notes.md
index 6f11f28..b6ed1ed 100644
--- a/.config/opencode/command/teleport-notes.md
+++ b/.config/omo/prompts/teleport-notes.md
@@ -1,7 +1,5 @@
 ---
 description: Teleport documentation files from Obsidian vault to local project
-agent: general
-subtask: true
 ---
 
 # Teleport Notes
diff --git a/.config/opencode/command/validate-notes-config.md b/.config/omo/prompts/validate-notes-config.md
similarity index 99%
rename from .config/opencode/command/validate-notes-config.md
rename to .config/omo/prompts/validate-notes-config.md
index b8a0c1e..e59c591 100644
--- a/.config/opencode/command/validate-notes-config.md
+++ b/.config/omo/prompts/validate-notes-config.md
@@ -1,7 +1,5 @@
 ---
 description: Validate .withcontextconfig.jsonc for errors and warnings
-agent: general
-subtask: true
 ---
 
 # Validate Notes Configuration
diff --git a/.config/omo/skills/README.md b/.config/omo/skills/README.md
new file mode 100644
index 0000000..a963ef2
--- /dev/null
+++ b/.config/omo/skills/README.md
@@ -0,0 +1,52 @@
+# Vendored agent skills
+
+These skills are vendored copies, not submodules. `link-ai-configs.sh` links every
+directory here into `~/.omo/agent/skills/`, and all of them except
+`frontend-workflow` into `~/.claude/skills/`, so OmO and Claude Code read one
+canonical source instead of divergent copies.
+
+They moved here from `.config/opencode/skills/` when OpenCode was retired; the
+OpenCode-era evaluation notes and rollback steps are in git history at
+`.config/opencode/README.md`.
+
+## Provenance
+
+| Skill | Upstream | Revision | License |
+|---|---|---|---|
+| `impeccable` | [pbakaus/impeccable](https://github.com/pbakaus/impeccable) (`.opencode` integration, skill 4.3.1) | `f2c7051853848826aac2f4646581d62a732155ad` | Apache 2.0, included |
+| `web-design-guidelines` | [vercel-labs/agent-skills](https://github.com/vercel-labs/agent-skills) (`skills/web-design-guidelines/SKILL.md`) | `063bee94c3f4df8453406c830b0a7df0f2860278` | per upstream |
+| ten marketing and copy skills | [coreyhaines31/marketingskills](https://github.com/coreyhaines31/marketingskills) (`skills/`) | `b9ba399dd88b082b926e261e8ccfb843d20aa066` | MIT, copied into each skill |
+| `frontend-workflow` | local | - | - |
+
+The ten marketing skills are `product-marketing`, `copywriting`, `copy-editing`,
+`emails`, `cold-email`, `content-strategy`, `seo-audit`, `ai-seo`, `launch` and
+`social`.
+
+## Local modifications
+
+- **`impeccable`**: every `.opencode/skills/impeccable/scripts/impeccable` command
+  path was rewritten to `~/.omo/agent/skills/impeccable/scripts/impeccable`,
+  including the `allowed-tools` Bash entry and the base-directory fallback in
+  `SKILL.md`. Without this the detector and live-server verbs do not resolve under
+  OmO. `reference/critique.md` also carries an OmO routing line that sends
+  Assessment A to the `design-critique-a` category and Assessment B to
+  `design-critique-b` (defined in `.config/omo/omo.jsonc`).
+- **`web-design-guidelines`**: unchanged. It fetches the current
+  [Web Interface Guidelines](https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md)
+  when invoked, so its rule feed is intentionally not pinned.
+- **marketing skills**: unchanged. They read a per-project
+  `.agents/product-marketing.md` for product context, and a project's own copy
+  skill overrides their generic direct-response advice. Links to the upstream
+  repo's top-level `tools/` directory were not vendored and resolve to nothing.
+
+## Upgrading
+
+Re-copy the same directories from a newer upstream revision, update the revision
+in the table above, then re-apply the local modifications listed for that skill
+and rerun `link-ai-configs.sh`. For `impeccable`, re-apply the path rewrite:
+
+```bash
+cd .config/omo/skills/impeccable
+rg -l -F '.opencode/skills/impeccable/scripts/impeccable' . \
+  | xargs sed -i '' 's#\.opencode/skills/impeccable/scripts/impeccable#~/.omo/agent/skills/impeccable/scripts/impeccable#g'
+```
diff --git a/.config/opencode/skills/ai-seo/LICENSE b/.config/omo/skills/ai-seo/LICENSE
similarity index 100%
rename from .config/opencode/skills/ai-seo/LICENSE
rename to .config/omo/skills/ai-seo/LICENSE
diff --git a/.config/opencode/skills/ai-seo/SKILL.md b/.config/omo/skills/ai-seo/SKILL.md
similarity index 100%
rename from .config/opencode/skills/ai-seo/SKILL.md
rename to .config/omo/skills/ai-seo/SKILL.md
diff --git a/.config/opencode/skills/ai-seo/evals/evals.json b/.config/omo/skills/ai-seo/evals/evals.json
similarity index 100%
rename from .config/opencode/skills/ai-seo/evals/evals.json
rename to .config/omo/skills/ai-seo/evals/evals.json
diff --git a/.config/opencode/skills/ai-seo/references/agent-readiness.md b/.config/omo/skills/ai-seo/references/agent-readiness.md
similarity index 100%
rename from .config/opencode/skills/ai-seo/references/agent-readiness.md
rename to .config/omo/skills/ai-seo/references/agent-readiness.md
diff --git a/.config/opencode/skills/ai-seo/references/citations-vs-recommendations.md b/.config/omo/skills/ai-seo/references/citations-vs-recommendations.md
similarity index 100%
rename from .config/opencode/skills/ai-seo/references/citations-vs-recommendations.md
rename to .config/omo/skills/ai-seo/references/citations-vs-recommendations.md
diff --git a/.config/opencode/skills/ai-seo/references/content-patterns.md b/.config/omo/skills/ai-seo/references/content-patterns.md
similarity index 100%
rename from .config/opencode/skills/ai-seo/references/content-patterns.md
rename to .config/omo/skills/ai-seo/references/content-patterns.md
diff --git a/.config/opencode/skills/ai-seo/references/content-types.md b/.config/omo/skills/ai-seo/references/content-types.md
similarity index 100%
rename from .config/opencode/skills/ai-seo/references/content-types.md
rename to .config/omo/skills/ai-seo/references/content-types.md
diff --git a/.config/opencode/skills/ai-seo/references/format-volatility.md b/.config/omo/skills/ai-seo/references/format-volatility.md
similarity index 100%
rename from .config/opencode/skills/ai-seo/references/format-volatility.md
rename to .config/omo/skills/ai-seo/references/format-volatility.md
diff --git a/.config/opencode/skills/ai-seo/references/linkedin-ai-citations.md b/.config/omo/skills/ai-seo/references/linkedin-ai-citations.md
similarity index 100%
rename from .config/opencode/skills/ai-seo/references/linkedin-ai-citations.md
rename to .config/omo/skills/ai-seo/references/linkedin-ai-citations.md
diff --git a/.config/opencode/skills/ai-seo/references/okf.md b/.config/omo/skills/ai-seo/references/okf.md
similarity index 100%
rename from .config/opencode/skills/ai-seo/references/okf.md
rename to .config/omo/skills/ai-seo/references/okf.md
diff --git a/.config/opencode/skills/ai-seo/references/platform-ranking-factors.md b/.config/omo/skills/ai-seo/references/platform-ranking-factors.md
similarity index 100%
rename from .config/opencode/skills/ai-seo/references/platform-ranking-factors.md
rename to .config/omo/skills/ai-seo/references/platform-ranking-factors.md
diff --git a/.config/opencode/skills/ai-seo/references/positioning-and-consensus.md b/.config/omo/skills/ai-seo/references/positioning-and-consensus.md
similarity index 100%
rename from .config/opencode/skills/ai-seo/references/positioning-and-consensus.md
rename to .config/omo/skills/ai-seo/references/positioning-and-consensus.md
diff --git a/.config/opencode/skills/ai-seo/references/youtube-ai-citations.md b/.config/omo/skills/ai-seo/references/youtube-ai-citations.md
similarity index 100%
rename from .config/opencode/skills/ai-seo/references/youtube-ai-citations.md
rename to .config/omo/skills/ai-seo/references/youtube-ai-citations.md
diff --git a/.config/opencode/skills/cold-email/LICENSE b/.config/omo/skills/cold-email/LICENSE
similarity index 100%
rename from .config/opencode/skills/cold-email/LICENSE
rename to .config/omo/skills/cold-email/LICENSE
diff --git a/.config/opencode/skills/cold-email/SKILL.md b/.config/omo/skills/cold-email/SKILL.md
similarity index 100%
rename from .config/opencode/skills/cold-email/SKILL.md
rename to .config/omo/skills/cold-email/SKILL.md
diff --git a/.config/opencode/skills/cold-email/evals/evals.json b/.config/omo/skills/cold-email/evals/evals.json
similarity index 100%
rename from .config/opencode/skills/cold-email/evals/evals.json
rename to .config/omo/skills/cold-email/evals/evals.json
diff --git a/.config/opencode/skills/cold-email/references/benchmarks.md b/.config/omo/skills/cold-email/references/benchmarks.md
similarity index 100%
rename from .config/opencode/skills/cold-email/references/benchmarks.md
rename to .config/omo/skills/cold-email/references/benchmarks.md
diff --git a/.config/opencode/skills/cold-email/references/deliverability.md b/.config/omo/skills/cold-email/references/deliverability.md
similarity index 100%
rename from .config/opencode/skills/cold-email/references/deliverability.md
rename to .config/omo/skills/cold-email/references/deliverability.md
diff --git a/.config/opencode/skills/cold-email/references/follow-up-sequences.md b/.config/omo/skills/cold-email/references/follow-up-sequences.md
similarity index 100%
rename from .config/opencode/skills/cold-email/references/follow-up-sequences.md
rename to .config/omo/skills/cold-email/references/follow-up-sequences.md
diff --git a/.config/opencode/skills/cold-email/references/frameworks.md b/.config/omo/skills/cold-email/references/frameworks.md
similarity index 100%
rename from .config/opencode/skills/cold-email/references/frameworks.md
rename to .config/omo/skills/cold-email/references/frameworks.md
diff --git a/.config/opencode/skills/cold-email/references/linkedin-outreach.md b/.config/omo/skills/cold-email/references/linkedin-outreach.md
similarity index 100%
rename from .config/opencode/skills/cold-email/references/linkedin-outreach.md
rename to .config/omo/skills/cold-email/references/linkedin-outreach.md
diff --git a/.config/opencode/skills/cold-email/references/multichannel-cadence.md b/.config/omo/skills/cold-email/references/multichannel-cadence.md
similarity index 100%
rename from .config/opencode/skills/cold-email/references/multichannel-cadence.md
rename to .config/omo/skills/cold-email/references/multichannel-cadence.md
diff --git a/.config/opencode/skills/cold-email/references/outbound-plays.md b/.config/omo/skills/cold-email/references/outbound-plays.md
similarity index 100%
rename from .config/opencode/skills/cold-email/references/outbound-plays.md
rename to .config/omo/skills/cold-email/references/outbound-plays.md
diff --git a/.config/opencode/skills/cold-email/references/personalization.md b/.config/omo/skills/cold-email/references/personalization.md
similarity index 100%
rename from .config/opencode/skills/cold-email/references/personalization.md
rename to .config/omo/skills/cold-email/references/personalization.md
diff --git a/.config/opencode/skills/cold-email/references/reply-handling.md b/.config/omo/skills/cold-email/references/reply-handling.md
similarity index 100%
rename from .config/opencode/skills/cold-email/references/reply-handling.md
rename to .config/omo/skills/cold-email/references/reply-handling.md
diff --git a/.config/opencode/skills/cold-email/references/subject-lines.md b/.config/omo/skills/cold-email/references/subject-lines.md
similarity index 100%
rename from .config/opencode/skills/cold-email/references/subject-lines.md
rename to .config/omo/skills/cold-email/references/subject-lines.md
diff --git a/.config/opencode/skills/content-strategy/LICENSE b/.config/omo/skills/content-strategy/LICENSE
similarity index 100%
rename from .config/opencode/skills/content-strategy/LICENSE
rename to .config/omo/skills/content-strategy/LICENSE
diff --git a/.config/opencode/skills/content-strategy/SKILL.md b/.config/omo/skills/content-strategy/SKILL.md
similarity index 100%
rename from .config/opencode/skills/content-strategy/SKILL.md
rename to .config/omo/skills/content-strategy/SKILL.md
diff --git a/.config/opencode/skills/content-strategy/evals/evals.json b/.config/omo/skills/content-strategy/evals/evals.json
similarity index 100%
rename from .config/opencode/skills/content-strategy/evals/evals.json
rename to .config/omo/skills/content-strategy/evals/evals.json
diff --git a/.config/opencode/skills/content-strategy/references/content-distribution.md b/.config/omo/skills/content-strategy/references/content-distribution.md
similarity index 100%
rename from .config/opencode/skills/content-strategy/references/content-distribution.md
rename to .config/omo/skills/content-strategy/references/content-distribution.md
diff --git a/.config/opencode/skills/content-strategy/references/headless-cms.md b/.config/omo/skills/content-strategy/references/headless-cms.md
similarity index 100%
rename from .config/opencode/skills/content-strategy/references/headless-cms.md
rename to .config/omo/skills/content-strategy/references/headless-cms.md
diff --git a/.config/opencode/skills/copy-editing/LICENSE b/.config/omo/skills/copy-editing/LICENSE
similarity index 100%
rename from .config/opencode/skills/copy-editing/LICENSE
rename to .config/omo/skills/copy-editing/LICENSE
diff --git a/.config/opencode/skills/copy-editing/SKILL.md b/.config/omo/skills/copy-editing/SKILL.md
similarity index 100%
rename from .config/opencode/skills/copy-editing/SKILL.md
rename to .config/omo/skills/copy-editing/SKILL.md
diff --git a/.config/opencode/skills/copy-editing/evals/evals.json b/.config/omo/skills/copy-editing/evals/evals.json
similarity index 100%
rename from .config/opencode/skills/copy-editing/evals/evals.json
rename to .config/omo/skills/copy-editing/evals/evals.json
diff --git a/.config/opencode/skills/copy-editing/references/checklist.md b/.config/omo/skills/copy-editing/references/checklist.md
similarity index 100%
rename from .config/opencode/skills/copy-editing/references/checklist.md
rename to .config/omo/skills/copy-editing/references/checklist.md
diff --git a/.config/opencode/skills/copy-editing/references/content-refresh.md b/.config/omo/skills/copy-editing/references/content-refresh.md
similarity index 100%
rename from .config/opencode/skills/copy-editing/references/content-refresh.md
rename to .config/omo/skills/copy-editing/references/content-refresh.md
diff --git a/.config/opencode/skills/copy-editing/references/plain-english-alternatives.md b/.config/omo/skills/copy-editing/references/plain-english-alternatives.md
similarity index 100%
rename from .config/opencode/skills/copy-editing/references/plain-english-alternatives.md
rename to .config/omo/skills/copy-editing/references/plain-english-alternatives.md
diff --git a/.config/opencode/skills/copywriting/LICENSE b/.config/omo/skills/copywriting/LICENSE
similarity index 100%
rename from .config/opencode/skills/copywriting/LICENSE
rename to .config/omo/skills/copywriting/LICENSE
diff --git a/.config/opencode/skills/copywriting/SKILL.md b/.config/omo/skills/copywriting/SKILL.md
similarity index 100%
rename from .config/opencode/skills/copywriting/SKILL.md
rename to .config/omo/skills/copywriting/SKILL.md
diff --git a/.config/opencode/skills/copywriting/evals/evals.json b/.config/omo/skills/copywriting/evals/evals.json
similarity index 100%
rename from .config/opencode/skills/copywriting/evals/evals.json
rename to .config/omo/skills/copywriting/evals/evals.json
diff --git a/.config/opencode/skills/copywriting/references/ai-tells.md b/.config/omo/skills/copywriting/references/ai-tells.md
similarity index 100%
rename from .config/opencode/skills/copywriting/references/ai-tells.md
rename to .config/omo/skills/copywriting/references/ai-tells.md
diff --git a/.config/opencode/skills/copywriting/references/copy-frameworks.md b/.config/omo/skills/copywriting/references/copy-frameworks.md
similarity index 100%
rename from .config/opencode/skills/copywriting/references/copy-frameworks.md
rename to .config/omo/skills/copywriting/references/copy-frameworks.md
diff --git a/.config/opencode/skills/copywriting/references/natural-transitions.md b/.config/omo/skills/copywriting/references/natural-transitions.md
similarity index 100%
rename from .config/opencode/skills/copywriting/references/natural-transitions.md
rename to .config/omo/skills/copywriting/references/natural-transitions.md
diff --git a/.config/opencode/skills/emails/LICENSE b/.config/omo/skills/emails/LICENSE
similarity index 100%
rename from .config/opencode/skills/emails/LICENSE
rename to .config/omo/skills/emails/LICENSE
diff --git a/.config/opencode/skills/emails/SKILL.md b/.config/omo/skills/emails/SKILL.md
similarity index 100%
rename from .config/opencode/skills/emails/SKILL.md
rename to .config/omo/skills/emails/SKILL.md
diff --git a/.config/opencode/skills/emails/evals/evals.json b/.config/omo/skills/emails/evals/evals.json
similarity index 100%
rename from .config/opencode/skills/emails/evals/evals.json
rename to .config/omo/skills/emails/evals/evals.json
diff --git a/.config/opencode/skills/emails/references/copy-guidelines.md b/.config/omo/skills/emails/references/copy-guidelines.md
similarity index 100%
rename from .config/opencode/skills/emails/references/copy-guidelines.md
rename to .config/omo/skills/emails/references/copy-guidelines.md
diff --git a/.config/opencode/skills/emails/references/email-types.md b/.config/omo/skills/emails/references/email-types.md
similarity index 100%
rename from .config/opencode/skills/emails/references/email-types.md
rename to .config/omo/skills/emails/references/email-types.md
diff --git a/.config/opencode/skills/emails/references/sequence-templates.md b/.config/omo/skills/emails/references/sequence-templates.md
similarity index 100%
rename from .config/opencode/skills/emails/references/sequence-templates.md
rename to .config/omo/skills/emails/references/sequence-templates.md
diff --git a/.config/opencode/skills/frontend-workflow/SKILL.md b/.config/omo/skills/frontend-workflow/SKILL.md
similarity index 92%
rename from .config/opencode/skills/frontend-workflow/SKILL.md
rename to .config/omo/skills/frontend-workflow/SKILL.md
index 1d74849..4795dfc 100644
--- a/.config/opencode/skills/frontend-workflow/SKILL.md
+++ b/.config/omo/skills/frontend-workflow/SKILL.md
@@ -30,7 +30,7 @@ Delegation handoff must include: purpose/action; context and reference paths; ap
 
 Run the affected build/type/tests. Start the app on loopback using its documented command. Inspect at desktop and mobile widths, with an intermediate width when breakpoints or layout complexity warrant it. Use product targets, or proposed defaults 1280×900, 390×844, and 768×900. Record URL, viewport, state, and screenshot path.
 
-After capture, check whether the tool response contains an actual image. If it returns only a path, use the native image-capable `read` tool to open the PNG, or attach it to the GPT session (`opencode run --model <existing-GPT-model> --file <screenshot> -- <inspection-prompt>`). Keep existing model identifiers; do not invent one. Describe concrete visible details to demonstrate receipt. DOM checks are complementary, not substitutes. If the model cannot see pixels, report the exact failing delivery step and do not claim visual QA.
+After capture, check whether the tool response contains an actual image. If it returns only a path, use the native image-capable `read` tool to open the PNG, or hand the screenshot path to a GPT worker through `task(category: "visual-engineering")` and have it open the PNG with its own image-capable `read` tool. Keep existing model identifiers; do not invent one. Describe concrete visible details to demonstrate receipt. DOM checks are complementary, not substitutes. If the model cannot see pixels, report the exact failing delivery step and do not claim visual QA.
 
 ## 5. Bounded critique and correction
 
diff --git a/.config/opencode/skills/frontend-workflow/references/dotfiles-workbench.md b/.config/omo/skills/frontend-workflow/references/dotfiles-workbench.md
similarity index 100%
rename from .config/opencode/skills/frontend-workflow/references/dotfiles-workbench.md
rename to .config/omo/skills/frontend-workflow/references/dotfiles-workbench.md
diff --git a/.config/opencode/skills/impeccable/LICENSE b/.config/omo/skills/impeccable/LICENSE
similarity index 100%
rename from .config/opencode/skills/impeccable/LICENSE
rename to .config/omo/skills/impeccable/LICENSE
diff --git a/.config/opencode/skills/impeccable/SKILL.md b/.config/omo/skills/impeccable/SKILL.md
similarity index 92%
rename from .config/opencode/skills/impeccable/SKILL.md
rename to .config/omo/skills/impeccable/SKILL.md
index 6599542..c38a5da 100644
--- a/.config/opencode/skills/impeccable/SKILL.md
+++ b/.config/omo/skills/impeccable/SKILL.md
@@ -7,7 +7,7 @@ argument-hint: "[shape · audit|critique · animate|bolder|colorize|delight|layo
 license: Apache 2.0
 allowed-tools:
   - Bash(npx impeccable *)
-  - Bash(.opencode/skills/impeccable/scripts/impeccable *)
+  - Bash(~/.omo/agent/skills/impeccable/scripts/impeccable *)
 ---
 
 This skill gives you the tools and permission to create design that earns to be called out-of-distribution craft: Whereas before, your design work would have been safe, timid and measured, you now approach every design task as an award-winning design director with impeccable understanding for what makes exceptional design work: production-grade code, peak creativity, a clear POV, deep understanding of the needs of the client and users, and exceptional craft.
@@ -19,7 +19,7 @@ Core principles:
 
 ## Setup
 
-1. Run `<skill-base-dir>/scripts/impeccable context` once per session, where `<skill-base-dir>` is the directory that contains this SKILL.md (the skill folder, not a plugin root two levels above it); keep cwd at the user's project. That base directory resolves every `.opencode/skills/impeccable/scripts/impeccable <verb>` command in this skill and its references, and `.opencode/skills/impeccable/scripts` is the fallback only when the runtime reports no base directory. On a Windows shell without `sh`, call `.opencode/skills/impeccable/scripts/impeccable.cmd` instead. The launcher runs a self-contained binary that ships next to it or is downloaded once on first run; no Node or other runtime is required. Pass a named source file or route as `--target <path>`. It loads PRODUCT.md, DESIGN.md, the matching surface brief, and native-platform guidance when applicable; follow its directives and do not rerun it.
+1. Run `<skill-base-dir>/scripts/impeccable context` once per session, where `<skill-base-dir>` is the directory that contains this SKILL.md (the skill folder, not a plugin root two levels above it); keep cwd at the user's project. That base directory resolves every `~/.omo/agent/skills/impeccable/scripts/impeccable <verb>` command in this skill and its references, and `~/.omo/agent/skills/impeccable/scripts` is the fallback only when the runtime reports no base directory. On a Windows shell without `sh`, call `~/.omo/agent/skills/impeccable/scripts/impeccable.cmd` instead. The launcher runs a self-contained binary that ships next to it or is downloaded once on first run; no Node or other runtime is required. Pass a named source file or route as `--target <path>`. It loads PRODUCT.md, DESIGN.md, the matching surface brief, and native-platform guidance when applicable; follow its directives and do not rerun it.
 2. Load the request's playbook: its Commands-table reference for an explicit/implied sub-command, or [reference/new-work.md](reference/new-work.md) for a new surface or replacement visual world. Inspect target and incumbent visual truth before editing. When the app cannot run, start with committed visual-regression goldens or screenshot fixtures; verify target and freshness against current tokens, CSS, components, or assets, resolve conflicts, and compare theme/variant captures.
 3. After resolving analysis and direction, read [reference/craft-floor.md](reference/craft-floor.md) immediately before any UI edit, including small refinements. It carries the quality floor, the absolute bans, and the reflexes no detector catches. Do not load it for planning-only work.
 
@@ -81,7 +81,7 @@ Routing:
 
 After init writes PRODUCT.md, resume without rerunning `impeccable context`; init loads the native platform reference itself when the platform it recorded is `ios`, `android`, or `adaptive`.
 
-**Pin / Unpin:** `.opencode/skills/impeccable/scripts/impeccable pin <pin|unpin> <command>` creates or removes a standalone `/<command>` shortcut. Report the script's result concisely; relay stderr verbatim on error.
+**Pin / Unpin:** `~/.omo/agent/skills/impeccable/scripts/impeccable pin <pin|unpin> <command>` creates or removes a standalone `/<command>` shortcut. Report the script's result concisely; relay stderr verbatim on error.
 
 **Hooks:** `/impeccable hooks <on|off|status|ignore-rule|ignore-file|ignore-value|reset>` manages the design detector hook for this project (auto-runs the detector after UI file edits and surfaces findings). Load [reference/hooks.md](reference/hooks.md) when the user invokes it with any argument.
 
diff --git a/.config/opencode/skills/impeccable/reference/adapt.md b/.config/omo/skills/impeccable/reference/adapt.md
similarity index 100%
rename from .config/opencode/skills/impeccable/reference/adapt.md
rename to .config/omo/skills/impeccable/reference/adapt.md
diff --git a/.config/opencode/skills/impeccable/reference/adapt.native.md b/.config/omo/skills/impeccable/reference/adapt.native.md
similarity index 100%
rename from .config/opencode/skills/impeccable/reference/adapt.native.md
rename to .config/omo/skills/impeccable/reference/adapt.native.md
diff --git a/.config/opencode/skills/impeccable/reference/android.md b/.config/omo/skills/impeccable/reference/android.md
similarity index 100%
rename from .config/opencode/skills/impeccable/reference/android.md
rename to .config/omo/skills/impeccable/reference/android.md
diff --git a/.config/opencode/skills/impeccable/reference/animate.md b/.config/omo/skills/impeccable/reference/animate.md
similarity index 100%
rename from .config/opencode/skills/impeccable/reference/animate.md
rename to .config/omo/skills/impeccable/reference/animate.md
diff --git a/.config/opencode/skills/impeccable/reference/audit.md b/.config/omo/skills/impeccable/reference/audit.md
similarity index 100%
rename from .config/opencode/skills/impeccable/reference/audit.md
rename to .config/omo/skills/impeccable/reference/audit.md
diff --git a/.config/opencode/skills/impeccable/reference/audit.native.md b/.config/omo/skills/impeccable/reference/audit.native.md
similarity index 100%
rename from .config/opencode/skills/impeccable/reference/audit.native.md
rename to .config/omo/skills/impeccable/reference/audit.native.md
diff --git a/.config/opencode/skills/impeccable/reference/bolder.md b/.config/omo/skills/impeccable/reference/bolder.md
similarity index 100%
rename from .config/opencode/skills/impeccable/reference/bolder.md
rename to .config/omo/skills/impeccable/reference/bolder.md
diff --git a/.config/opencode/skills/impeccable/reference/clarify.md b/.config/omo/skills/impeccable/reference/clarify.md
similarity index 100%
rename from .config/opencode/skills/impeccable/reference/clarify.md
rename to .config/omo/skills/impeccable/reference/clarify.md
diff --git a/.config/opencode/skills/impeccable/reference/colorize.md b/.config/omo/skills/impeccable/reference/colorize.md
similarity index 100%
rename from .config/opencode/skills/impeccable/reference/colorize.md
rename to .config/omo/skills/impeccable/reference/colorize.md
diff --git a/.config/opencode/skills/impeccable/reference/craft-floor.md b/.config/omo/skills/impeccable/reference/craft-floor.md
similarity index 100%
rename from .config/opencode/skills/impeccable/reference/craft-floor.md
rename to .config/omo/skills/impeccable/reference/craft-floor.md
diff --git a/.config/opencode/skills/impeccable/reference/craft.md b/.config/omo/skills/impeccable/reference/craft.md
similarity index 100%
rename from .config/opencode/skills/impeccable/reference/craft.md
rename to .config/omo/skills/impeccable/reference/craft.md
diff --git a/.config/opencode/skills/impeccable/reference/critique.md b/.config/omo/skills/impeccable/reference/critique.md
similarity index 98%
rename from .config/opencode/skills/impeccable/reference/critique.md
rename to .config/omo/skills/impeccable/reference/critique.md
index dedf037..03cdac0 100644
--- a/.config/opencode/skills/impeccable/reference/critique.md
+++ b/.config/omo/skills/impeccable/reference/critique.md
@@ -23,7 +23,7 @@ Resolve one stable target, run two independent assessments, synthesize a design
    - "this page" -> the current URL or source file
 2. **Confirm the target slugs cleanly**:
    ```bash
-   .opencode/skills/impeccable/scripts/impeccable critique-storage slug "<resolved-path-or-url>"
+   ~/.omo/agent/skills/impeccable/scripts/impeccable critique-storage slug "<resolved-path-or-url>"
    ```
    Every later command also accepts the resolved target directly and derives the same slug internally; never hand-write a slug. If this exits non-zero, skip persistence and trend for this run, but continue the critique.
 3. **Read `.impeccable/critique/ignore.md`** if it exists. Drop matching findings silently; it is the only prior-run input critique consumes.
@@ -61,7 +61,7 @@ Run the bundled detector and browser visualization evidence. Assessment B is man
 
 CLI scan:
 ```bash
-.opencode/skills/impeccable/scripts/impeccable detect --json [target]
+~/.omo/agent/skills/impeccable/scripts/impeccable detect --json [target]
 ```
 
 - Pass markup files/directories as `[target]`; do not pass CSS-only files.
@@ -75,7 +75,7 @@ Browser visualization is required for a viewable target when browser automation
 1. Create a fresh tab and navigate. Prefer the harness's native/browser-canvas screenshot path before hand-rolling a Playwright/Puppeteer script; only fall back to a custom script when no native browser tool is exposed.
 2. Preflight mutable injection by setting `document.title` and appending a `<script>` tag. Read-only evaluate APIs do not count.
 3. If mutation is unavailable, skip live server, browser presentation, and injection; report fallback signal.
-4. If mutation is available, start `.opencode/skills/impeccable/scripts/impeccable live-server --background`, present the browser if supported, label `[Human]`, scroll top, inject `http://localhost:PORT/detect.js`, wait 2-3 seconds, read `impeccable` console messages, then stop the live server.
+4. If mutation is available, start `~/.omo/agent/skills/impeccable/scripts/impeccable live-server --background`, present the browser if supported, label `[Human]`, scroll top, inject `http://localhost:PORT/detect.js`, wait 2-3 seconds, read `impeccable` console messages, then stop the live server.
 5. For multi-view targets, inject on 3-5 representative pages.
 
 Return: CLI findings JSON/counts, browser console findings if applicable, false positives, and skipped/failed browser steps with concrete reasons.
@@ -197,7 +197,7 @@ Skip this step if the Setup slug was null (vague or root-level target).
 2. **Pass the structured metadata** through `IMPECCABLE_CRITIQUE_META` (JSON), then run the write command:
    ```bash
    IMPECCABLE_CRITIQUE_META='{"target":"<user phrasing>","total_score":<n>,"max_score":<n>,"na_heuristics":"<comma-separated numbers, or empty>","p0_count":<n>,"p1_count":<n>}' \
-     .opencode/skills/impeccable/scripts/impeccable critique-storage write "<resolved target>" <body-file>
+     ~/.omo/agent/skills/impeccable/scripts/impeccable critique-storage write "<resolved target>" <body-file>
    ```
    `max_score` is the applicable maximum from the heuristic table (40 when every heuristic applied), so a later run can tell a renormalized total from a full one. For a local file target, the helper also records an exact content fingerprint so polish can distinguish the assessed bytes from later edits without relying on Git state or timestamps. The helper prints the absolute path it wrote. Leave that file on disk. Polish closes it; this run does not.
 
@@ -205,7 +205,7 @@ Skip this step if the Setup slug was null (vague or root-level target).
 
 4. **Read the trend** for context:
    ```bash
-   .opencode/skills/impeccable/scripts/impeccable critique-storage trend "<resolved target>" 5
+   ~/.omo/agent/skills/impeccable/scripts/impeccable critique-storage trend "<resolved target>" 5
    ```
    This returns a JSON array of the last 5 frontmatter entries (including the one you just wrote).
 
diff --git a/.config/opencode/skills/impeccable/reference/degraded/asset-producer.md b/.config/omo/skills/impeccable/reference/degraded/asset-producer.md
similarity index 84%
rename from .config/opencode/skills/impeccable/reference/degraded/asset-producer.md
rename to .config/omo/skills/impeccable/reference/degraded/asset-producer.md
index a4a4b19..70e5e54 100644
--- a/.config/opencode/skills/impeccable/reference/degraded/asset-producer.md
+++ b/.config/omo/skills/impeccable/reference/degraded/asset-producer.md
@@ -25,9 +25,9 @@ Every region with `medium: raster` in the spec ships as a plate at its `plate` p
 
 Per region, in the spec's order:
 
-1. `.opencode/skills/impeccable/scripts/impeccable comp-spec --crop <id>` writes the reference crop under `.impeccable/build/crops/`.
-2. Choose the background from the approved region: an isolated figure, object, or line drawing on the page ground is a **transparent cutout**; a photograph, full-frame illustration, or texture stays **opaque**. Save `.opencode/skills/impeccable/scripts/impeccable comp-spec --plate-prompt <id> --background transparent` to a UTF-8 prompt file for a cutout; use `--background opaque` otherwise. The transparent prompt preserves reference placement and clear margins, white paint, fine edges, and interior holes.
-3. Produce the plate at its exact spec `plate` path. Create the output directory first and choose a supported output size matching the region's aspect, at least 1.5x its pixel dimensions. Prefer the harness-native image tool with the crop as input and the saved prompt; request a transparent PNG for cutouts, then run `.opencode/skills/impeccable/scripts/impeccable embed-prompt <plate> --prompt-file <prompt.txt>` (if you refine the prompt, save and embed the exact text sent). With the API fallback, run `.opencode/skills/impeccable/scripts/impeccable generate-image --ref <crop.png> --prompt-file <prompt.txt> --out <plate.png> --size <WxH> --quality high --background transparent` for a cutout, or `--background opaque` otherwise. The API fallback embeds the prompt and records the background in the sidecar. The output must be PNG; the fallback requests native alpha and performs no chroma-keying.
+1. `~/.omo/agent/skills/impeccable/scripts/impeccable comp-spec --crop <id>` writes the reference crop under `.impeccable/build/crops/`.
+2. Choose the background from the approved region: an isolated figure, object, or line drawing on the page ground is a **transparent cutout**; a photograph, full-frame illustration, or texture stays **opaque**. Save `~/.omo/agent/skills/impeccable/scripts/impeccable comp-spec --plate-prompt <id> --background transparent` to a UTF-8 prompt file for a cutout; use `--background opaque` otherwise. The transparent prompt preserves reference placement and clear margins, white paint, fine edges, and interior holes.
+3. Produce the plate at its exact spec `plate` path. Create the output directory first and choose a supported output size matching the region's aspect, at least 1.5x its pixel dimensions. Prefer the harness-native image tool with the crop as input and the saved prompt; request a transparent PNG for cutouts, then run `~/.omo/agent/skills/impeccable/scripts/impeccable embed-prompt <plate> --prompt-file <prompt.txt>` (if you refine the prompt, save and embed the exact text sent). With the API fallback, run `~/.omo/agent/skills/impeccable/scripts/impeccable generate-image --ref <crop.png> --prompt-file <prompt.txt> --out <plate.png> --size <WxH> --quality high --background transparent` for a cutout, or `--background opaque` otherwise. The API fallback embeds the prompt and records the background in the sidecar. The output must be PNG; the fallback requests native alpha and performs no chroma-keying.
 4. Open the plate beside the crop and compare subject, placement, scale, palette, and style. For cutouts, verify a real alpha channel and inspect composites on light and dark grounds: white paint must stay solid, interior holes must clear, and fine edges must avoid halos. Inspect glass and soft shadows carefully; partial alpha alone does not ensure convincing translucency. Never chroma-key native transparent output or flatten it before saving. If a native tool returns opaque pixels or a painted checkerboard, retry with the API fallback when available; otherwise report the transparency blocker. On a visual miss, tighten the prompt and regenerate once. Two misses on one region: keep the better plate, mark it `needs_parent_review`, and name the drift. The parent runs the plates gate after all assets exist; report `unscored` until a gate score is available.
 
 Do not redesign. Do not add objects, restyle, or reinterpret; the comp was approved as it is. Do not touch the page code, the spec, or the comp. Do not produce anything the spec does not list; a region the parent forgot goes back as a one-line note, not a plate.
diff --git a/.config/opencode/skills/impeccable/reference/degraded/documenter.md b/.config/omo/skills/impeccable/reference/degraded/documenter.md
similarity index 100%
rename from .config/opencode/skills/impeccable/reference/degraded/documenter.md
rename to .config/omo/skills/impeccable/reference/degraded/documenter.md
diff --git a/.config/opencode/skills/impeccable/reference/degraded/finish-reviewer.md b/.config/omo/skills/impeccable/reference/degraded/finish-reviewer.md
similarity index 100%
rename from .config/opencode/skills/impeccable/reference/degraded/finish-reviewer.md
rename to .config/omo/skills/impeccable/reference/degraded/finish-reviewer.md
diff --git a/.config/opencode/skills/impeccable/reference/degraded/manual-edit-applier.md b/.config/omo/skills/impeccable/reference/degraded/manual-edit-applier.md
similarity index 100%
rename from .config/opencode/skills/impeccable/reference/degraded/manual-edit-applier.md
rename to .config/omo/skills/impeccable/reference/degraded/manual-edit-applier.md
diff --git a/.config/opencode/skills/impeccable/reference/delight.md b/.config/omo/skills/impeccable/reference/delight.md
similarity index 100%
rename from .config/opencode/skills/impeccable/reference/delight.md
rename to .config/omo/skills/impeccable/reference/delight.md
diff --git a/.config/opencode/skills/impeccable/reference/distill.md b/.config/omo/skills/impeccable/reference/distill.md
similarity index 100%
rename from .config/opencode/skills/impeccable/reference/distill.md
rename to .config/omo/skills/impeccable/reference/distill.md
diff --git a/.config/opencode/skills/impeccable/reference/doctor.md b/.config/omo/skills/impeccable/reference/doctor.md
similarity index 94%
rename from .config/opencode/skills/impeccable/reference/doctor.md
rename to .config/omo/skills/impeccable/reference/doctor.md
index 17d9741..ddfa1c7 100644
--- a/.config/opencode/skills/impeccable/reference/doctor.md
+++ b/.config/omo/skills/impeccable/reference/doctor.md
@@ -13,7 +13,7 @@ Three kinds of drift travel under "out of date". Keep them apart:
 ## Step 1: Run the pass
 
 ```
-.opencode/skills/impeccable/scripts/impeccable doctor --json
+~/.omo/agent/skills/impeccable/scripts/impeccable doctor --json
 ```
 
 Add `--target <path>` when the user named a workspace, file, or route in a monorepo. Without it the report describes the repo root, and in a monorepo that is often the wrong project.
@@ -26,7 +26,7 @@ An empty `findings` array is the good outcome. Say so in one line and stop.
 
 The severity says what should happen, not how bad it is.
 
-- **`auto`** carries no decision. Run `.opencode/skills/impeccable/scripts/impeccable doctor --fix` once to apply these, then report what it moved in one line. Do not ask permission first, and do not ask about them afterward.
+- **`auto`** carries no decision. Run `~/.omo/agent/skills/impeccable/scripts/impeccable doctor --fix` once to apply these, then report what it moved in one line. Do not ask permission first, and do not ask about them afterward.
 - **`mention`** needs the user to know but not to decide anything now. State each one in a sentence with its offered fix.
 - **`route`** needs a specific command. Name the command and the gap it would close. Run it only if the user asks in this turn; `init` and `document` are conversations, not repairs you perform unattended.
 
diff --git a/.config/opencode/skills/impeccable/reference/document.md b/.config/omo/skills/impeccable/reference/document.md
similarity index 100%
rename from .config/opencode/skills/impeccable/reference/document.md
rename to .config/omo/skills/impeccable/reference/document.md
diff --git a/.config/opencode/skills/impeccable/reference/extract.md b/.config/omo/skills/impeccable/reference/extract.md
similarity index 100%
rename from .config/opencode/skills/impeccable/reference/extract.md
rename to .config/omo/skills/impeccable/reference/extract.md
diff --git a/.config/opencode/skills/impeccable/reference/generate.md b/.config/omo/skills/impeccable/reference/generate.md
similarity index 92%
rename from .config/opencode/skills/impeccable/reference/generate.md
rename to .config/omo/skills/impeccable/reference/generate.md
index c9a7105..7510e63 100644
--- a/.config/opencode/skills/impeccable/reference/generate.md
+++ b/.config/omo/skills/impeccable/reference/generate.md
@@ -46,7 +46,7 @@ Done when you hold an action from the vocabulary (asked for, when the request na
    - **No browser tool** (Codex, others): run the start command with `--open --wait-for-browser 120000`; it opens the system browser, and the longer wait covers the user finding the tab. **`browser_open_failed` back**: tell the user the `url` in one line and rerun with `--wait-for-browser 120000`.
 
 ```bash
-.opencode/skills/impeccable/scripts/impeccable live-generate --target src/App.jsx --dev-url http://127.0.0.1:5173/ --selector ".pricing-grid" --action bolder --count 3 --boot --wait-for-browser 60000
+~/.omo/agent/skills/impeccable/scripts/impeccable live-generate --target src/App.jsx --dev-url http://127.0.0.1:5173/ --selector ".pricing-grid" --action bolder --count 3 --boot --wait-for-browser 60000
 ```
 
 Run it in the foreground in Cursor and Claude Code (it returns within the wait); on Codex, in an exec you yield from, the way Step 3 runs the poll.
@@ -63,7 +63,7 @@ Read the output in this order: `boot` (or `boot.contextMissing` with `boot.conte
 - **`dev_server_gone`**: the dev server stopped answering while the command waited for the page (on Cursor, a server another chat started dies with that chat). Start it the way the verdict says, then rerun with `--dev-url <url>`.
 - **`no_match`**: the tab is on a route that does not render the element (navigate to the right route, rerun), or the selector is wrong (derive a better one from the source, or add `--text`).
 - **`config_missing` / `config_invalid`** under `bootError`: follow [live-setup.md](live-setup.md) first, then rerun.
-- **`event: null`** with `ok: true`: the event was slower than the wait; run `.opencode/skills/impeccable/scripts/impeccable live-poll` once to collect it, then continue.
+- **`event: null`** with `ok: true`: the event was slower than the wait; run `~/.omo/agent/skills/impeccable/scripts/impeccable live-poll` once to collect it, then continue.
 
 Done when the output shows `ok: true`, a `sessionId`, and an `event`, reached with at most one server started and one tab opened by you.
 
@@ -74,7 +74,7 @@ The event is a standard `generate` event: the picked element's context, a prefli
 **Reply and wait in one call**, with the file you wrote:
 
 ```bash
-.opencode/skills/impeccable/scripts/impeccable live-poll --reply EVENT_ID done --file src/App.jsx --then-poll
+~/.omo/agent/skills/impeccable/scripts/impeccable live-poll --reply EVENT_ID done --file src/App.jsx --then-poll
 ```
 
 This replies done (the browser mounts the variants) and then blocks until the user's choice arrives, so run it the way your harness runs a long wait: **Claude Code** in the foreground with your tool's longest timeout (600000 ms), so you are paused until the choice arrives; **Codex** in a yielded foreground exec; **Cursor** in a background terminal with notify on `"type":"(accept|discard|variant_mount_failed|exit)"`. Never pass a short `--timeout=`. While it runs there is nothing else to do: never sleep and never poll its output on a timer; a harness that backgrounds it wakes you when it returns. `{"type":"timeout"}` means the user has not chosen yet: run `live-poll` again and keep waiting. If the edit fails after the browser flipped to GENERATING, `--reply EVENT_ID error "Short reason"` (without `--then-poll`) so the bar resets.
@@ -85,17 +85,17 @@ Outside the replace path, read the matching live.md section before acting: `scaf
 
 ## Step 4: Accept and close
 
-The call from Step 3 returns the user's choice. **`discard`**: nothing to do. **`accept`**: `_acceptResult.carbonize: true` is the normal case, and the cleanup is live.md's **Required after accept**, unchanged: move the accepted variant's rules into the stylesheet that already owns the element with real selectors, bake the chosen knob values in, unwrap the element and drop every `data-impeccable-*` attribute, delete the inline `<style>` block and both `impeccable-carbonize` markers, then `.opencode/skills/impeccable/scripts/impeccable live-complete --id SESSION_ID` and confirm `phase: "completed"`. (`baked: true` appears only when the accept was run with `--bake`; then the helper already made the variant permanent and no `live-complete` is owed.)
+The call from Step 3 returns the user's choice. **`discard`**: nothing to do. **`accept`**: `_acceptResult.carbonize: true` is the normal case, and the cleanup is live.md's **Required after accept**, unchanged: move the accepted variant's rules into the stylesheet that already owns the element with real selectors, bake the chosen knob values in, unwrap the element and drop every `data-impeccable-*` attribute, delete the inline `<style>` block and both `impeccable-carbonize` markers, then `~/.omo/agent/skills/impeccable/scripts/impeccable live-complete --id SESSION_ID` and confirm `phase: "completed"`. (`baked: true` appears only when the accept was run with `--bake`; then the helper already made the variant permanent and no `live-complete` is owed.)
 
 Close without being asked, the moment the choice is handled:
 
 ```bash
-.opencode/skills/impeccable/scripts/impeccable live-server stop
+~/.omo/agent/skills/impeccable/scripts/impeccable live-server stop
 ```
 
 Stopping removes the injected script and reloads the page once: the user sees the accepted design with no overlay chrome, still served by their dev server. **Never kill or restart the dev server**, including one you started in Step 2.
 
 - **The user asks for more variants before you closed**: skip the close, run Step 2 again for the next element (the helper is reused), and close after the last choice.
-- **Interrupted or unsure of the state**: `.opencode/skills/impeccable/scripts/impeccable live-status`, then `live-resume`; the journal under `.impeccable/live/sessions/` is canonical.
+- **Interrupted or unsure of the state**: `~/.omo/agent/skills/impeccable/scripts/impeccable live-status`, then `live-resume`; the journal under `.impeccable/live/sessions/` is canonical.
 
 Done when the helper is stopped and the dev site still answers with the accepted design.
diff --git a/.config/opencode/skills/impeccable/reference/harden.md b/.config/omo/skills/impeccable/reference/harden.md
similarity index 100%
rename from .config/opencode/skills/impeccable/reference/harden.md
rename to .config/omo/skills/impeccable/reference/harden.md
diff --git a/.config/opencode/skills/impeccable/reference/hooks.md b/.config/omo/skills/impeccable/reference/hooks.md
similarity index 93%
rename from .config/opencode/skills/impeccable/reference/hooks.md
rename to .config/omo/skills/impeccable/reference/hooks.md
index 6a9afc0..8620b49 100644
--- a/.config/opencode/skills/impeccable/reference/hooks.md
+++ b/.config/omo/skills/impeccable/reference/hooks.md
@@ -40,7 +40,7 @@ The first argument is the action. Defaults to `status`.
 2. Invoke the admin script and pass the user's output through verbatim:
 
    ```bash
-   .opencode/skills/impeccable/scripts/impeccable hooks <action> [args...]
+   ~/.omo/agent/skills/impeccable/scripts/impeccable hooks <action> [args...]
    ```
 
 3. If `<action>` is `off`, follow up with a one-line note: "Done. New edits will not trigger the design hook in this project until you run `/impeccable hooks on`."
@@ -70,32 +70,32 @@ Prefer the narrowest exception:
 Example value-specific exception:
 
 ```bash
-.opencode/skills/impeccable/scripts/impeccable hooks ignore-value overused-font Inter --shared --reason "User confirmed Inter is intentional"
+~/.omo/agent/skills/impeccable/scripts/impeccable hooks ignore-value overused-font Inter --shared --reason "User confirmed Inter is intentional"
 ```
 
 Example self-served exception, with the evidence named:
 
 ```bash
-.opencode/skills/impeccable/scripts/impeccable hooks ignore-value bounce-easing bounce-ball --shared --reason "Agent: literal ball-bounce animation, bounce easing is the subject"
+~/.omo/agent/skills/impeccable/scripts/impeccable hooks ignore-value bounce-easing bounce-ball --shared --reason "Agent: literal ball-bounce animation, bounce easing is the subject"
 ```
 
 Example whole-rule font exception:
 
 ```bash
-.opencode/skills/impeccable/scripts/impeccable hooks ignore-rule overused-font --all-values --reason "User asked to ignore overused fonts generally"
+~/.omo/agent/skills/impeccable/scripts/impeccable hooks ignore-rule overused-font --all-values --reason "User asked to ignore overused fonts generally"
 ```
 
 Example one-rule-in-one-file exception, for a file that is still worth reviewing
 for everything else:
 
 ```bash
-.opencode/skills/impeccable/scripts/impeccable hooks ignore-value design-system-font-size "*" --file "src/overlay/widget.js" --reason "Injected widget builds its own type scale; DESIGN.md's ramp describes the site"
+~/.omo/agent/skills/impeccable/scripts/impeccable hooks ignore-value design-system-font-size "*" --file "src/overlay/widget.js" --reason "Injected widget builds its own type scale; DESIGN.md's ramp describes the site"
 ```
 
 Example whole-file exception, for a file that is out of scope entirely:
 
 ```bash
-.opencode/skills/impeccable/scripts/impeccable hooks ignore-file "src/legacy/Card.tsx"
+~/.omo/agent/skills/impeccable/scripts/impeccable hooks ignore-file "src/legacy/Card.tsx"
 ```
 
 ## Constraints
diff --git a/.config/opencode/skills/impeccable/reference/init.md b/.config/omo/skills/impeccable/reference/init.md
similarity index 100%
rename from .config/opencode/skills/impeccable/reference/init.md
rename to .config/omo/skills/impeccable/reference/init.md
diff --git a/.config/opencode/skills/impeccable/reference/ios.md b/.config/omo/skills/impeccable/reference/ios.md
similarity index 100%
rename from .config/opencode/skills/impeccable/reference/ios.md
rename to .config/omo/skills/impeccable/reference/ios.md
diff --git a/.config/opencode/skills/impeccable/reference/layout.md b/.config/omo/skills/impeccable/reference/layout.md
similarity index 98%
rename from .config/opencode/skills/impeccable/reference/layout.md
rename to .config/omo/skills/impeccable/reference/layout.md
index 57ee422..6e76cff 100644
--- a/.config/opencode/skills/impeccable/reference/layout.md
+++ b/.config/omo/skills/impeccable/reference/layout.md
@@ -25,7 +25,7 @@ When a sub-agent tool is available and permitted, run these independently; other
 2. **Mechanical scan:** run:
 
 ```bash
-.opencode/skills/impeccable/scripts/impeccable detect --json --scope layout [target files or dirs]
+~/.omo/agent/skills/impeccable/scripts/impeccable detect --json --scope layout [target files or dirs]
 ```
 
 Also inspect arbitrary spacing, overflow, stacking, and container behavior the detector cannot resolve. Keep mechanical evidence out of the first assessment, then synthesize both passes before editing. A clean scan cannot prove hierarchy or rhythm.
diff --git a/.config/opencode/skills/impeccable/reference/live-setup.md b/.config/omo/skills/impeccable/reference/live-setup.md
similarity index 99%
rename from .config/opencode/skills/impeccable/reference/live-setup.md
rename to .config/omo/skills/impeccable/reference/live-setup.md
index 7af86b7..77f2aa3 100644
--- a/.config/opencode/skills/impeccable/reference/live-setup.md
+++ b/.config/omo/skills/impeccable/reference/live-setup.md
@@ -47,7 +47,7 @@ Keep all allowances below development-only, including manual middleware and meta
 If `config.cspChecked === true`, skip this whole section; the user was already asked once.
 
 ```bash
-.opencode/skills/impeccable/scripts/impeccable detect-csp
+~/.omo/agent/skills/impeccable/scripts/impeccable detect-csp
 ```
 
 Output `{ shape, signals }`; the shape names the *patch mechanism*, so one template covers many frameworks:
diff --git a/.config/opencode/skills/impeccable/reference/live.md b/.config/omo/skills/impeccable/reference/live.md
similarity index 92%
rename from .config/opencode/skills/impeccable/reference/live.md
rename to .config/omo/skills/impeccable/reference/live.md
index 64f0e79..0f2e282 100644
--- a/.config/opencode/skills/impeccable/reference/live.md
+++ b/.config/omo/skills/impeccable/reference/live.md
@@ -4,13 +4,13 @@ Interactive live variant mode: select elements in the browser, pick a design act
 
 A running dev server with HMR (Vite, Next.js, Bun, etc.), OR a static HTML file open in the browser. If the dev server's default port is busy, the app is very likely ALREADY running; probe the default URL before spawning a second server.
 
-Live editing requires a local checkout; injection into deployed production sites (including HTTPS) is unsupported. For production inspection, use `.opencode/skills/impeccable/scripts/impeccable detect <url>` or the browser extension, not the live helper. Do not disable browser security or weaken production CSP to enable live mode.
+Live editing requires a local checkout; injection into deployed production sites (including HTTPS) is unsupported. For production inspection, use `~/.omo/agent/skills/impeccable/scripts/impeccable detect <url>` or the browser extension, not the live helper. Do not disable browser security or weaken production CSP to enable live mode.
 
 ## The contract (read once)
 
 Execute in order. No step skipped, no step reordered. Every tool output in live mode may carry an `_instructions` field: it is the authoritative next step for that exact situation, with real ids and paths substituted; when it conflicts with your recollection of this document, `_instructions` wins.
 
-1. `impeccable live`: boot. If the request names or implies a file, route, or app inside a monorepo, infer the concrete path and run `.opencode/skills/impeccable/scripts/impeccable live --target <path>` instead; then run the rest of this live session from the returned `projectRoot`. The boot resolves the app root from dev-server config files and persists it in `.impeccable/live/roots.json`; every helper re-anchors to that manifest at startup (a wrong cwd cannot fork session state), PRODUCT.md / DESIGN.md are discovered upward to the git root, and relative helper args like `--file` resolve against the app root.
+1. `impeccable live`: boot. If the request names or implies a file, route, or app inside a monorepo, infer the concrete path and run `~/.omo/agent/skills/impeccable/scripts/impeccable live --target <path>` instead; then run the rest of this live session from the returned `projectRoot`. The boot resolves the app root from dev-server config files and persists it in `.impeccable/live/roots.json`; every helper re-anchors to that manifest at startup (a wrong cwd cannot fork session state), PRODUCT.md / DESIGN.md are discovered upward to the git root, and relative helper args like `--file` resolve against the app root.
 2. Open the app URL that serves `pageFile` (infer from `package.json`, docs, terminal output, or an open tab). Never use `serverPort`; it's the helper, not the app. **Cursor:** `browser_navigate` to that URL before polling; do not skip. **Other harnesses:** use the available browser tool; if the URL is uncertain, ask the user once.
 3. Poll loop with the default long timeout (600000 ms). Run `impeccable live-poll` again immediately after every event or `--reply`; Codex runs this one-shot poll in the foreground. Never pass a short `--timeout=`. The global bar's **Impeccable mark** dims with a pulsing amber dot when nothing is polling `/poll`; restart `impeccable live-poll` to reconnect.
 4. On `generate`: reuse `event.scaffold` when present; read the screenshot if present; load the action's reference; deliver variants; `--reply done`; poll again. Generate in this thread: you already hold the project's tokens and layout. The overlay preview IS the verification channel; do not screenshot, re-render, or QA variants between generate and accept. Apply craft-floor's contrast, spacing, and type floors by construction as you write; full verification runs once at accept on the chosen variant.
@@ -33,7 +33,7 @@ Chat is overhead. No recap, no tutorial output, no pasting PRODUCT / DESIGN bodi
 
 ```
 LOOP:
-  .opencode/skills/impeccable/scripts/impeccable live-poll   # default long timeout; no --timeout=
+  ~/.omo/agent/skills/impeccable/scripts/impeccable live-poll   # default long timeout; no --timeout=
   Read JSON; dispatch on "type"
 
   "generate"  → Handle Generate; reply done; LOOP
@@ -54,7 +54,7 @@ LOOP:
 ## Start
 
 ```bash
-.opencode/skills/impeccable/scripts/impeccable live
+~/.omo/agent/skills/impeccable/scripts/impeccable live
 ```
 
 Output JSON: `{ ok, serverPort, serverToken, pageFiles, roots, hasProduct, product, productPath, hasDesign, design, designPath, hasSurfaceBrief, surfaceBrief }`. `roots` is the resolved root manifest; `projectRoot` mirrors `roots.appRoot`. The surface brief rides along; do not shell out to `impeccable surface-brief` separately. Precedence for generation: **DESIGN.md wins on visual decisions; PRODUCT.md wins on durable product and voice decisions; the surface brief wins on this surface's strategy.** When DESIGN.md is missing, identity is **not** absent; extract it from CSS variables, computed styles, and sibling components (Step 4 Phase A). Identity preservation is the default; departure requires the user's explicit redesign intent.
@@ -68,9 +68,9 @@ If output is `{ ok: false, error: "config_missing" | "config_invalid", path }`,
 The append-only journal under `.impeccable/live/sessions/` is canonical durable state (not project source). When the chat was interrupted, polling was missed, the helper restarted, or the browser reloaded:
 
 ```bash
-.opencode/skills/impeccable/scripts/impeccable live-status      # helper state, active sessions, queued events; works with the helper down
-.opencode/skills/impeccable/scripts/impeccable live-resume --id SESSION_ID   # active snapshot, pending event, next safe action
-.opencode/skills/impeccable/scripts/impeccable live-complete --id SESSION_ID # canonical manual final acknowledgement after verified cleanup
+~/.omo/agent/skills/impeccable/scripts/impeccable live-status      # helper state, active sessions, queued events; works with the helper down
+~/.omo/agent/skills/impeccable/scripts/impeccable live-resume --id SESSION_ID   # active snapshot, pending event, next safe action
+~/.omo/agent/skills/impeccable/scripts/impeccable live-complete --id SESSION_ID # canonical manual final acknowledgement after verified cleanup
 ```
 
 Server restart rule: start `impeccable live-server` again, then poll; startup requeues unacknowledged events, so never ask the user to click Go again unless `impeccable live-resume` says no active session exists.
@@ -89,7 +89,7 @@ Speed matters; the user is watching the selected element. Reuse preflight metada
 2. If `event.scaffold` is present, use it and do **not** run the helper again. Otherwise:
 
 ```bash
-.opencode/skills/impeccable/scripts/impeccable live-insert --id EVENT_ID --count EVENT_COUNT --position after \
+~/.omo/agent/skills/impeccable/scripts/impeccable live-insert --id EVENT_ID --count EVENT_COUNT --position after \
   --element-id "ANCHOR_ID" --classes "class1,class2" --tag "section" --text "ANCHOR_TEXT"
 ```
 
@@ -110,7 +110,7 @@ When `event.scaffold` is present, the helper already found the source and comput
 **On source-preview targets `event.scaffold` carries `sourceWritten: false`.** The helper did NOT write the wrapper; it hands you `scaffold.wrapperBlock` plus the picked element's source range (`replaceStartLine`, `replaceEndLine`, 1-indexed). Write the wrapper **and** all variants in ONE edit: splice your variants into `wrapperBlock` at the "Variants: insert below this line" marker, then replace lines `[replaceStartLine, replaceEndLine]` with the result. A separate scaffold write reloads the framework before your variant write lands and strands the browser at 0/N. (`replaceEndLine < replaceStartLine` means insert mode: insert, remove nothing.) The `svelte-component` path never sets `sourceWritten`.
 
 ```bash
-.opencode/skills/impeccable/scripts/impeccable live-wrap --id EVENT_ID --count EVENT_COUNT --element-id "ELEMENT_ID" --classes "class1,class2" --tag "div" --text "TEXT_SNIPPET"
+~/.omo/agent/skills/impeccable/scripts/impeccable live-wrap --id EVENT_ID --count EVENT_COUNT --element-id "ELEMENT_ID" --classes "class1,class2" --tag "div" --text "TEXT_SNIPPET"
 ```
 
 Flag mapping (keep separate, never collapse into `--query`): `--element-id` ← `event.element.id`; `--classes` ← classes joined with commas; `--tag` ← tagName; `--text` ← first ~80 chars of textContent, **every call**: it disambiguates repeated sibling components, without it wrap lands on the first match. If `event.pageUrl` implies the file, pass `--file PATH`. If `--text` still matches several candidates, wrap exits `{ error: "element_ambiguous", candidates, fallback: "agent-driven" }`: pick the right range from page context and write the wrapper manually per the fallback flow.
@@ -242,14 +242,14 @@ Three kinds: `range` (slider; drives `--p-<id>`; author `var(--p-color-amount, 0
 ### 8. Signal done
 
 ```bash
-.opencode/skills/impeccable/scripts/impeccable live-poll --reply EVENT_ID done --file RELATIVE_PATH
+~/.omo/agent/skills/impeccable/scripts/impeccable live-poll --reply EVENT_ID done --file RELATIVE_PATH
 ```
 
 `RELATIVE_PATH` is relative to project root; the browser fetches source directly if the dev server lacks HMR. Then poll again immediately.
 
 ### Aborting an in-flight session
 
-If wrap or generation fails after the browser flipped to GENERATING, tell the **browser** so its bar resets: `.opencode/skills/impeccable/scripts/impeccable live-poll --reply EVENT_ID error "Short reason"`. Never use `live-accept --discard` for this (pure file mutator, browser never sees it, bar sticks on dots); `--discard` is only source-side cleanup for a discard the browser itself initiated.
+If wrap or generation fails after the browser flipped to GENERATING, tell the **browser** so its bar resets: `~/.omo/agent/skills/impeccable/scripts/impeccable live-poll --reply EVENT_ID error "Short reason"`. Never use `live-accept --discard` for this (pure file mutator, browser never sees it, bar sticks on dots); `--discard` is only source-side cleanup for a discard the browser itself initiated.
 
 ## Handle fallback
 
@@ -290,7 +290,7 @@ Event: `{id, _acceptResult, _completionAck}`. The poll script already restored t
 
 ## Handle `steer`
 
-Event: `{id, message, pageUrl}`: page-level direction from the global bar's Steer control (typed or spoken), no element context, no variant cycling. Read `message`, inspect the page or files as needed, make edits or answer in prose. Reply `.opencode/skills/impeccable/scripts/impeccable live-poll --reply EVENT_ID steer_done ["Optional short toast"]`, or on failure `--reply EVENT_ID error "Short reason"`, then poll immediately. No separate pickup reply; the Steer bar unlocks on `steer_done` or `error`.
+Event: `{id, message, pageUrl}`: page-level direction from the global bar's Steer control (typed or spoken), no element context, no variant cycling. Read `message`, inspect the page or files as needed, make edits or answer in prose. Reply `~/.omo/agent/skills/impeccable/scripts/impeccable live-poll --reply EVENT_ID steer_done ["Optional short toast"]`, or on failure `--reply EVENT_ID error "Short reason"`, then poll immediately. No separate pickup reply; the Steer bar unlocks on `steer_done` or `error`.
 
 ## Handle `prefetch`
 
@@ -306,7 +306,7 @@ When native subagents are available, delegate source edits to `impeccable_manual
 
 If `repair` is present, the previous Apply changed source but final validation failed. Fix the current source and return the same canonical JSON result; do not roll files back yourself. The browser will ask the user before any rollback.
 
-After source edits finish, reply exactly once with `.opencode/skills/impeccable/scripts/impeccable live-poll --reply EVENT_ID done --data '{"status":"done","appliedEntryIds":["8hexid"],"failed":[],"files":["src/page.html"],"notes":[]}'`. Use `status:"partial"` or `status:"error"` with `failed[]` when not every entry applied. Then poll again. Never reply without the event id; `--reply done --file ...` is invalid for manual Apply.
+After source edits finish, reply exactly once with `~/.omo/agent/skills/impeccable/scripts/impeccable live-poll --reply EVENT_ID done --data '{"status":"done","appliedEntryIds":["8hexid"],"failed":[],"files":["src/page.html"],"notes":[]}'`. Use `status:"partial"` or `status:"error"` with `failed[]` when not every entry applied. Then poll again. Never reply without the event id; `--reply done --file ...` is invalid for manual Apply.
 
 ## Exit
 
@@ -315,7 +315,7 @@ The user stops live mode by saying so in chat, closing the tab (SSE drops; poll
 ## Cleanup
 
 ```bash
-.opencode/skills/impeccable/scripts/impeccable live-server stop
+~/.omo/agent/skills/impeccable/scripts/impeccable live-server stop
 ```
 
 Stops the helper and runs `impeccable live-inject --remove` to strip the injected script (use `stop --keep-inject` to keep it for a quick restart; `.impeccable/live/config.json` persists as project config). Then search for and remove any leftover `impeccable-variants-start` wrappers and `impeccable-carbonize-start` blocks.
diff --git a/.config/opencode/skills/impeccable/reference/new-work.md b/.config/omo/skills/impeccable/reference/new-work.md
similarity index 88%
rename from .config/opencode/skills/impeccable/reference/new-work.md
rename to .config/omo/skills/impeccable/reference/new-work.md
index c8426e9..2e65583 100644
--- a/.config/opencode/skills/impeccable/reference/new-work.md
+++ b/.config/omo/skills/impeccable/reference/new-work.md
@@ -34,7 +34,7 @@ Inherit its world and composition. Resolve only the new purpose, content, hierar
 
 Keep the visual system fixed. Derive five to seven materially different structures from the content, task, and user behavior, ordered by resonance. For a genuinely open whole page, screen, or flow, run:
 
-`.opencode/skills/impeccable/scripts/impeccable concept-seed --scope surface --mode <mode>`
+`~/.omo/agent/skills/impeccable/scripts/impeccable concept-seed --scope surface --mode <mode>`
 
 The script deals three of your structures; the dice pick which three reach the user, breaking the ranking rut while the user keeps a real choice. Present them on the decision page as full cards of equal salience, the dealt lead under kicker THE ROLL, with steer and re-roll; the user locks one. No canon card and no pick card at surface scope: the world is settled, so every card visualizes composition, not identity. With image generation and a comp-led default (`.impeccable/config.json`; the build-path paragraph below), each card declares a `comp` under `.impeccable/mocks/decision/`, generated after serving, in reading order, under [visualize.md](visualize.md)'s comp discipline. Anchor each comp on the established identity: pass a screenshot of a representative existing page as a reference image (the harness image tool's input image, or `impeccable generate-image --ref`) with a prompt that leads with the new surface's structure and names DESIGN.md's palette, type, and component character; prose paraphrases of a design system drift, pixel references do not. Without image generation, or under a code-led default, each card carries a `wireframe` schematic (`impeccable serve-question --schema`) the page draws itself. Locking a card is the approval and sets the build path: a locked comp builds comp-led with that comp as the approved comp, discharging [visualize.md](visualize.md)'s three-option round with no second approval point; a locked wireframe builds code-led, its ambition carried by the direction contract. Never run the script for a local extension or a precisely specified narrow request; shape those directly.
 
@@ -43,10 +43,10 @@ The script deals three of your structures; the dice pick which three reach the u
 1. Name the product's unique mechanism in one sentence, the audience's real scene, its cultural home, and what this first surface must prove. Note the page this category always ships and its predictable opposite; both are the rut, kept out of the seven-candidate list. A brief that paints its own picture, a product name, a titled artifact, a governing metaphor, adds its literal reading to the rut: spend at most one candidate on it and derive the rest from elsewhere in the audience's world.
 2. From that cultural world, list seven concrete visual systems, artifacts, places, or rituals the audience knows by heart, each with one line on why it resonates and can carry the mechanism, ordered by resonance. The audience's world includes its graphic and screen traditions, not only its physical objects: the notation, publications, identity programs, data graphics, and interfaces it reads daily. A nameable abstract system (a school of poster, a documentation standard) is as concrete a candidate as any artifact. What would this thing look like as a physical object; what did its world look like before the web? Near-duplicates count once. When more than three of the seven share one material family, the derivation stopped at the subject's most obvious artifact; dig until the list spans at least three families.
 3. Turn that material into complete directions: each joins a reusable visual world to a concrete first-surface experience.
-4. Run `.opencode/skills/impeccable/scripts/impeccable concept-seed --scope direction --mode <mode>` and follow what it prints. No substitute, no skip: on a new or replacement world, writing artifact code before this script has run and its assignment is acknowledged is a contract violation, whatever the harness, the model, or the time pressure; the roll is what keeps every run from converging on the category default. The script assigns the direction to build and deals catalog challengers. Fuse each challenger before judging it: the challenger supplies the form and its system grammar, the product supplies every fact, clarity wins conflicts. Weigh fused challengers against the assigned direction on exactly two axes, audience identification and product clarity. Losing to strong grounded material is a valid outcome; beating a thin or tool-monoculture list is the point. Close with a verdict per challenger, decided before any borrowing: wins (beats the assigned direction on both axes; becomes the build candidate), competitive (holds one axis; stays a full alternate), or declined (loses both). A declined challenger is not spent: name the one discipline of its system the assigned direction lacks, and raise the assigned direction to match before presenting it. A donation transfers ambition and system discipline (a palette's total commitment, a grid's density courage, a form's structural honesty), never the challenger's clothes; a lifted motif is a costume note, not a raise, and one world owns the page. Write each raise into the presented direction as its own line, named for its donor; a raise nobody can read did not happen.
+4. Run `~/.omo/agent/skills/impeccable/scripts/impeccable concept-seed --scope direction --mode <mode>` and follow what it prints. No substitute, no skip: on a new or replacement world, writing artifact code before this script has run and its assignment is acknowledged is a contract violation, whatever the harness, the model, or the time pressure; the roll is what keeps every run from converging on the category default. The script assigns the direction to build and deals catalog challengers. Fuse each challenger before judging it: the challenger supplies the form and its system grammar, the product supplies every fact, clarity wins conflicts. Weigh fused challengers against the assigned direction on exactly two axes, audience identification and product clarity. Losing to strong grounded material is a valid outcome; beating a thin or tool-monoculture list is the point. Close with a verdict per challenger, decided before any borrowing: wins (beats the assigned direction on both axes; becomes the build candidate), competitive (holds one axis; stays a full alternate), or declined (loses both). A declined challenger is not spent: name the one discipline of its system the assigned direction lacks, and raise the assigned direction to match before presenting it. A donation transfers ambition and system discipline (a palette's total commitment, a grid's density courage, a form's structural honesty), never the challenger's clothes; a lifted motif is a costume note, not a raise, and one world owns the page. Write each raise into the presented direction as its own line, named for its donor; a raise nobody can read did not happen.
 5. Present one direction, fully committed and already raised by the hand it beat, raises visible as named lines: world, first viewport, visitor path, signature interaction, cross-surface reach, honest risk. Route each challenger by verdict: winning and competitive challengers are full alternates with their QUALITY BAR cards and one-line case; declined challengers render demoted, compact and quiet, each carrying its verdict and what the direction kept from it, never full-size, never silently dropped, still adoptable on request. The verdict informs the user's choice, never pre-empts it; the demoted row is the hand's proof of judgment. A hand holds at most three full-card challengers: when the roll deals more, the three strongest join and the rest wait in the re-roll pool, noted in one line; dropping a challenger from the hand itself takes a named product-truth failure, disclosed. Add one card for your own top-ranked grounded candidate when it is not the assigned direction, kicker IMPECCABLE’S PICK, same anatomy as every card, with an honest risk line naming its familiarity when true: the strongest grounded direction is often where most runs in this category land, and the user deciding that trade is the point of showing it. Familiar and effective is a legitimate destination, not a failure of nerve; the pick card and the standing exit serve it at two depths. One pick card, never two, never a ranked list: a lineup of your candidates hands selection back to a taste function and invites the safest card. The pick never takes the lead position; when the dice assign your top candidate there is no pick card, and the assigned card notes it topped your list. Add re-roll with an optional one-line steer, in three registers: plain (a fresh hand, same spread), safer (your remaining conventional grounded candidates plus the canon against named competitors), bolder (foreign forms only, at full commitment). The register is the user's steering on the familiar-to-bold axis, never yours to pre-select; when the answer carries one, re-run the seed with `--register <value>` and the next `--reroll` round, and follow what it prints. A user saying "bolder" or "safer" while a direction round is open means these registers, never the bolder or harden commands. The two channels share this structure and differ only in richness: cards and boards on the decision page, names and one-liners through the structured tool, whose option list carries the assigned direction, the pick, the winning and competitive challengers, and the standing exit last; declined challengers fold into the assigned option's description as their kept lines, so the raise survives the text channel.
 
-The standing exit: every direction round offers one quiet, permanent alternative, the category standard, played straight. It is the user's door, never yours: never recommend it, never weigh it against the roll, never let it soften the dealt directions; the counterweights bind the unchosen default, not the chosen one. When the user takes it (the canon action, a safer-steer, or plain words asking for the familiar or competitor-like path), convention becomes the commitment: ask once for two or three products this should sit alongside, make their craft level the bar, and execute the canon at full fidelity, without irony or smuggled quirk. Record a standing preference as a brand commitment in PRODUCT.md. Re-roll eliminates every direction already shown, grounded and challenger alike; after two consecutive re-rolls, ask what quality is missing. Re-roll on your own only on named factual grounds, when the assigned direction cannot carry the product's truth or task; taste is never grounds. The user may re-roll freely, and a user- or brief-pinned direction beats the roll, always. Resolve collisions field by field: preserve every user- or brief-pinned constraint. In dimensions the brief leaves open, the assignment still binds through its topology, controls, state vocabulary, and ritual; when only its materials conflict with a pinned visual direction or PRODUCT.md brand commitment, translate that material expression and name the translation in the presented direction. A look mismatch is not grounds to re-roll. Present the decision visually: write an options payload with the assigned direction leading, its raised lines included; the pick card when one exists; the dealt challengers as alternates with their QUALITY BAR cards, verdicts, and kept lines; re-roll with its safer and bolder registers; steer; canon enabled; and `buildPath` carrying the recorded default with `toggle: true` whenever image generation exists (details in the build-path paragraph below). A degraded roll with no challengers still uses the page, as a single text-only card with re-roll. Give every card the same anatomy: thesis, palette, materials, first viewport, honest risk, and the challengers' case lines (`--schema` prints the exact shape); the page renders identity from these fields, demotes declined challengers to their row on its own, and a challenger's catalog image rides as labeled inspiration, never the promise of the build. Author `canonCard` too: the category standard as one honest card, same anatomy; the page keeps it subordinate, and the counterweights still bind you. Run `.opencode/skills/impeccable/scripts/impeccable serve-question --start --payload <file>` (`--schema` first for the payload shape). It daemonizes, prints the page URL and a key, and exits; open that URL for the user, in-app browser first, then the system opener, then showing the URL. Collect the choice with `--wait --key <key>`, repeating while it exits 3; the ANSWER prints as JSON. An ANSWER of `{"optionId":"reroll"}` keeps the server alive and the page open on a loading hand: rerun concept-seed with the same `--scope` and `--mode` plus `--from <seed-key> --reroll <n>` (1 on the first re-roll, counting up), build the next payload, deliver it with `--update --key <same key> --payload <file>`, then return to `--wait` on that key. Never `--start` a second server or fall back to chat here: either strands the open tab on a hand that never arrives. Exit 4 means the page closed unanswered: re-present once through the structured question tool, and with no answer there either, proceed unattended with the assigned direction and state the assumptions. A harness that can leave a shell blocked in the background may run the script without `--start` and let it auto-open and block. Never predict the fallback: run the script, and only exit code 2 from starting it routes the decision to the structured tool; that exit is the fallback, never an error to retry.
+The standing exit: every direction round offers one quiet, permanent alternative, the category standard, played straight. It is the user's door, never yours: never recommend it, never weigh it against the roll, never let it soften the dealt directions; the counterweights bind the unchosen default, not the chosen one. When the user takes it (the canon action, a safer-steer, or plain words asking for the familiar or competitor-like path), convention becomes the commitment: ask once for two or three products this should sit alongside, make their craft level the bar, and execute the canon at full fidelity, without irony or smuggled quirk. Record a standing preference as a brand commitment in PRODUCT.md. Re-roll eliminates every direction already shown, grounded and challenger alike; after two consecutive re-rolls, ask what quality is missing. Re-roll on your own only on named factual grounds, when the assigned direction cannot carry the product's truth or task; taste is never grounds. The user may re-roll freely, and a user- or brief-pinned direction beats the roll, always. Resolve collisions field by field: preserve every user- or brief-pinned constraint. In dimensions the brief leaves open, the assignment still binds through its topology, controls, state vocabulary, and ritual; when only its materials conflict with a pinned visual direction or PRODUCT.md brand commitment, translate that material expression and name the translation in the presented direction. A look mismatch is not grounds to re-roll. Present the decision visually: write an options payload with the assigned direction leading, its raised lines included; the pick card when one exists; the dealt challengers as alternates with their QUALITY BAR cards, verdicts, and kept lines; re-roll with its safer and bolder registers; steer; canon enabled; and `buildPath` carrying the recorded default with `toggle: true` whenever image generation exists (details in the build-path paragraph below). A degraded roll with no challengers still uses the page, as a single text-only card with re-roll. Give every card the same anatomy: thesis, palette, materials, first viewport, honest risk, and the challengers' case lines (`--schema` prints the exact shape); the page renders identity from these fields, demotes declined challengers to their row on its own, and a challenger's catalog image rides as labeled inspiration, never the promise of the build. Author `canonCard` too: the category standard as one honest card, same anatomy; the page keeps it subordinate, and the counterweights still bind you. Run `~/.omo/agent/skills/impeccable/scripts/impeccable serve-question --start --payload <file>` (`--schema` first for the payload shape). It daemonizes, prints the page URL and a key, and exits; open that URL for the user, in-app browser first, then the system opener, then showing the URL. Collect the choice with `--wait --key <key>`, repeating while it exits 3; the ANSWER prints as JSON. An ANSWER of `{"optionId":"reroll"}` keeps the server alive and the page open on a loading hand: rerun concept-seed with the same `--scope` and `--mode` plus `--from <seed-key> --reroll <n>` (1 on the first re-roll, counting up), build the next payload, deliver it with `--update --key <same key> --payload <file>`, then return to `--wait` on that key. Never `--start` a second server or fall back to chat here: either strands the open tab on a hand that never arrives. Exit 4 means the page closed unanswered: re-present once through the structured question tool, and with no answer there either, proceed unattended with the assigned direction and state the assumptions. A harness that can leave a shell blocked in the background may run the script without `--start` and let it auto-open and block. Never predict the fallback: run the script, and only exit code 2 from starting it routes the decision to the structured tool; that exit is the fallback, never an error to retry.
 
 When image generation exists, every card also declares a `comp` path under `.impeccable/mocks/decision/`, the canon card included. Where the harness sandboxes its shell, start the page through the least-sandboxed command path it offers: a sandboxed shell cannot bind the board's port, and the first-attempt failure costs a retry every session. Serve the page first, then produce the comps; the page shimmer-waits per slot and the user may answer before they land. Each card's image is that direction's north-star comp at full fidelity under [visualize.md](visualize.md)'s comp discipline: the requested surface's first viewport, structure-led prompt, real product name and real content, no invented commercial claims, in that card's own palette, type character, and material world, committed all the way. Generation takes the same time at any fidelity, so an unfinished draft pays comp cost for draft quality; fairness between cards is equal fidelity in each card's own grammar, one surface, one aspect, never shared unfinishedness. The frame's aspect is the surface's own: portrait at device viewport for a native app or mobile-first surface, landscape for desktop web; the decision page adapts to either, and a phone screen comped landscape is a broken frame, not a neutral default. Produce in reading order, the assigned card, then the pick, then the full-card hand, then canon, each file written with its prompt sidecar the moment it is done, so a re-roll's spend front-loads onto the cards read first; declined challengers get no comp, their catalog thumb is their face. With parallel subagents, fan out one agent per card: each spawn is the shipped asset producer with a single-comp packet, that card's fields, PRODUCT.md, the shared frame, and the card's declared path, up to four in flight. Regenerate inline any slot still empty when its agent returns; drop without ceremony any slot still empty when the user answers. No other supervision is owed. Without parallel subagents, generate in the main thread after serving, same order, and let the harness's own generation display carry the progress; the wait for the answer follows the last file. The chosen card's comp is not spent by the choice: comp-led, it enters the comp round as compositional option one; code-led, it returns at the finish review as the critique reference, what the image dared that the build did not. Unchosen comps stay in `.impeccable/mocks/decision/` as the round's spent hand; they carry no approval and imply none. With no image generation, cards carry their identity in palette chips and facts, and that page is complete, not a lesser version; the page then also demotes every challenger's catalog art to a labeled thumbnail on its own, because salience must encode the verdict, never the accident of which cards have images.
 
@@ -76,9 +76,9 @@ On a new or replacement world, DESIGN.md is written at finish, from the built wo
 
 Read the existing surface brief before updating it:
 
-`.opencode/skills/impeccable/scripts/impeccable surface-brief read <primary-target>`
+`~/.omo/agent/skills/impeccable/scripts/impeccable surface-brief read <primary-target>`
 
-`.opencode/skills/impeccable/scripts/impeccable surface-brief write <primary-target> <body-file> [related-target ...]`
+`~/.omo/agent/skills/impeccable/scripts/impeccable surface-brief write <primary-target> <body-file> [related-target ...]`
 
 After writing, read the brief once more and verify that all six contract blocks and the seed key are present before building.
 
@@ -96,9 +96,9 @@ Build the assigned direction, not a safer interpretation of it. The form supplie
 
 When an approved comp exists, it is a spatial contract, not a mood board: only the user can downgrade its authority, in explicit words. Models systematically believe their HTML, CSS, and SVG recreation of an image succeeded when it did not, so the build runs as a state machine on disk whose gates measure the screen against the comp instead of asking you to remember it. Start it once, and let it tell you what is next:
 
-`.opencode/skills/impeccable/scripts/impeccable build-phase start --direction <seed key> --kind <assigned|pick|challenger|canon>` right after the direction choice (this is also the choice ping; the roll's output names the exact command), or `start --comp <approved comp>` when a surface round already locked one.
+`~/.omo/agent/skills/impeccable/scripts/impeccable build-phase start --direction <seed key> --kind <assigned|pick|challenger|canon>` right after the direction choice (this is also the choice ping; the roll's output names the exact command), or `start --comp <approved comp>` when a surface round already locked one.
 
-Then, in order, each closed by `.opencode/skills/impeccable/scripts/impeccable build-phase advance` (every verb below runs as `.opencode/skills/impeccable/scripts/impeccable <verb>`; exit 2 means the gate failed and printed why; fix that and advance again; write nothing for a later phase while an earlier gate is open):
+Then, in order, each closed by `~/.omo/agent/skills/impeccable/scripts/impeccable build-phase advance` (every verb below runs as `~/.omo/agent/skills/impeccable/scripts/impeccable <verb>`; exit 2 means the gate failed and printed why; fix that and advance again; write nothing for a later phase while an earlier gate is open):
 
 0. **comps.** The comp round from [visualize.md](visualize.md): three compositional comps of the requested surface at its own viewport under `.impeccable/mocks/`, each with a prompt sidecar, put in front of the user; the chosen one's sidecar gets `"approved": true`. The gate counts them and reads the approval; a `start --comp` skips this phase because it already happened.
 The comp-led path is a frontier-tier job: it asks the builder to hold a measured layout, place plates at their boxes, and act on numeric readings across a dozen attempts. Smaller or faster models produce a recognisable page and stall under the hero gate; if the model in hand is one of those, say so before the direction round and take the code-led path, or expect the run to end at the hero with its readings unmet.
@@ -128,17 +128,17 @@ Preserve semantics, accessibility, performance, responsiveness, project conventi
 
 ## 7. Inspect and finish
 
-Inspect the surface's target sizes in one batched screenshot round: desktop and mobile on the web; on a native platform (`ios` / `android` / `adaptive`), the shipped device classes per OS, captured from the simulator or emulator the way the platform reference's Verifying the build section describes. When the harness reports the user's actual viewport (an in-app browser's size, a named resolution), add that width to the set: the width that breaks is the one the user sees first. Critique the render against the user's request and the direction contract, fix material gaps, and confirm with one final round; two rounds is the ceiling, and fixes batch between them rather than earning per-tweak screenshots. On a comp-led build, run `.opencode/skills/impeccable/scripts/impeccable comp-diff --comp <approved comp> --build .impeccable/review/desktop.png --spec .impeccable/build/spec.json --out-dir .impeccable/review/diff/final` and read its region rows and paired crops as the critique: the side-by-side is the view the build thread never has on its own, and a region it scores missing or contradicted is a fix whatever the page looks like from memory. Never judge fidelity from one full-page thumbnail; it hides exactly the failures that matter. On a Persuade surface, verify the mode did its job: a first-time visitor should know what this is, why it matters, and what to do within seconds, in the form's own vocabulary.
+Inspect the surface's target sizes in one batched screenshot round: desktop and mobile on the web; on a native platform (`ios` / `android` / `adaptive`), the shipped device classes per OS, captured from the simulator or emulator the way the platform reference's Verifying the build section describes. When the harness reports the user's actual viewport (an in-app browser's size, a named resolution), add that width to the set: the width that breaks is the one the user sees first. Critique the render against the user's request and the direction contract, fix material gaps, and confirm with one final round; two rounds is the ceiling, and fixes batch between them rather than earning per-tweak screenshots. On a comp-led build, run `~/.omo/agent/skills/impeccable/scripts/impeccable comp-diff --comp <approved comp> --build .impeccable/review/desktop.png --spec .impeccable/build/spec.json --out-dir .impeccable/review/diff/final` and read its region rows and paired crops as the critique: the side-by-side is the view the build thread never has on its own, and a region it scores missing or contradicted is a fix whatever the page looks like from memory. Never judge fidelity from one full-page thumbnail; it hides exactly the failures that matter. On a Persuade surface, verify the mode did its job: a first-time visitor should know what this is, why it matters, and what to do within seconds, in the form's own vocabulary.
 
 A capture is evidence only when it is valid, and you validate before you send. Settle or disable entrance motion first: an element hidden by animation timing reads as a missing element and gets fixed into a regression. Capture full-page shots from the document top. Capture the comp comparison at the comp's own pixel dimensions. Then open every file once and confirm it shows what its name claims: no black or blank regions, no wrong section behind a right filename, no half-loaded state. A malformed capture sent onward costs the whole round; the reviewer answers it with `disposition: recapture` and nothing it reviewed binds.
 
-After the second inspection round the build thread's polishing is over: no further defect hunts, micro-edit scripts, or rebuilds here; whatever remains ships through the handoffs, where a fresh context does the finding better and cheaper. On the web, where this harness runs no design hook, run `.opencode/skills/impeccable/scripts/impeccable detect --json` on the changed targets once here, fix what is mechanical, and pass the remaining findings to the reviewer; a hookless web build that skips this ships every tell the hook exists to catch. A native platform skips the detector entirely: it reads HTML and CSS and has no verdict on native code, so the reviewer's floor check is the only slop gate and the input packet says so. Capture the screenshots into `.impeccable/review/`, one file per captured viewport (on the web, `desktop.png` and `mobile.png`, plus `user-<width>.png` whenever the user's viewport joined the inspected set; on native, one per device class, such as `phone.png` and `tablet.png`, suffixed per OS on adaptive), creating that directory when the harness does not; the paths you pass the reviewer are its spec, every viewport you inspected is named required in the packet, and that directory is where it looks when a passed path is missing.
+After the second inspection round the build thread's polishing is over: no further defect hunts, micro-edit scripts, or rebuilds here; whatever remains ships through the handoffs, where a fresh context does the finding better and cheaper. On the web, where this harness runs no design hook, run `~/.omo/agent/skills/impeccable/scripts/impeccable detect --json` on the changed targets once here, fix what is mechanical, and pass the remaining findings to the reviewer; a hookless web build that skips this ships every tell the hook exists to catch. A native platform skips the detector entirely: it reads HTML and CSS and has no verdict on native code, so the reviewer's floor check is the only slop gate and the input packet says so. Capture the screenshots into `.impeccable/review/`, one file per captured viewport (on the web, `desktop.png` and `mobile.png`, plus `user-<width>.png` whenever the user's viewport joined the inspected set; on native, one per device class, such as `phone.png` and `tablet.png`, suffixed per OS on adaptive), creating that directory when the harness does not; the paths you pass the reviewer are its spec, every viewport you inspected is named required in the packet, and that directory is where it looks when a passed path is missing.
 
 Then spawn the shipped finish reviewer, `impeccable-finish-reviewer` (`impeccable_finish_reviewer` in codex; `/impeccable-finish-reviewer` in Cursor; on GitHub Copilot say "Use the impeccable-finish-reviewer agent"), with the original request, confirmed answers, the artifact path, the screenshot paths, the direction contract, existing hook findings, the QUALITY BAR card and approved comp paths (a code-led build has no approved comp; the chosen decision comp rides in that slot as the critique reference, named as such), on a comp-led build the build state (`.impeccable/build/state.json`), the spec, and the diff directories (`.impeccable/review/diff/hero/` and `.impeccable/review/diff/final/`, whose side-by-side, heatmap, region pairs, and `report.json` are the fidelity evidence), the craft-floor reference path, and on a native platform the platform reference path(s), [ios.md](ios.md) / [android.md](android.md), both on adaptive, plus one line saying no detector ran, so the reviewer judges in the platform's conventions rather than the web's. The reviewer has no browser; screenshots you fail to pass are checks it cannot run. Never read the shipped agents' definition files before spawning; the harness loads them at spawn, and you owe only the input packet. Wait on any agent with one long timeout rather than a loop of short polls, and spend the wait on the next independent step. Verify the return carries the five contract sections (a recapture return carries one, its recapture list); on an empty or thrashed return, respawn once with the same inputs. This review never runs inside the build thread and never inherits it: spawn the reviewer fresh, with no forked conversation history (`fork_turns: 0` in codex); a reviewer that inherits your transcript inherits your framing, your optimism, and your abstractions, and everything it needs travels in the inputs above. Only a harness with no subagent capability at all substitutes a fresh in-thread pass after stepping fully out of the build context, run from [degraded/finish-reviewer.md](degraded/finish-reviewer.md), and a substituted or failed-and-replaced review is disclosed in one line at finish, never silently.
 
 Act on the disposition word; there are exactly four. **recapture**: the evidence failed, not the build. Recapture what the return names under the capture-validity rules, then run a full review over the new evidence. A review conducted on invalid evidence binds nothing, and a verdict pass may never follow it. **rebuild**: fidelity failed wholesale, not in patches. Skip the fix batch and execute the rebuild immediately: re-derive the named regions, produce the named assets, and send the result back for a fresh full review, never a verdict pass; a rebuild replaces regions wholesale, so the whole matrix runs again over the recaptures. Tell the user what is happening rather than asking permission to fix a failure. Consult the user only on a second rebuild directive, both verdicts on the table, or when rebuilding would discard content the user approved. **ship**: nothing is owed; report the verdict at its scope and continue to the documenter. **fix**: apply the material fixes in one batch, rebuild once, and recapture the same viewports over the same files. A recapture measures positions, loading, and overflow; it cannot measure whether a fix reached the quality the finding named, so send the recaptured screenshots back to the same reviewer for a verdict scoring every material fix resolved, partial, or unresolved (through the harness's agent continuation; without one, run the scoring fresh from [degraded/finish-reviewer.md](degraded/finish-reviewer.md)'s Verdict Pass). Fixes scored partial or unresolved get another batch, recapture, and verdict. Two rounds is the budget an unattended run ends at; an attended session's ceiling belongs to the user, so when the second verdict still lists open items, put the table in front of them and let them choose between shipping as it stands and funding another round. Whoever decides, stop the moment a round resolves nothing, and the reviewer's findings are the only list you work from, never your own re-opened hunt. Do not run a second detector.
 
-A rebuild and a fix round share one asset rule: a raster either round creates or replaces is still asset work under [visualize.md](visualize.md)'s Produce section and keeps its **provenance** like every build raster, and a raster the round abandons is deleted in the same batch. Before either round's result goes back for review or verdict, run `.opencode/skills/impeccable/scripts/impeccable embed-prompt --scan <asset-dir...>` over the directories the artifact's rasters ship from and clear every file it reports by embedding what it is missing: the exact generation prompt for a produced raster, the origin for a sourced, stock, or pre-existing one. The scan only reads; deletion is reserved for rasters the round abandoned, never for a file the scan flagged.
+A rebuild and a fix round share one asset rule: a raster either round creates or replaces is still asset work under [visualize.md](visualize.md)'s Produce section and keeps its **provenance** like every build raster, and a raster the round abandons is deleted in the same batch. Before either round's result goes back for review or verdict, run `~/.omo/agent/skills/impeccable/scripts/impeccable embed-prompt --scan <asset-dir...>` over the directories the artifact's rasters ship from and clear every file it reports by embedding what it is missing: the exact generation prompt for a produced raster, the origin for a sourced, stock, or pre-existing one. The scan only reads; deletion is reserved for rasters the round abandoned, never for a file the scan flagged.
 
 Report the final verdict under the reviewer's own disposition word and at its actual scope. A verdict pass scores the listed fixes and nothing else: "the reviewer scored all three fixes resolved" is a claim it supports, "no material issues remain" is not. A table with open material findings is never announced as a pass, never softened, and never dressed as whole-surface approval when only a fix list was scored. When the user answers a ship with evidence against it, their own screenshot, a named mismatch with the comp, that evidence outranks every capture you made: put their material in the packet and spawn a fresh reviewer for a new full review. Patching inline and self-certifying is how a rejected page ships twice.
 
diff --git a/.config/opencode/skills/impeccable/reference/onboard.md b/.config/omo/skills/impeccable/reference/onboard.md
similarity index 100%
rename from .config/opencode/skills/impeccable/reference/onboard.md
rename to .config/omo/skills/impeccable/reference/onboard.md
diff --git a/.config/opencode/skills/impeccable/reference/operate.md b/.config/omo/skills/impeccable/reference/operate.md
similarity index 100%
rename from .config/opencode/skills/impeccable/reference/operate.md
rename to .config/omo/skills/impeccable/reference/operate.md
diff --git a/.config/opencode/skills/impeccable/reference/optimize.md b/.config/omo/skills/impeccable/reference/optimize.md
similarity index 100%
rename from .config/opencode/skills/impeccable/reference/optimize.md
rename to .config/omo/skills/impeccable/reference/optimize.md
diff --git a/.config/opencode/skills/impeccable/reference/overdrive.md b/.config/omo/skills/impeccable/reference/overdrive.md
similarity index 100%
rename from .config/opencode/skills/impeccable/reference/overdrive.md
rename to .config/omo/skills/impeccable/reference/overdrive.md
diff --git a/.config/opencode/skills/impeccable/reference/polish.md b/.config/omo/skills/impeccable/reference/polish.md
similarity index 96%
rename from .config/opencode/skills/impeccable/reference/polish.md
rename to .config/omo/skills/impeccable/reference/polish.md
index 70a40af..99d9057 100644
--- a/.config/opencode/skills/impeccable/reference/polish.md
+++ b/.config/omo/skills/impeccable/reference/polish.md
@@ -29,7 +29,7 @@ Use the feature yourself at the surface's representative sizes: desktop and mobi
 If a prior critique exists, use it as one input:
 
 ```bash
-.opencode/skills/impeccable/scripts/impeccable critique-storage latest "<resolved target>" --json
+~/.omo/agent/skills/impeccable/scripts/impeccable critique-storage latest "<resolved target>" --json
 ```
 
 Exit 0 returns JSON with the latest snapshot's `body` and an exact `snapshot_file` identity. Retain `snapshot_file` until the end of the pass. For a local file target, the helper compares the file's exact current content fingerprint with the fingerprint captured by critique. Unchanged staged, unstaged, or untracked content remains current; any byte change, deletion, or replacement with a non-file closes the backlog it identified while preserving its trend history and exits 2. A URL target has no local fingerprint and remains current until explicitly closed. When current, incorporate relevant P0/P1 findings from `body` and name the snapshot read. Exit 2 means none exists or the target changed. Perform an independent pass either way.
@@ -99,7 +99,7 @@ Finish with a source diff: remove accidental churn, orphaned code, redundant val
 When this pass clears every Priority Issue it took from a snapshot, close that snapshot:
 
 ```bash
-.opencode/skills/impeccable/scripts/impeccable critique-storage close "<resolved target>" "<snapshot_file returned by latest>"
+~/.omo/agent/skills/impeccable/scripts/impeccable critique-storage close "<resolved target>" "<snapshot_file returned by latest>"
 ```
 
 This closes only the snapshot this pass actually processed; if a newer critique landed meanwhile, its backlog stays live. Do not close when no snapshot was read, when `snapshot_file` was not retained, or when Priority Issues remain.
diff --git a/.config/opencode/skills/impeccable/reference/quieter.md b/.config/omo/skills/impeccable/reference/quieter.md
similarity index 100%
rename from .config/opencode/skills/impeccable/reference/quieter.md
rename to .config/omo/skills/impeccable/reference/quieter.md
diff --git a/.config/opencode/skills/impeccable/reference/routing.md b/.config/omo/skills/impeccable/reference/routing.md
similarity index 63%
rename from .config/opencode/skills/impeccable/reference/routing.md
rename to .config/omo/skills/impeccable/reference/routing.md
index 66656ee..23e704c 100644
--- a/.config/opencode/skills/impeccable/reference/routing.md
+++ b/.config/omo/skills/impeccable/reference/routing.md
@@ -8,7 +8,7 @@ Give advice without executing commands; the menu below is only for bare invocati
 
 Read this when the user invokes `/impeccable` with no argument. They are asking "what should I do?" Make the menu context-aware instead of static.
 
-Setup has already run `impeccable context`. If that reported `NO_PRODUCT_MD`, the project has no captured context yet: lead the menu with `/impeccable init` as the top recommendation (one line on why) and still show the rest below; don't silently jump into init. Otherwise run `.opencode/skills/impeccable/scripts/impeccable signals` once and read its JSON, then lead with the **2-3 highest-value next commands**, each with a one-line reason pulled from the signals, followed by the full menu (the Commands table in SKILL.md, grouped by category). **Never auto-run a command; the recommendation is a suggestion the user confirms.**
+Setup has already run `impeccable context`. If that reported `NO_PRODUCT_MD`, the project has no captured context yet: lead the menu with `/impeccable init` as the top recommendation (one line on why) and still show the rest below; don't silently jump into init. Otherwise run `~/.omo/agent/skills/impeccable/scripts/impeccable signals` once and read its JSON, then lead with the **2-3 highest-value next commands**, each with a one-line reason pulled from the signals, followed by the full menu (the Commands table in SKILL.md, grouped by category). **Never auto-run a command; the recommendation is a suggestion the user confirms.**
 
 Reason over the signals; there is no score to obey:
 
@@ -19,6 +19,6 @@ Reason over the signals; there is no score to obey:
 - `devServer.running` true → `live` is available for in-browser iteration, and `generate` for one-shot variant runs on a named element; if false, don't lead with either. **`live`, `generate`, and the bundled `impeccable detect` are web-only.** If `setup.platform` is `ios`, `android`, or `adaptive`, don't lead with any of them; the browser overlay and the HTML rule engine don't apply to native app code.
 - Otherwise group by intent (build new / improve what's there / iterate visually), tailored to the current surface and `setup.platform`.
 
-**If `scan.targets` is non-empty and `setup.platform` is not `ios`/`android`/`adaptive`, run `.opencode/skills/impeccable/scripts/impeccable detect --json <scan.targets joined by spaces>` once** (the bundled detector over local files: no network, no npx; it reads HTML/CSS, so skip it for native projects). `scan.via` tells you what they are: `git-changes` (the markup/style files in your dirty tree, the most relevant set), `source-dir` (e.g. `src`, `app`), `html`, or `root`. Fold the hits into your picks: many quality / contrast hits → `audit` or `polish`; a specific slop family → the matching command (gradient text or eyebrows → `quieter` / `typeset`, flat or gray palette → `colorize`, and so on). It's a real, current signal that beats guessing. If detect errors or the tree is large and slow, skip it and recommend the user run `audit` themselves; never block the suggestion on it.
+**If `scan.targets` is non-empty and `setup.platform` is not `ios`/`android`/`adaptive`, run `~/.omo/agent/skills/impeccable/scripts/impeccable detect --json <scan.targets joined by spaces>` once** (the bundled detector over local files: no network, no npx; it reads HTML/CSS, so skip it for native projects). `scan.via` tells you what they are: `git-changes` (the markup/style files in your dirty tree, the most relevant set), `source-dir` (e.g. `src`, `app`), `html`, or `root`. Fold the hits into your picks: many quality / contrast hits → `audit` or `polish`; a specific slop family → the matching command (gradient text or eyebrows → `quieter` / `typeset`, flat or gray palette → `colorize`, and so on). It's a real, current signal that beats guessing. If detect errors or the tree is large and slow, skip it and recommend the user run `audit` themselves; never block the suggestion on it.
 
 Keep it to 2-3 pointed picks with the exact command to type. The menu stays the fallback; the recommendation is the lede.
diff --git a/.config/opencode/skills/impeccable/reference/shape.md b/.config/omo/skills/impeccable/reference/shape.md
similarity index 100%
rename from .config/opencode/skills/impeccable/reference/shape.md
rename to .config/omo/skills/impeccable/reference/shape.md
diff --git a/.config/opencode/skills/impeccable/reference/typeset.md b/.config/omo/skills/impeccable/reference/typeset.md
similarity index 98%
rename from .config/opencode/skills/impeccable/reference/typeset.md
rename to .config/omo/skills/impeccable/reference/typeset.md
index c3b045c..a673352 100644
--- a/.config/opencode/skills/impeccable/reference/typeset.md
+++ b/.config/omo/skills/impeccable/reference/typeset.md
@@ -24,7 +24,7 @@ When a sub-agent tool is available and permitted, run these independently; other
 2. **Mechanical scan:** run:
 
 ```bash
-.opencode/skills/impeccable/scripts/impeccable detect --json --scope type [target files or dirs]
+~/.omo/agent/skills/impeccable/scripts/impeccable detect --json --scope type [target files or dirs]
 ```
 
 Also inspect dynamic or arbitrary font values the detector cannot interpret. Synthesize both assessments before editing, noting what each caught alone. A clean scan is a floor, not proof of good typography.
diff --git a/.config/opencode/skills/impeccable/reference/visualize.md b/.config/omo/skills/impeccable/reference/visualize.md
similarity index 94%
rename from .config/opencode/skills/impeccable/reference/visualize.md
rename to .config/omo/skills/impeccable/reference/visualize.md
index 7c4cbe7..27d6d44 100644
--- a/.config/opencode/skills/impeccable/reference/visualize.md
+++ b/.config/omo/skills/impeccable/reference/visualize.md
@@ -39,7 +39,7 @@ What the comp shows is measured, not remembered. new-work.md section 6 runs the
 
 ## Plates and provenance
 
-Every raster region's plate is produced in the plates phase, before any page code, by the shipped asset producer or in the current thread (use `impeccable comp-spec --crop <id>` and save `impeccable comp-spec --plate-prompt <id>` to a prompt file; pass the crop and prompt to the harness image tool, or use `impeccable generate-image --ref <crop.png> --prompt-file <prompt.txt> --out <plate.png> --size <WxH> --quality high`). For isolated cutouts, add `--background transparent` to both the plate-prompt and API generation commands; use native PNG alpha and preserve white paint and clear gaps. Use `--background opaque` for full-frame imagery. Create output directories first and inspect alpha on light and dark grounds. Generation context is part of the asset: after generating any image with any tool, run `.opencode/skills/impeccable/scripts/impeccable embed-prompt <image> --prompt "<prompt>"` with the exact string the tool received (`impeccable generate-image` does this itself), so the intent lives inside the file; `--read` recovers it, `--scan <dir>` lists rasters still missing one. The embedded prompt plus the region's row in the spec is the raster's **provenance**, and every raster the artifact references carries it; a sourced, stock, or pre-existing raster embeds its origin instead. A raster created or replaced later, in a fix batch or a reviewer's rebuild, is produced the same way; a raster a fix abandons is deleted in the same batch.
+Every raster region's plate is produced in the plates phase, before any page code, by the shipped asset producer or in the current thread (use `impeccable comp-spec --crop <id>` and save `impeccable comp-spec --plate-prompt <id>` to a prompt file; pass the crop and prompt to the harness image tool, or use `impeccable generate-image --ref <crop.png> --prompt-file <prompt.txt> --out <plate.png> --size <WxH> --quality high`). For isolated cutouts, add `--background transparent` to both the plate-prompt and API generation commands; use native PNG alpha and preserve white paint and clear gaps. Use `--background opaque` for full-frame imagery. Create output directories first and inspect alpha on light and dark grounds. Generation context is part of the asset: after generating any image with any tool, run `~/.omo/agent/skills/impeccable/scripts/impeccable embed-prompt <image> --prompt "<prompt>"` with the exact string the tool received (`impeccable generate-image` does this itself), so the intent lives inside the file; `--read` recovers it, `--scan <dir>` lists rasters still missing one. The embedded prompt plus the region's row in the spec is the raster's **provenance**, and every raster the artifact references carries it; a sourced, stock, or pre-existing raster embeds its origin instead. A raster created or replaced later, in a fix batch or a reviewer's rebuild, is produced the same way; a raster a fix abandons is deleted in the same batch.
 
 Convert images with a converter `impeccable context` reported at boot (the IMAGE_TOOLS line); probe only when it reported none, at most once per session, never per image.
 
diff --git a/.config/opencode/skills/impeccable/scripts/VERSION b/.config/omo/skills/impeccable/scripts/VERSION
similarity index 100%
rename from .config/opencode/skills/impeccable/scripts/VERSION
rename to .config/omo/skills/impeccable/scripts/VERSION
diff --git a/.config/opencode/skills/impeccable/scripts/command-metadata.json b/.config/omo/skills/impeccable/scripts/command-metadata.json
similarity index 100%
rename from .config/opencode/skills/impeccable/scripts/command-metadata.json
rename to .config/omo/skills/impeccable/scripts/command-metadata.json
diff --git a/.config/opencode/skills/impeccable/scripts/data/font-index-failures.json b/.config/omo/skills/impeccable/scripts/data/font-index-failures.json
similarity index 100%
rename from .config/opencode/skills/impeccable/scripts/data/font-index-failures.json
rename to .config/omo/skills/impeccable/scripts/data/font-index-failures.json
diff --git a/.config/opencode/skills/impeccable/scripts/data/font-index.json b/.config/omo/skills/impeccable/scripts/data/font-index.json
similarity index 100%
rename from .config/opencode/skills/impeccable/scripts/data/font-index.json
rename to .config/omo/skills/impeccable/scripts/data/font-index.json
diff --git a/.config/opencode/skills/impeccable/scripts/impeccable b/.config/omo/skills/impeccable/scripts/impeccable
similarity index 100%
rename from .config/opencode/skills/impeccable/scripts/impeccable
rename to .config/omo/skills/impeccable/scripts/impeccable
diff --git a/.config/opencode/skills/impeccable/scripts/impeccable.cmd b/.config/omo/skills/impeccable/scripts/impeccable.cmd
similarity index 100%
rename from .config/opencode/skills/impeccable/scripts/impeccable.cmd
rename to .config/omo/skills/impeccable/scripts/impeccable.cmd
diff --git a/.config/opencode/skills/impeccable/scripts/live-browser-dom.js b/.config/omo/skills/impeccable/scripts/live-browser-dom.js
similarity index 100%
rename from .config/opencode/skills/impeccable/scripts/live-browser-dom.js
rename to .config/omo/skills/impeccable/scripts/live-browser-dom.js
diff --git a/.config/opencode/skills/impeccable/scripts/live-browser-ignores.js b/.config/omo/skills/impeccable/scripts/live-browser-ignores.js
similarity index 100%
rename from .config/opencode/skills/impeccable/scripts/live-browser-ignores.js
rename to .config/omo/skills/impeccable/scripts/live-browser-ignores.js
diff --git a/.config/opencode/skills/impeccable/scripts/live-browser-session.js b/.config/omo/skills/impeccable/scripts/live-browser-session.js
similarity index 100%
rename from .config/opencode/skills/impeccable/scripts/live-browser-session.js
rename to .config/omo/skills/impeccable/scripts/live-browser-session.js
diff --git a/.config/opencode/skills/impeccable/scripts/live-browser.js b/.config/omo/skills/impeccable/scripts/live-browser.js
similarity index 100%
rename from .config/opencode/skills/impeccable/scripts/live-browser.js
rename to .config/omo/skills/impeccable/scripts/live-browser.js
diff --git a/.config/opencode/skills/impeccable/scripts/modern-screenshot.umd.js b/.config/omo/skills/impeccable/scripts/modern-screenshot.umd.js
similarity index 100%
rename from .config/opencode/skills/impeccable/scripts/modern-screenshot.umd.js
rename to .config/omo/skills/impeccable/scripts/modern-screenshot.umd.js
diff --git a/.config/opencode/skills/launch/LICENSE b/.config/omo/skills/launch/LICENSE
similarity index 100%
rename from .config/opencode/skills/launch/LICENSE
rename to .config/omo/skills/launch/LICENSE
diff --git a/.config/opencode/skills/launch/SKILL.md b/.config/omo/skills/launch/SKILL.md
similarity index 100%
rename from .config/opencode/skills/launch/SKILL.md
rename to .config/omo/skills/launch/SKILL.md
diff --git a/.config/opencode/skills/launch/evals/evals.json b/.config/omo/skills/launch/evals/evals.json
similarity index 100%
rename from .config/opencode/skills/launch/evals/evals.json
rename to .config/omo/skills/launch/evals/evals.json
diff --git a/.config/opencode/skills/launch/references/shipped-changes.md b/.config/omo/skills/launch/references/shipped-changes.md
similarity index 100%
rename from .config/opencode/skills/launch/references/shipped-changes.md
rename to .config/omo/skills/launch/references/shipped-changes.md
diff --git a/.config/opencode/skills/launch/references/site-launch-qa.md b/.config/omo/skills/launch/references/site-launch-qa.md
similarity index 100%
rename from .config/opencode/skills/launch/references/site-launch-qa.md
rename to .config/omo/skills/launch/references/site-launch-qa.md
diff --git a/.config/opencode/skills/product-marketing/LICENSE b/.config/omo/skills/product-marketing/LICENSE
similarity index 100%
rename from .config/opencode/skills/product-marketing/LICENSE
rename to .config/omo/skills/product-marketing/LICENSE
diff --git a/.config/opencode/skills/product-marketing/SKILL.md b/.config/omo/skills/product-marketing/SKILL.md
similarity index 100%
rename from .config/opencode/skills/product-marketing/SKILL.md
rename to .config/omo/skills/product-marketing/SKILL.md
diff --git a/.config/opencode/skills/product-marketing/evals/evals.json b/.config/omo/skills/product-marketing/evals/evals.json
similarity index 100%
rename from .config/opencode/skills/product-marketing/evals/evals.json
rename to .config/omo/skills/product-marketing/evals/evals.json
diff --git a/.config/opencode/skills/seo-audit/LICENSE b/.config/omo/skills/seo-audit/LICENSE
similarity index 100%
rename from .config/opencode/skills/seo-audit/LICENSE
rename to .config/omo/skills/seo-audit/LICENSE
diff --git a/.config/opencode/skills/seo-audit/SKILL.md b/.config/omo/skills/seo-audit/SKILL.md
similarity index 100%
rename from .config/opencode/skills/seo-audit/SKILL.md
rename to .config/omo/skills/seo-audit/SKILL.md
diff --git a/.config/opencode/skills/seo-audit/evals/evals.json b/.config/omo/skills/seo-audit/evals/evals.json
similarity index 100%
rename from .config/opencode/skills/seo-audit/evals/evals.json
rename to .config/omo/skills/seo-audit/evals/evals.json
diff --git a/.config/opencode/skills/seo-audit/references/ai-writing-detection.md b/.config/omo/skills/seo-audit/references/ai-writing-detection.md
similarity index 100%
rename from .config/opencode/skills/seo-audit/references/ai-writing-detection.md
rename to .config/omo/skills/seo-audit/references/ai-writing-detection.md
diff --git a/.config/opencode/skills/seo-audit/references/international-seo.md b/.config/omo/skills/seo-audit/references/international-seo.md
similarity index 100%
rename from .config/opencode/skills/seo-audit/references/international-seo.md
rename to .config/omo/skills/seo-audit/references/international-seo.md
diff --git a/.config/opencode/skills/seo-audit/references/rankings-push.md b/.config/omo/skills/seo-audit/references/rankings-push.md
similarity index 100%
rename from .config/opencode/skills/seo-audit/references/rankings-push.md
rename to .config/omo/skills/seo-audit/references/rankings-push.md
diff --git a/.config/opencode/skills/seo-audit/references/title-tags.md b/.config/omo/skills/seo-audit/references/title-tags.md
similarity index 100%
rename from .config/opencode/skills/seo-audit/references/title-tags.md
rename to .config/omo/skills/seo-audit/references/title-tags.md
diff --git a/.config/opencode/skills/social/LICENSE b/.config/omo/skills/social/LICENSE
similarity index 100%
rename from .config/opencode/skills/social/LICENSE
rename to .config/omo/skills/social/LICENSE
diff --git a/.config/opencode/skills/social/SKILL.md b/.config/omo/skills/social/SKILL.md
similarity index 100%
rename from .config/opencode/skills/social/SKILL.md
rename to .config/omo/skills/social/SKILL.md
diff --git a/.config/opencode/skills/social/evals/evals.json b/.config/omo/skills/social/evals/evals.json
similarity index 100%
rename from .config/opencode/skills/social/evals/evals.json
rename to .config/omo/skills/social/evals/evals.json
diff --git a/.config/opencode/skills/social/references/carousel-frameworks.md b/.config/omo/skills/social/references/carousel-frameworks.md
similarity index 100%
rename from .config/opencode/skills/social/references/carousel-frameworks.md
rename to .config/omo/skills/social/references/carousel-frameworks.md
diff --git a/.config/opencode/skills/social/references/listening-sources-template.md b/.config/omo/skills/social/references/listening-sources-template.md
similarity index 100%
rename from .config/opencode/skills/social/references/listening-sources-template.md
rename to .config/omo/skills/social/references/listening-sources-template.md
diff --git a/.config/opencode/skills/social/references/listening.md b/.config/omo/skills/social/references/listening.md
similarity index 100%
rename from .config/opencode/skills/social/references/listening.md
rename to .config/omo/skills/social/references/listening.md
diff --git a/.config/opencode/skills/social/references/platform-limits.md b/.config/omo/skills/social/references/platform-limits.md
similarity index 100%
rename from .config/opencode/skills/social/references/platform-limits.md
rename to .config/omo/skills/social/references/platform-limits.md
diff --git a/.config/opencode/skills/social/references/platforms.md b/.config/omo/skills/social/references/platforms.md
similarity index 100%
rename from .config/opencode/skills/social/references/platforms.md
rename to .config/omo/skills/social/references/platforms.md
diff --git a/.config/opencode/skills/social/references/post-templates.md b/.config/omo/skills/social/references/post-templates.md
similarity index 100%
rename from .config/opencode/skills/social/references/post-templates.md
rename to .config/omo/skills/social/references/post-templates.md
diff --git a/.config/opencode/skills/social/references/reverse-engineering.md b/.config/omo/skills/social/references/reverse-engineering.md
similarity index 100%
rename from .config/opencode/skills/social/references/reverse-engineering.md
rename to .config/omo/skills/social/references/reverse-engineering.md
diff --git a/.config/opencode/skills/social/references/short-form-video.md b/.config/omo/skills/social/references/short-form-video.md
similarity index 100%
rename from .config/opencode/skills/social/references/short-form-video.md
rename to .config/omo/skills/social/references/short-form-video.md
diff --git a/.config/opencode/skills/social/references/x-algorithm.md b/.config/omo/skills/social/references/x-algorithm.md
similarity index 100%
rename from .config/opencode/skills/social/references/x-algorithm.md
rename to .config/omo/skills/social/references/x-algorithm.md
diff --git a/.config/opencode/skills/web-design-guidelines/SKILL.md b/.config/omo/skills/web-design-guidelines/SKILL.md
similarity index 100%
rename from .config/opencode/skills/web-design-guidelines/SKILL.md
rename to .config/omo/skills/web-design-guidelines/SKILL.md
diff --git a/.config/opencode/command/impeccable.md b/.config/opencode/command/impeccable.md
deleted file mode 100644
index 33f4a6f..0000000
--- a/.config/opencode/command/impeccable.md
+++ /dev/null
@@ -1,6 +0,0 @@
----
-description: Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
-agent: build
-subtask: true
----
-Call skill({ name: "impeccable" }) and follow its `Setup` and `Commands` sections to handle $ARGUMENTS.
diff --git a/.withcontextconfig.jsonc b/.withcontextconfig.jsonc
index 986e45b..ae52551 100644
--- a/.withcontextconfig.jsonc
+++ b/.withcontextconfig.jsonc
@@ -26,9 +26,11 @@
       "/LICENSE",
       "/AGENTS.md",
       
-      // OpenCode configuration and documentation (must stay local per AGENTS.md)
+      // Agent configuration and documentation (must stay local per AGENTS.md)
+      ".config/omo/**",
+      ".config/claude/**",
+      ".config/ai/**",
       ".config/opencode/**",
-      "opencode.json",
       
       // Component READMEs (stay with their configurations)
       ".config/*/README.md",
diff --git a/Brewfile.apps b/Brewfile.apps
index c172f6f..97c5193 100644
--- a/Brewfile.apps
+++ b/Brewfile.apps
@@ -24,7 +24,6 @@ cask "johannesnagl/tap/showmd", trusted: true
 # AI and agents
 cask "conductor"
 cask "claude"
-cask "opencode-desktop"
 cask "lm-studio"
 cask "ollama-app"
 cask "emdash"
diff --git a/README.md b/README.md
index 4c67436..084c2e1 100644
--- a/README.md
+++ b/README.md
@@ -25,7 +25,7 @@ This repository contains personal dotfiles for configuring a complete developmen
 - **Neovim Configuration**: Extensive Lua-based configuration with LSP support, debugging, and 50+ productivity plugins
 - **Terminal Emulators**: Configurations for Ghostty and WezTerm with custom themes and visual effects
 - **Shell Environment**: Optimized Zsh configuration with Starship prompt and useful aliases
-- **AI Integration**: OpenCode, OmO and Claude Code configuration, shared agent preferences, and `owt` workspaces that give each agent task its own git worktree
+- **AI Integration**: OmO and Claude Code configuration, shared agent preferences, and `owt` workspaces that give each agent task its own git worktree
 - **Development Tools**: Pre-configured settings for Git, tmux, direnv, and various language servers
 - **Documentation Management**: with-context MCP integration for knowledge management
 
@@ -66,7 +66,7 @@ The script is safe to rerun: each step checks what is already in place and only
 | `links` | Fetches the Neovim submodule on a fresh clone and symlinks the configs and `.local/bin` scripts into `$HOME`, backing up anything it replaces to `~/.local/state/dotfiles/backups/` |
 | `shell` | Installs oh-my-zsh and the tmux plugins |
 | `runtimes` | Node with nvm and the global npm packages, Rust, Python with pyenv, poetry, and Flutter with fvm |
-| `ai` | Installs omo, Claude Code, OpenCode and Codex, then runs `link-ai-configs.sh` |
+| `ai` | Installs omo, Claude Code and Codex, then runs `link-ai-configs.sh` |
 | `apps` | Installs the GUI and App Store apps in `Brewfile.apps` |
 
 `brew` and `apps` never upgrade packages that are already installed. `apps` skips apps already in `/Applications` that Homebrew did not install, and its App Store entries need you signed in to the App Store first. To list what is installed but missing from `Brewfile`, run `brew bundle dump --file=- | diff Brewfile -`.
@@ -91,7 +91,7 @@ ln -s ~/dotfiles/.zshrc ~/.zshrc
 
 ### AI configuration restore
 
-The `ai` step of `setup-mac.sh` runs this script. To run it on its own after installing Node.js, OpenCode, Claude Code, and OMC:
+The `ai` step of `setup-mac.sh` runs this script. To run it on its own after installing Node.js, omo, Claude Code, and OMC:
 
 ```bash
 bash ~/dotfiles/link-ai-configs.sh --dry-run
@@ -100,16 +100,16 @@ bash ~/dotfiles/link-ai-configs.sh
 
 The script creates individual relative symlinks, skips existing correct links, and backs up replaced files or links under `~/.local/state/dotfiles-ai/backups/`. It does not replace whole configuration directories. To undo a replacement, remove that individual symlink and move its corresponding backup back to the original path.
 
-- `.config/omo/omo.jsonc` supplies `~/.omo/omo.jsonc`. Model routing is preserved; the OpenCode overlay excludes only the OMC Claude plugin through `claude_code.plugins_override`.
-- `.config/ai/AGENTS.md` holds shared personal preferences. OpenCode loads it through `~/.config/opencode/AGENTS.md` instead of falling back to Claude's global orchestration instructions. Claude imports it from its own `CLAUDE.md`.
+- `.config/omo/omo.jsonc` supplies `~/.omo/omo.jsonc` with OmO's model routing, including the `design-critique-a` and `design-critique-b` categories that the Impeccable critique delegates its two assessments to.
+- `.config/ai/AGENTS.md` holds shared personal preferences. OmO reads it through `~/.config/opencode/AGENTS.md`, which is hard-wired in OmO's rules engine ahead of `~/.claude/CLAUDE.md`; the engine stops at the first file it finds, so this link both supplies these preferences and keeps Claude's OMC orchestration instructions out of OmO. Keep it even though OpenCode is retired. Claude imports the same file from its own `CLAUDE.md`.
 - `.config/claude/` supplies Claude's global instructions, settings, and OMC preferences. The machine-specific OMC `nodeBinary` cache is intentionally omitted; install Node.js and run OMC setup on each new machine to configure its runtime and HUD.
-- OpenCode's main configuration, TUI registration, and existing command/MCP isolation plugins are linked individually. Other portable Claude plugins and user skills remain enabled.
+- `.config/omo/skills/` holds the vendored Impeccable, Vercel `web-design-guidelines`, `frontend-workflow` and marketing skills. The script links every one into `~/.omo/agent/skills/`, and all but `frontend-workflow` into `~/.claude/skills/`; see [the skills README](.config/omo/skills/README.md) for provenance and upgrades. Portable Claude plugins and unrelated user skills remain enabled.
 
-Credentials, `settings.local.json`, plugin installations, unrelated user skills, histories, caches, and runtime state are not copied into this repository or managed by this script. The selected Impeccable, Vercel web-design-guidelines and frontend-workflow skills are managed individually; see [the GPT visual workflow](.config/opencode/README.md) for provenance, verification and rollback. Install other desired plugins and portable skills separately. OpenCode's local MCP servers are referenced through `{env:HOME}`, so the paths are portable, but the servers themselves (headroom, agcanvas, uvx, ast-grep-mcp, portfolio-mcp) must be installed at those locations on a new machine.
+Credentials, `settings.local.json`, plugin installations, unrelated user skills, histories, caches, and runtime state are not copied into this repository or managed by this script. Install other desired plugins and portable skills separately. OmO's MCP servers live in `~/.omo/agent/mcp.json`, which this repository does not manage; the local ones (headroom, agcanvas, uvx, ast-grep-mcp, portfolio-mcp) must be installed on a new machine before they resolve.
 
 The OmO hooks and slash commands (`~/.omo/agent/hooks.json` and `~/.omo/agent/prompts`) and the workspace scripts in `~/.local/bin` are linked by the `links` step of `setup-mac.sh` instead.
 
-Restart OpenCode and Claude Code after applying changes. On first use, Claude may ask to approve the shared preferences import. Updates can rewrite generated configuration or replace symlinks: review the live files and repository diff before rerunning the link script, which backs up divergent live files rather than merging them. No plugin versions or model choices are changed by this restore step.
+Restart OmO and Claude Code after applying changes. On first use, Claude may ask to approve the shared preferences import. Updates can rewrite generated configuration or replace symlinks: review the live files and repository diff before rerunning the link script, which backs up divergent live files rather than merging them. No plugin versions or model choices are changed by this restore step.
 
 ## Components
 
@@ -122,7 +122,7 @@ Restart OpenCode and Claude Code after applying changes. On first use, Claude ma
 - **Themes**: Multiple colorschemes including Catppuccin, Tokyo Night, and Rose Pine
 
 Key features:
-- AI-powered coding assistance (Claude, OpenCode)
+- AI-powered coding assistance (Claude, OmO)
 - Advanced Git integration
 - Flutter and mobile development support
 - Python environment management
@@ -169,37 +169,21 @@ Key features:
 
 ### AI and Coding Assistants
 
-#### OpenCode (`.config/opencode/`)
-
-Specialized AI agents for different development workflows:
-
-- **debug**: Debugging assistance and troubleshooting
-- **docs**: Documentation generation and maintenance
-- **qa**: Quality assurance and code analysis
-- **refactor**: Code refactoring patterns and best practices
-- **review**: Code review guidelines and automation
-- **security**: Security audits and vulnerability scanning
-- **setup**: Project initialization and setup workflows
-- **test**: Test generation and execution
-- **webgen**: Web page generation from ideas
-
-Custom commands:
-- `/setup-mcp`: MCP server configuration
-- Additional commands in `.config/opencode/command/`
-
-Plugins:
-- **oh-my-openagent**, **opencode-antigravity-auth** and **envsitter-guard** from npm
-- **strip-claude-only-commands** and **strip-omc-mcp** (`.config/opencode/plugin/`): keep Claude-only commands and OMC's MCP servers out of OpenCode
-
-MCP servers: Playwright, Chrome DevTools, Linear, reoclo, time, ast-grep, headroom, agcanvas and portfolio.
-
 #### OmO (`.config/omo/`)
 
-- `omo.jsonc` (linked as `~/.omo/omo.jsonc`): agent and category model routing for OpenCode and the native harness.
+OpenCode is retired. Its agents, commands and plugins are left in `.config/opencode/` for reference, are no longer installed or linked, and its skills and slash commands moved here.
+
+- `omo.jsonc` (linked as `~/.omo/omo.jsonc`): model routing for the main session, task categories and curated agents. `design-critique-a` and `design-critique-b` are the two lanes the Impeccable critique delegates its assessments to.
 - `hooks.json` (linked as `~/.omo/agent/hooks.json`): runs `omo-notify` when you send a prompt, when a session stops and when it asks you something, for the sound, the notification and the coloured tab marker.
-- `prompts/` (linked as `~/.omo/agent/prompts`): slash commands for `owt` workspaces.
+- `prompts/` (linked as `~/.omo/agent/prompts`): slash commands.
   - `/linear-sync [notes]` posts a progress comment on the workspace's Linear issues and sets them to In Progress, or In Review once a PR is open.
   - `/owt-done [notes]` finishes a workspace after its PR merges: it comments on each issue and moves it to Done, then runs `owt done --detach`. It asks before discarding uncommitted or unmerged work.
+  - `/impeccable [command] [target]` runs the Impeccable design skill.
+  - `/setup-notes`, `/sync-notes`, `/ingest-notes`, `/teleport-notes`, `/analyze-vault`, `/reorganize-notes`, `/preview-notes-delegation` and `/validate-notes-config` manage with-context documentation delegation. They came over from OpenCode and need the with-context MCP server, which is not in `~/.omo/agent/mcp.json`.
+- `skills/` (linked into `~/.omo/agent/skills/`, and into `~/.claude/skills/` for the shared ones): the vendored Impeccable, Vercel `web-design-guidelines`, `frontend-workflow` and marketing skills. See [the skills README](.config/omo/skills/README.md) for provenance, local modifications and upgrades.
+- `archive/`: the OpenCode-era `DEVELOPMENT-WORKFLOW.md` and `UI-WORKFLOW.md`, kept for reference and loaded by nothing.
+
+MCP servers (in `~/.omo/agent/mcp.json`, which this repository does not manage): Playwright, Chrome DevTools, Linear, reoclo, time, ast-grep, headroom, agcanvas and portfolio.
 
 #### Agent workspaces (`owt`)
 
@@ -265,8 +249,8 @@ Docker Compose configuration for local development services in `local_servers/`.
    - Configure in `.config/nvim/lua/absolute/after/`
 2. **Shell Aliases**: Modify `.zshrc` to add custom aliases and functions
 3. **Git Configuration**: Update `.gitignore` or `.rgignore` for global ignore patterns
-4. **OpenCode Agents**: Create custom agents in `.config/opencode/agent/`
-5. **OpenCode Commands**: Add custom commands in `.config/opencode/command/`
+4. **OmO Skills**: Add a skill in `.config/omo/skills/`, then link it with `link-ai-configs.sh`
+5. **OmO Slash Commands**: Add a prompt template in `.config/omo/prompts/`
 
 ### Theme Customization
 
@@ -287,7 +271,7 @@ This repository uses the with-context MCP server for documentation management. S
 
 - Documentation delegation patterns
 - Local vs. vault documentation
-- OpenCode agent workflows
+- OmO skills and slash commands
 - Best practices for AI agents
 
 Key documentation files:
@@ -386,12 +370,12 @@ This project is open source and available under the MIT License. See individual
 
 - [Absolute VIM](https://github.com/boxpositron/absolute-vim) - Neovim configuration foundation
 - The open-source community for the amazing tools and plugins
-- OpenCode team for AI-powered development workflows
+- The OmO and Claude Code teams for AI-powered development workflows
 - Contributors and users who provide feedback and improvements
 
 ## Resources
 
-- **OpenCode Documentation**: https://opencode.ai/docs
+- **OmO Documentation**: https://github.com/code-yeongyu/oh-my-openagent
 - **Neovim Plugin Ecosystem**: https://github.com/rockerBOO/awesome-neovim
 - **Dotfiles Community**: https://dotfiles.github.io
 
@@ -405,4 +389,4 @@ For questions, issues, or suggestions, please open an issue on the GitHub reposi
 **Platform**: macOS (Darwin)  
 **Primary Editor**: Neovim  
 **Shell**: Zsh  
-**AI Tools**: OpenCode, OmO, Claude Code
+**AI Tools**: OmO, Claude Code, Codex
diff --git a/link-ai-configs.sh b/link-ai-configs.sh
index b4a77a1..e2f8e88 100644
--- a/link-ai-configs.sh
+++ b/link-ai-configs.sh
@@ -31,16 +31,6 @@ sources=(
     .config/claude/omc.json
     .config/claude/CLAUDE.md
     .config/claude/settings.json
-    .config/opencode/opencode.json
-    .config/opencode/tui.json
-    .config/opencode/plugin/strip-omc-mcp.ts
-    .config/opencode/plugin/strip-claude-only-commands.ts
-    .config/opencode/plugin/lib/claude-only-command-registry.ts
-    .config/opencode/UI-WORKFLOW.md
-    .config/opencode/DEVELOPMENT-WORKFLOW.md
-    .config/opencode/skills/frontend-workflow
-    .config/opencode/skills/impeccable
-    .config/opencode/skills/web-design-guidelines
 )
 targets=(
     .config/ai/AGENTS.md
@@ -49,26 +39,26 @@ targets=(
     .claude/.omc-config.json
     .claude/CLAUDE.md
     .claude/settings.json
-    .config/opencode/opencode.json
-    .config/opencode/tui.json
-    .config/opencode/plugin/strip-omc-mcp.ts
-    .config/opencode/plugin/strip-claude-only-commands.ts
-    .config/opencode/plugin/lib/claude-only-command-registry.ts
-    .config/opencode/UI-WORKFLOW.md
-    .config/opencode/DEVELOPMENT-WORKFLOW.md
-    .config/opencode/skills/frontend-workflow
-    .config/opencode/skills/impeccable
-    .config/opencode/skills/web-design-guidelines
 )
 
-# Marketing and copy skills vendored from coreyhaines31/marketingskills (see
-# .config/opencode/README.md), linked for OpenCode, Claude Code and OMO.
-marketing_skills=(product-marketing copywriting copy-editing emails cold-email content-strategy seo-audit ai-seo launch social)
-for skill in "${marketing_skills[@]}"; do
-    for target_dir in .config/opencode/skills .claude/skills .omo/agent/skills; do
-        sources+=(".config/opencode/skills/$skill")
-        targets+=("$target_dir/$skill")
-    done
+# ~/.config/opencode/AGENTS.md above is OmO's global-rules path, not an OpenCode
+# file. OmO's rules engine reads it before ~/.claude/CLAUDE.md and stops at the
+# first hit, so this link both supplies the shared preferences and keeps Claude
+# Code's OMC orchestration text out of OmO. Keep it after OpenCode is gone.
+
+# Skills vendored from upstream repos; provenance, verification and upgrade
+# steps are in .config/omo/skills/README.md. frontend-workflow is the OmO
+# delegation process skill and is not linked into Claude Code; the rest are
+# shared by both harnesses.
+omo_skills=(frontend-workflow impeccable web-design-guidelines product-marketing copywriting copy-editing emails cold-email content-strategy seo-audit ai-seo launch social)
+claude_skills=(impeccable web-design-guidelines product-marketing copywriting copy-editing emails cold-email content-strategy seo-audit ai-seo launch social)
+for skill in "${omo_skills[@]}"; do
+    sources+=(".config/omo/skills/$skill")
+    targets+=(".omo/agent/skills/$skill")
+done
+for skill in "${claude_skills[@]}"; do
+    sources+=(".config/omo/skills/$skill")
+    targets+=(".claude/skills/$skill")
 done
 
 # Preflight the entire manifest before changing any live file.
diff --git a/setup-mac.sh b/setup-mac.sh
index 7d13647..09a39d5 100755
--- a/setup-mac.sh
+++ b/setup-mac.sh
@@ -46,8 +46,6 @@ local_servers
 .config/zellij/config.kdl
 .config/zed/keymap.json
 .config/zed/settings.json
-.config/opencode/agent
-.config/opencode/command
 .config/omo/hooks.json:.omo/agent/hooks.json
 .config/omo/prompts:.omo/agent/prompts
 "
@@ -319,11 +317,6 @@ step_ai() {
     else
         run_remote https://claude.ai/install.sh
     fi
-    if have opencode; then
-        info "OpenCode already installed"
-    else
-        run_remote https://opencode.ai/install --no-modify-path
-    fi
     if have codex; then info "Codex already installed"; else run brew install --cask codex; fi
     # link-ai-configs.sh needs Node from the runtimes step.
     local args=""
@@ -423,7 +416,7 @@ main() {
     if [[ -z $selected ]]; then selected=$STEPS; fi
 
     # Tools from non-Homebrew installers live here; the steps look for them.
-    export PATH="$HOME/.local/bin:$HOME/.bun/bin:$HOME/.opencode/bin:$HOME/.cargo/bin:$PATH"
+    export PATH="$HOME/.local/bin:$HOME/.bun/bin:$HOME/.cargo/bin:$PATH"
     load_brew_env || true
     if $DRY_RUN; then say "Dry run: nothing will be changed"; fi
 
@@ -449,7 +442,7 @@ main() {
         info "Steps that need you:"
         info "- Sign in to the App Store, then rerun ./setup-mac.sh apps for the App Store apps"
         info "- 1Password: turn on the SSH agent (Settings > Developer); .zshrc uses it for SSH"
-        info "- Sign in: gh auth login, then Claude Code, Codex and OpenCode"
+        info "- Sign in: gh auth login, then omo, Claude Code and Codex"
         info "- Open a new terminal to load the new shell setup"
     fi
     [[ -z $failed ]]