skillpacks 0.1.1 → 0.1.2

package/{global → base}/claude/skills/CHANGELOG.md

@@ -1,5 +1,13 @@
 # Changelog
 
+## v0.8 - 2026-06-13
+
+- Renamed the scanned skill set from "global" to "base": now scans `base/<tool>/*/SKILL.md`, and ungrouped skills are labeled `base` instead of `global`.
+
+## v0.7 - 2026-06-12
+
+- Standardized active pack and skill install guidance on `npx skillpacks install <pack-or-skill>` instead of agent-native `/pack install` or `$pack install` recommendations.
+
 ## v0.6 - 2026-06-11
 
 - Added npm-aware install-route alternatives to available-but-not-installed skill guidance while preserving Claude `/pack install` routes.

package/base/claude/skills/SKILL.md

@@ -0,0 +1,141 @@
+---
+name: skills
+description: Browse and search all available skills, grouped by workflow stage or activity type
+type: ops
+version: v0.8
+argument-hint: "[list | types | search <keyword>]"
+---
+
+# Skills
+
+Discover and search installed base skills plus enabled project-local pack skills, grouped by workflow stage or activity type.
+
+## Process
+
+1. **Parse arguments:**
+   - If `$ARGUMENTS` is empty or `list` → **list mode** (show all skills grouped by workflow stage).
+   - If `$ARGUMENTS` is `types` → **type mode** (show all skills grouped by activity type).
+   - If `$ARGUMENTS` starts with `search ` → **search mode** (filter by keyword after `search`).
+
+2. **Discover skills:**
+   - Always scan base Claude skills in `base/claude/*/SKILL.md`.
+   - If `.agents/project.json` exists, read `enabled_packs` and scan `packs/<pack>/claude/*/SKILL.md` for each enabled pack. Also scan sub-directories like `packs/<pack>/claude/<skill>/frameworks/*/SKILL.md` for sub-skills.
+   - Also scan all packs in `packs/*/claude/*/SKILL.md` (and `frameworks/*/SKILL.md` children) to discover available-but-not-installed skills.
+   - If `.claude/skills/*/SKILL.md` exists in the current project, include those local skills too.
+   - Read the first 10 lines of each file to extract YAML frontmatter fields: `name`, `description`, `type`, `invocation`, `parent`.
+   - Track which pack each skill belongs to (if any).
+   - Default `invocation` to `primary` when the field is absent.
+
+3. **Group skills by workflow stage** using this static mapping:
+
+   The mapping includes base skills and pack-provided skills. Only skills
+   discovered in step 2 should be printed, so domain and kanban entries appear
+   only when the corresponding project-local pack is enabled or linked.
+   PoketoWork kanban skills are intentionally absent while the kanban packs are hibernated.
+
+   | Stage | Skills (pack in parentheses; no label = base) |
+   |-------|--------|
+   | Pack Management | `pack`, `pack list`, `pack status`, `pack recommend`, `npx skillpacks install <pack-or-skill>` (or project shell: `npx skillpacks install <pack-or-skill>`), `pack remove <pack-or-skill>`, `pack which <skill>` |
+   | Discovery & Market Fit | `customer-discovery` (business-discovery), `enterprise-icp` (business-discovery) |
+   | Game Development | `game-workflow` (game), `game-audience` (game), `game-fantasy` (game), `game-genre-map` (game), `game-comparables` (game), `game-core-loop` (game), `game-prototype-test` (game), `game-store-page-test` (game), `game-playtest-metrics` (game), `game-roadmap` (game), `game-launch` (game) |
+   | Devtool Development | `devtool-workflow` (devtool), `devtool-user-map` (devtool), `devtool-integration-map` (devtool), `devtool-dx-journey` (devtool), `devtool-adoption` (devtool), `devtool-positioning` (devtool), `devtool-monetization` (devtool), `devtool-docs-audit` (devtool) |
+   | Planning | `idea-scope-brief`, `brainstorm` (product-design), `feature-interview` (product-design), `user-flow-map` (product-design), `spec-interview` (product-design), `spec-interview --ideas` (product-design), `ui-interview` (product-design), `ux-variations` (product-design), `consolidate-variations` (product-design), `experiment` (business-growth) |
+   | Mapping | `journey-map` (customer-lifecycle), `metrics` (business-ops) |
+   | Strategize | `roadmap` (agent-work-admin), `competitive-analysis` (business-discovery), `platform-strategy` (business-growth), `gtm` (business-growth), `landing-copy` (business-growth), `monetization` (business-growth), `positioning` (business-discovery), `runway-model` (business-ops) |
+   | Evaluate | `dogfood` (product-testing), `mvp-gap` (business-discovery), `scale-audit` (business-ops), `customer-feedback` (customer-lifecycle), `assumption-tracker` (business-discovery), `cohort-review` (customer-lifecycle), `retro` (business-ops) |
+   | Research Health | `research-roadmap` (research-admin), `reconcile-research` (business-discovery), `reconcile-dev-docs` (docs-health) |
+   | Detail | `plan-phase` (agent-work-admin) |
+   | Execution | `exec` (exec-loop), `guide` (guided-walkthrough) |
+   | Shipping | `ship` (exec-loop), `ship-end` (exec-loop) |
+   | Code Quality | `expert-review` (code-review), `regression-check` (code-review), `dead-code` (code-review), `slim-audit` (code-review) |
+   | Debugging | `investigate` (code-debug), `debug` (code-debug), `trace` (code-debug), `session-triage` (session-analytics) |
+   | Refactoring & Migration | `migrate` (code-maintenance), `decommission` (teardown), `scaffold` (monorepo) |
+   | Monorepo | `affected` (monorepo), `mono-plan` (monorepo), `mono-guard` (monorepo) |
+   | Release & Deploy | `release` (release-ops), `deploy` (release-ops), `branch-lifecycle` (release-ops) |
+   | Context & Session | `afps-status`, `codebase-status`, `analyze-sessions` (session-analytics), `handoff` (context-transfer), `sync` (gitops), `investor-update` (business-ops) |
+   | Skill Development | `targeted-skill-builder` (skill-dev), `skill-interview` (skill-dev), `create-agentic-skill` (skill-dev), `create-local-skill` (skill-dev) |
+   | Testing | `uat` (product-testing), `uat-guide` (guided-walkthrough), `quiz-me` (knowledge-check) |
+   | Utility | `commit-and-push-by-feature` (gitops), `init-agentic-skills`, `provision-agentic-config`, `skills`, `bootstrap-repo` (repo-maintenance), `desk-flip` (teardown), `compile-central-alignment` (alignment-page-admin), `patch-exec-profile` (exec-profile), `delegate` (agent-bridge), `report-website` (report-gen), `icon-handler` (website-polish), `design-system` (product-design), `prototype` (product-design), `spec-drift` (agent-work-admin), `hygiene` (docs-health), `update-packages` (code-maintenance) |
+
+   Skills not found in the mapping go into an **Other** group at the end.
+
+4. **Group skills by activity type** (type mode only) using the `type` field from frontmatter:
+
+   | Type | Description |
+   |------|-------------|
+   | `research` | Web search + analysis → produces documents |
+   | `analysis` | Reads codebase/docs → produces assessments |
+   | `planning` | Interactive → produces specs/plans |
+   | `execution` | Writes/modifies code |
+   | `review` | Reads code → reports issues (no changes) |
+   | `debugging` | Investigates + fixes problems |
+   | `shipping` | Commits, deploys, session management |
+   | `ops` | Manages boards, branches, meta-tooling |
+
+   Display order: research → analysis → planning → execution → review → debugging → shipping → ops.
+   Skills with no `type` field go into an **Other** group at the end.
+
+5. **Apply filter (search mode only):**
+   - Match the keyword case-insensitively against each skill's `name`, `description`, and `type`.
+   - Keep only matching skills. Remove empty groups.
+
+6. **Output results:**
+   - Print each non-empty group as a `## Group Name` heading.
+   - Under each heading, list installed/base primary and chained skills as `/<name> — <description>  [type]`.
+   - Show orchestrator skills with an `⚙` prefix: `⚙ /<name> — <description>  [type]`.
+   - Show sub-skills indented under their parent skill (identified by the `parent:` frontmatter field or by living under a `frameworks/` directory). Format: `  ↳ /<name> — <description>  [sub-skill]`. If the parent is not in the same group, place sub-skills in a "Sub-skills" subsection at the end of the parent's group.
+   - For available-but-not-installed pack skills, list as `/<name> — <description>  [type]  ⚠ requires \`npx skillpacks install <skill>\` or \`npx skillpacks install <pack>\` inside Claude Code, or \`npx skillpacks install <pack-or-skill>\` from the project shell`.
+   - Omit groups that have no skills (after filtering in search mode).
+   - At the bottom, print a total count: `**N skills** installed (M sub-skills), **P skills** available via packs` (or `**N skills** matching "<keyword>"`).
+
+## Output
+
+### List mode (default — grouped by workflow stage)
+```
+## Discovery & Market Fit
+/customer-discovery — Customer discovery interview...  [research]
+/enterprise-icp — Enterprise multi-stakeholder discovery...  [research]
+
+## Strategize
+⚙ /positioning — Parent router — detect market vs product mode...  [research]
+  ↳ /category-design — Play Bigger category design framework  [sub-skill]
+  ↳ /jtbd-positioning — Jobs to Be Done positioning framework  [sub-skill]
+  ↳ /moore-positioning — Geoffrey Moore positioning framework  [sub-skill]
+  ↳ /obviously-awesome — Obviously Awesome positioning framework  [sub-skill]
+  ↳ /strategic-canvas — Strategic Canvas positioning framework  [sub-skill]
+/competitive-analysis — Research competitors...  [research]
+...
+
+## Execution
+⚙ /exec — Execute next plan step...  [execution]
+...
+
+**N skills** installed (M sub-skills), **P skills** available via packs
+```
+
+### Type mode (`/skills types`)
+```
+## Research
+/customer-discovery — Customer discovery interview...
+/competitive-analysis — Research competitors...
+...
+
+## Analysis
+/mvp-gap — Evaluate codebase against customer-discovery evidence...
+...
+
+**N skills** found
+```
+
+## Constraints
+
+- This is a read-only scan — never modify any files.
+- Always read the live frontmatter from SKILL.md files; do not hardcode descriptions.
+- Use the static stage mapping for stage grouping; use the `type` frontmatter field for type grouping.
+- Keep output compact — one line per skill, no extra detail beyond name, description, and type tag.
+- In search mode, if no skills match the keyword, print: `No skills matching "<keyword>"`.
+
+
+## Default Shipping Contract
+
+Follow the shared shipping contract convention in CLAUDE.md.

package/base/claude/skills/archive/v0.7/SKILL.md

@@ -0,0 +1,141 @@
+---
+name: skills
+description: Browse and search all available skills, grouped by workflow stage or activity type
+type: ops
+version: v0.7
+argument-hint: "[list | types | search <keyword>]"
+---
+
+# Skills
+
+Discover and search installed global skills plus enabled project-local pack skills, grouped by workflow stage or activity type.
+
+## Process
+
+1. **Parse arguments:**
+   - If `$ARGUMENTS` is empty or `list` → **list mode** (show all skills grouped by workflow stage).
+   - If `$ARGUMENTS` is `types` → **type mode** (show all skills grouped by activity type).
+   - If `$ARGUMENTS` starts with `search ` → **search mode** (filter by keyword after `search`).
+
+2. **Discover skills:**
+   - Always scan global Claude skills in `global/claude/*/SKILL.md`.
+   - If `.agents/project.json` exists, read `enabled_packs` and scan `packs/<pack>/claude/*/SKILL.md` for each enabled pack. Also scan sub-directories like `packs/<pack>/claude/<skill>/frameworks/*/SKILL.md` for sub-skills.
+   - Also scan all packs in `packs/*/claude/*/SKILL.md` (and `frameworks/*/SKILL.md` children) to discover available-but-not-installed skills.
+   - If `.claude/skills/*/SKILL.md` exists in the current project, include those local skills too.
+   - Read the first 10 lines of each file to extract YAML frontmatter fields: `name`, `description`, `type`, `invocation`, `parent`.
+   - Track which pack each skill belongs to (if any).
+   - Default `invocation` to `primary` when the field is absent.
+
+3. **Group skills by workflow stage** using this static mapping:
+
+   The mapping includes global skills and pack-provided skills. Only skills
+   discovered in step 2 should be printed, so domain and kanban entries appear
+   only when the corresponding project-local pack is enabled or linked.
+   PoketoWork kanban skills are intentionally absent while the kanban packs are hibernated.
+
+   | Stage | Skills (pack in parentheses; no label = global) |
+   |-------|--------|
+   | Pack Management | `pack`, `pack list`, `pack status`, `pack recommend`, `npx skillpacks install <pack-or-skill>` (or project shell: `npx skillpacks install <pack-or-skill>`), `pack remove <pack-or-skill>`, `pack which <skill>` |
+   | Discovery & Market Fit | `customer-discovery` (business-discovery), `enterprise-icp` (business-discovery) |
+   | Game Development | `game-workflow` (game), `game-audience` (game), `game-fantasy` (game), `game-genre-map` (game), `game-comparables` (game), `game-core-loop` (game), `game-prototype-test` (game), `game-store-page-test` (game), `game-playtest-metrics` (game), `game-roadmap` (game), `game-launch` (game) |
+   | Devtool Development | `devtool-workflow` (devtool), `devtool-user-map` (devtool), `devtool-integration-map` (devtool), `devtool-dx-journey` (devtool), `devtool-adoption` (devtool), `devtool-positioning` (devtool), `devtool-monetization` (devtool), `devtool-docs-audit` (devtool) |
+   | Planning | `idea-scope-brief`, `brainstorm` (product-design), `feature-interview` (product-design), `user-flow-map` (product-design), `spec-interview` (product-design), `spec-interview --ideas` (product-design), `ui-interview` (product-design), `ux-variations` (product-design), `consolidate-variations` (product-design), `experiment` (business-growth) |
+   | Mapping | `journey-map` (customer-lifecycle), `metrics` (business-ops) |
+   | Strategize | `roadmap` (agent-work-admin), `competitive-analysis` (business-discovery), `platform-strategy` (business-growth), `gtm` (business-growth), `landing-copy` (business-growth), `monetization` (business-growth), `positioning` (business-discovery), `runway-model` (business-ops) |
+   | Evaluate | `dogfood` (product-testing), `mvp-gap` (business-discovery), `scale-audit` (business-ops), `customer-feedback` (customer-lifecycle), `assumption-tracker` (business-discovery), `cohort-review` (customer-lifecycle), `retro` (business-ops) |
+   | Research Health | `research-roadmap` (research-admin), `reconcile-research` (business-discovery), `reconcile-dev-docs` (docs-health) |
+   | Detail | `plan-phase` (agent-work-admin) |
+   | Execution | `exec` (exec-loop), `guide` (guided-walkthrough) |
+   | Shipping | `ship` (exec-loop), `ship-end` (exec-loop) |
+   | Code Quality | `expert-review` (code-review), `regression-check` (code-review), `dead-code` (code-review), `slim-audit` (code-review) |
+   | Debugging | `investigate` (code-debug), `debug` (code-debug), `trace` (code-debug), `session-triage` (session-analytics) |
+   | Refactoring & Migration | `migrate` (code-maintenance), `decommission` (teardown), `scaffold` (monorepo) |
+   | Monorepo | `affected` (monorepo), `mono-plan` (monorepo), `mono-guard` (monorepo) |
+   | Release & Deploy | `release` (release-ops), `deploy` (release-ops), `branch-lifecycle` (release-ops) |
+   | Context & Session | `afps-status`, `codebase-status`, `analyze-sessions` (session-analytics), `handoff` (context-transfer), `sync` (gitops), `investor-update` (business-ops) |
+   | Skill Development | `targeted-skill-builder` (skill-dev), `skill-interview` (skill-dev), `create-agentic-skill` (skill-dev), `create-local-skill` (skill-dev) |
+   | Testing | `uat` (product-testing), `uat-guide` (guided-walkthrough), `quiz-me` (knowledge-check) |
+   | Utility | `commit-and-push-by-feature` (gitops), `init-agentic-skills`, `provision-agentic-config`, `skills`, `bootstrap-repo` (repo-maintenance), `desk-flip` (teardown), `compile-central-alignment` (alignment-page-admin), `patch-exec-profile` (exec-profile), `delegate` (agent-bridge), `report-website` (report-gen), `icon-handler` (website-polish), `design-system` (product-design), `prototype` (product-design), `spec-drift` (agent-work-admin), `hygiene` (docs-health), `update-packages` (code-maintenance) |
+
+   Skills not found in the mapping go into an **Other** group at the end.
+
+4. **Group skills by activity type** (type mode only) using the `type` field from frontmatter:
+
+   | Type | Description |
+   |------|-------------|
+   | `research` | Web search + analysis → produces documents |
+   | `analysis` | Reads codebase/docs → produces assessments |
+   | `planning` | Interactive → produces specs/plans |
+   | `execution` | Writes/modifies code |
+   | `review` | Reads code → reports issues (no changes) |
+   | `debugging` | Investigates + fixes problems |
+   | `shipping` | Commits, deploys, session management |
+   | `ops` | Manages boards, branches, meta-tooling |
+
+   Display order: research → analysis → planning → execution → review → debugging → shipping → ops.
+   Skills with no `type` field go into an **Other** group at the end.
+
+5. **Apply filter (search mode only):**
+   - Match the keyword case-insensitively against each skill's `name`, `description`, and `type`.
+   - Keep only matching skills. Remove empty groups.
+
+6. **Output results:**
+   - Print each non-empty group as a `## Group Name` heading.
+   - Under each heading, list installed/global primary and chained skills as `/<name> — <description>  [type]`.
+   - Show orchestrator skills with an `⚙` prefix: `⚙ /<name> — <description>  [type]`.
+   - Show sub-skills indented under their parent skill (identified by the `parent:` frontmatter field or by living under a `frameworks/` directory). Format: `  ↳ /<name> — <description>  [sub-skill]`. If the parent is not in the same group, place sub-skills in a "Sub-skills" subsection at the end of the parent's group.
+   - For available-but-not-installed pack skills, list as `/<name> — <description>  [type]  ⚠ requires \`npx skillpacks install <skill>\` or \`npx skillpacks install <pack>\` inside Claude Code, or \`npx skillpacks install <pack-or-skill>\` from the project shell`.
+   - Omit groups that have no skills (after filtering in search mode).
+   - At the bottom, print a total count: `**N skills** installed (M sub-skills), **P skills** available via packs` (or `**N skills** matching "<keyword>"`).
+
+## Output
+
+### List mode (default — grouped by workflow stage)
+```
+## Discovery & Market Fit
+/customer-discovery — Customer discovery interview...  [research]
+/enterprise-icp — Enterprise multi-stakeholder discovery...  [research]
+
+## Strategize
+⚙ /positioning — Parent router — detect market vs product mode...  [research]
+  ↳ /category-design — Play Bigger category design framework  [sub-skill]
+  ↳ /jtbd-positioning — Jobs to Be Done positioning framework  [sub-skill]
+  ↳ /moore-positioning — Geoffrey Moore positioning framework  [sub-skill]
+  ↳ /obviously-awesome — Obviously Awesome positioning framework  [sub-skill]
+  ↳ /strategic-canvas — Strategic Canvas positioning framework  [sub-skill]
+/competitive-analysis — Research competitors...  [research]
+...
+
+## Execution
+⚙ /exec — Execute next plan step...  [execution]
+...
+
+**N skills** installed (M sub-skills), **P skills** available via packs
+```
+
+### Type mode (`/skills types`)
+```
+## Research
+/customer-discovery — Customer discovery interview...
+/competitive-analysis — Research competitors...
+...
+
+## Analysis
+/mvp-gap — Evaluate codebase against customer-discovery evidence...
+...
+
+**N skills** found
+```
+
+## Constraints
+
+- This is a read-only scan — never modify any files.
+- Always read the live frontmatter from SKILL.md files; do not hardcode descriptions.
+- Use the static stage mapping for stage grouping; use the `type` frontmatter field for type grouping.
+- Keep output compact — one line per skill, no extra detail beyond name, description, and type tag.
+- In search mode, if no skills match the keyword, print: `No skills matching "<keyword>"`.
+
+
+## Default Shipping Contract
+
+Follow the shared shipping contract convention in CLAUDE.md.

package/{global → base}/codex/afps-status/ALIGNMENT-PAGE.md

@@ -1,6 +1,6 @@
 # Alignment Page — afps-status
 
-When this skill produces durable deliverables (research, specs, plans, reports, prototypes, or any document output), build a full-depth HTML alignment page at `alignment/afps-status-{topic}.html`. Use a normalized topic slug derived from the app, feature, research subject, report subject, or output filename.
+Alignment pages are optional for this operational skill. By default, report the outcome inline and write only the skill's normal durable artifacts (`tasks/*.md`, reports, queues, benchmark notes, status docs, or other skill-specific files). Build `alignment/afps-status-{topic}.html` only when the user explicitly requests an alignment page or when the agent explicitly identifies a concrete clarification/review need that cannot be resolved cleanly in conversation or the normal artifacts. When an alignment page is created, use the full contract below and a normalized topic slug derived from the app, feature, research subject, report subject, or output filename.
 
 **Visual rendering tier.** Each alignment page declares a rendering tier:
 - `document` (default) — text, tables, approval gates. No charts or interactive elements.
@@ -57,7 +57,9 @@ The tier is set per skill via `visual_tier` in SKILL.md frontmatter (or detected
 
 **Report-only research gates.** For report-only or pre-approval research skills, the first `review` alignment page must explicitly contain proposed research scope, source plan, assumptions/confidence, recommended output path, proposed file changes, and approval gates before synthesized research begins and before any working packet, canonical research, spec, or task file is created or updated.
 
-**Staged research workflow.** Heavy report-first research uses a scope-first three-stage approval workflow. Stage 1 is minimal scope discovery only: inspect enough repository, user, and source context to propose research scope, source plan, assumptions, output paths, and approval questions. Build the `review` alignment page before synthesized research. The page must render the proposed scope, available source categories, known context, assumptions/confidence, proposed working-packet and canonical output paths, and research-scope approval gates. Stop for final compiled response YAML approval of the research scope. Do not synthesize findings, rank candidates, recommend a path, or create working packets, canonical research, spec, or task files in Stage 1. Stage 2 starts only after final compiled response YAML approves the research scope with no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Perform the synthesized research, run required source/code checks, and write only a non-canonical working packet. Flat mode uses `research/_working/preliminary-afps-status-research.md`; product-path mode uses `research/{slug}/_working/preliminary-afps-status-research.md`. Existing raw evidence or search-log outputs may remain as supporting evidence when the skill contract already requires them, but synthesized deliverables stay in the working packet. Update the same `review` alignment page so it renders the full preliminary packet, evidence matrix, assumptions/confidence register, source coverage gaps, proposed canonical file changes, and artifact approval gates. Partial compiled responses revise the working packet and review page, then remain in Stage 2. Stage 3 consumes final compiled response YAML for artifact approval only when it has `approval_status: ready-for-agent-review` and no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Apply approved edits first, archive the working packet to `docs/history/archive/YYYY-MM-DD/HHMMSS/<original-working-path>`, remove the active working packet, write the approved canonical artifacts to the unchanged output paths, and convert the page to `confirmed` with the approval record preserved.
+**Staged research workflow.** Heavy report-first research uses a scope-first three-stage approval workflow. Stage 1 is minimal scope discovery only: inspect enough repository, user, and source context to propose research scope, source plan, assumptions, output paths, and approval questions. Build the `review` alignment page before synthesized research. The page must render the proposed scope, available source categories, known context, assumptions/confidence, proposed working-packet and canonical output paths, research-scope approval gates, and a `Stage 2 Preview / Expected Review Format` section that shows the future Stage 2 review shape before research starts. Stop for final compiled response YAML approval of the research scope. Do not synthesize findings, rank candidates, recommend a path, or create working packets, canonical research, spec, or task files in Stage 1. Stage 2 starts only after final compiled response YAML approves the research scope with no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Perform the synthesized research, run required source/code checks, and write only a non-canonical working packet. Flat mode uses `research/_working/preliminary-afps-status-research.md`; product-path mode uses `research/{slug}/_working/preliminary-afps-status-research.md`. Existing raw evidence or search-log outputs may remain as supporting evidence when the skill contract already requires them, but synthesized deliverables stay in the working packet. Update the same `review` alignment page so it renders the complete working-packet substance as structured HTML review UI: purpose-built sections, tables, matrices, gates, cards, and tier-appropriate charts or diagrams that preserve every packet section, finding, caveat, and decision detail without summary loss. Raw Markdown packet text may appear only as a supplemental source view after the rendered review UI; do not make a `Full Preliminary Packet` or `Full Working Packet` raw Markdown dump, giant `<pre><code>` block, link-only view, or source-only view the primary review surface. Include the evidence matrix, assumptions/confidence register, source coverage gaps, proposed canonical file changes, and artifact approval gates. Partial compiled responses revise the working packet and review page, then remain in Stage 2. Stage 3 consumes final compiled response YAML for artifact approval only when it has `approval_status: ready-for-agent-review` and no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Apply approved edits first, archive the working packet to `docs/history/archive/YYYY-MM-DD/HHMMSS/<original-working-path>`, remove the active working packet, write the approved canonical artifacts to the unchanged output paths, and convert the page to `confirmed` with the approval record preserved.
+
+**Stage 2 review-page template.** Stage 1 scope-review pages must include a `Stage 2 Preview / Expected Review Format` section that previews the exact section sequence, table shapes, evidence treatment, visual density, and approval gates the user will see after research; make it specific enough for the user to flag preferred content formats, grouping, labels, visuals, and evidence density before the agent does heavy research. After scope approval and research, the Stage 2 review page must include these sections as structured HTML, not as raw Markdown dumps: `Research Scope Approved` status block with approved scope, source plan, output paths, and unresolved caveats; `Executive Findings` or a skill-specific top-findings section with confidence labels; `Evidence Matrix` mapping claim, evidence/source/path, inference, confidence, assumptions, and decision impact; `Working Packet Review` with the complete working-packet substance rendered as purpose-built HTML sections, lists, tables, matrices, cards, and tier-appropriate charts or diagrams; `Alternatives / Rejected or Lower-Confidence Findings`; `Source Coverage & Gaps`; `Assumptions / Confidence Register`; `Proposed Canonical Artifacts & File Changes`; a required `User Format Preferences` gate asking whether the layout, tables, grouping, visuals, labels, and evidence density match expectations; and a required `Final Artifact Approval` gate for Stage 3 readiness. Raw Markdown packet text, search logs, or source notes may appear only as supplemental source views after the rendered review UI and never replace the Stage 2 review sections.
 
 **Glossary Additions gate.** When this research introduces domain-specific terms, acronyms, or concept definitions that a reader outside the project would not know, include a `## Glossary Additions` section in the alignment page. Render a table of proposed terms with columns: Term, Definition, Source (`afps-status`), Category (business/tooling/workflow/technical/domain), and per-term Approve/Edit/Reject/Flag radio controls. Only user-approved terms are appended to the target glossary (`research/glossary.md` or `research/{slug}/glossary.md` for scoped paths) during the confirmed-page write step. When the skill operates in a product-path scope, ask whether each term belongs in the parent or scoped glossary; default to the scoped glossary.
 

package/{global → base}/codex/afps-status/CHANGELOG.md

@@ -1,5 +1,13 @@
 # Changelog
 
+## v0.4 - 2026-06-12
+
+- Made alignment pages optional by default: report inline and write the skill's normal durable artifacts unless the user requests an alignment page or the agent identifies a concrete clarification/review need.
+
+## v0.3 - 2026-06-12
+
+- Standardized active pack and skill install guidance on `npx skillpacks install <pack-or-skill>` instead of agent-native `/pack install` or `$pack install` recommendations.
+
 ## v0.2 - 2026-06-11
 
 - Added npm-aware install-route alternatives to AFPS pack fallback recommendations while preserving Codex `$pack install` routes.

package/base/codex/afps-status/SKILL.md

@@ -0,0 +1,104 @@
+---
+name: afps-status
+description: Summarize AFPS product-workflow progress from existing artifacts and recommend the next concrete skill command
+type: analysis
+version: v0.4
+argument-hint: "[optional project path, product path, or focus]"
+---
+
+# AFPS Status
+
+Invoke as `$afps-status`.
+
+Use this skill when the user asks where a product project is in the AFPS workflow, what research/planning/implementation artifact is missing next, whether task docs match product evidence, or which AFPS command should run next.
+
+AFPS here means the product workflow from raw idea through concept scoping, customer discovery/research, lifecycle/growth planning, specs, roadmap/phase work, implementation, validation, and shipping. This is read-mostly reconciliation. It summarizes existing artifacts and recommends a route; it does not create a competing workflow state system.
+
+## Process
+
+1. Resolve target project:
+   - Default to the current working directory.
+   - If `$ARGUMENTS` names a path, inspect that project.
+   - If `$ARGUMENTS` names a product path, app, customer, audience, or focus, prioritize matching artifacts under `research/`, `specs/`, `tasks/`, and `alignment/`.
+   - Confirm whether the target is a git worktree when possible. Continue with filesystem evidence if git is unavailable.
+2. Read project orientation:
+   - `.agents/project.json`
+   - `README.md`, `AGENTS.md`, `CLAUDE.md`
+   - package/workspace manifests and obvious app entrypoints when needed to understand whether implementation exists.
+   - Use `scripts/pack.sh list-packs` when available to determine enabled packs; do not grep `.agents/project.json` directly when choosing installed-pack routes.
+3. Inspect AFPS evidence from existing artifacts:
+   - Product-path state: `research/.progress.yaml`, including legacy `active_path` normalized mentally to `active_paths`.
+   - Concept artifacts: `research/idea-brief*.md`, app-scoped `research/*/idea-brief*.md`, and concept/interview notes.
+   - Discovery artifacts: customer-discovery docs such as `research/icp.md`, competitive analysis, customer feedback, journey/lifecycle maps, value-prop canvas, positioning, lean canvas, market evidence, and assumption/risk trackers.
+   - Lifecycle/growth artifacts: onboarding, activation, retention, conversion, monetization, GTM, growth model, metrics, PMF, and experiment docs.
+   - Product/spec artifacts: `specs/`, `spec.md`, app/feature specs, UX/UI/prototype/UAT/consolidation notes, and alignment pages under `alignment/`.
+   - Execution artifacts: `tasks/roadmap.md`, `tasks/todo.md`, `tasks/manual-todo.md`, `tasks/record-todo.md`, `tasks/recurring-todo.md`, `tasks/history.md`, `tasks/phases/`, and recent validation notes.
+   - Git evidence: `git status --short`, current branch/upstream, last relevant commits, unpushed commits, and changed files.
+4. Reconcile evidence instead of trusting one file:
+   - Distinguish missing artifacts, stale artifacts, contradictory artifacts, completed work, active implementation tasks, manual blockers, unvalidated implementation, and unshipped local changes.
+   - Treat `research/.progress.yaml` as a manifest of product/app/customer focus, not as the source of truth over concrete artifacts.
+   - If product-path manifest entries are missing or stale, report the exact proposed update in prose. Do not write `research/.progress.yaml` unless the user explicitly asks for mutation.
+   - If task docs contradict research/spec/code/git evidence, call out the contradiction and route to reconciliation rather than choosing whichever artifact is newest.
+5. Classify AFPS stage:
+   - `unscoped`: no concept brief or the concept is too unclear for customer discovery.
+   - `concept-ready`: concept exists but discovery pack/skills are not enabled.
+   - `discovery-needed`: concept exists and discovery skills are enabled, but customer discovery is absent or not specific enough.
+   - `research-incomplete`: customer discovery exists but market, competitive, value, positioning, journey, or lifecycle evidence is missing.
+   - `lifecycle-gap`: discovery exists but onboarding, conversion, activation, retention, monetization, GTM, or metrics questions block spec quality.
+   - `spec-needed`: research is sufficient but durable product/spec artifacts are absent or stale.
+   - `roadmap-needed`: research/spec artifacts exist but `tasks/roadmap.md` or `tasks/todo.md` is missing, stale, contradictory, or not actionable.
+   - `execution-ready`: a clear unchecked implementation task exists with no blocking manual task.
+   - `ship-needed`: implementation changes are present, completed, or unpushed but validation, task review, commit, push, or deploy packaging is pending.
+   - `reconcile-needed`: artifacts conflict enough that the next step should be reconciliation before new research or implementation.
+6. Choose the next route with these rules:
+   - No concept brief or unclear concept: `$idea-scope-brief`
+   - Concept exists but business discovery is missing: `npx skillpacks install business-discovery` from the project shell.
+   - Concept exists and discovery is enabled, but no customer-discovery evidence: `$customer-discovery`
+   - Customer discovery exists but market/value evidence is missing: the most specific discovery command, usually `$competitive-analysis`, `$value-prop-canvas`, or `$positioning`
+   - Journey/lifecycle/growth questions are missing after discovery: recommend the relevant installed command, or install the required pack first, such as `npx skillpacks install customer-lifecycle` from the project shell, or `npx skillpacks install business-growth` from the project shell.
+   - Research/specs exist but task queue is stale or absent: `$roadmap`
+   - Clear executable task exists: `$exec`
+   - Implementation is done but unvalidated, dirty, uncommitted, unpushed, or otherwise unshipped: `$ship`
+   - Contradictory research/spec/task evidence: `$reconcile-research` when business-ops is enabled, `$spec-drift` when agent-work-admin is enabled, otherwise `$codebase-status` with a focused prompt naming the contradiction.
+7. Validate command availability before recommending pack-local routes:
+   - Use `scripts/pack.sh list-packs` when present to detect enabled packs.
+   - If the best command lives in an uninstalled pack, recommend the package install command instead of the unavailable command: `npx skillpacks install <pack>` from the project shell.
+   - If `scripts/pack.sh` is missing or pack lookup fails, silently fall back to the global/default route and mention the degraded lookup only if it changes confidence.
+
+## Output
+
+Produce a concise structured report with:
+
+- **Overview:** repo path, product/app focus, git status, enabled packs, and whether AFPS evidence is single-path or multi-path.
+- **Artifact Map:** concept, customer discovery/research, lifecycle/growth, specs/prototypes/UAT, tasks, alignment pages, and shipping evidence with present/missing/stale status.
+- **AFPS Stage:** one stage label from the workflow above, with confidence and evidence.
+- **Contradictions And Gaps:** conflicting artifacts, missing product-path manifest updates, stale task queues, manual blockers, validation/shipping gaps, and uncertainty.
+- **Recommended Route:** the next concrete work item and why it is the narrowest route.
+
+End with exactly:
+
+```md
+**Next work:** <specific AFPS step or blocker>
+**Recommended next command:** <one command or route>
+```
+
+## Constraints
+
+- Read-only by default. Do not modify workflow state, task docs, research docs, specs, or git state unless the user explicitly asks for mutation.
+- Do not create a new AFPS state file or schema. Use existing artifacts, especially `research/.progress.yaml`, `research/`, `specs/`, `tasks/`, `alignment/`, and git.
+- Propose missing `research/.progress.yaml` updates in the report instead of writing them by default.
+- Do not run expensive tests, installs, web research, deploys, or external-account actions during status synthesis.
+- Do not treat `tasks/record-todo.md` or `tasks/recurring-todo.md` as execution queues unless an item has clearly been promoted into `tasks/todo.md`.
+- Do not route agent-executable repo work to `$guide`; reserve guided/manual routes for human-only blockers.
+- Do not create or modify GitHub Actions workflows.
+
+## Alignment Page
+
+By default, this skill reports results inline and writes only its normal durable artifacts (for example `tasks/*.md`, reports, queues, benchmark notes, status docs, or other skill-specific files). Do not build an alignment page automatically. Create `alignment/afps-status-{topic}.html` only when the user explicitly requests an alignment page or when you explicitly identify a concrete clarification/review need that cannot be handled cleanly inline; when you create one, follow `ALIGNMENT-PAGE.md` in this skill's directory.
+
+## Default Shipping Contract
+
+- **Default next-step routing:** when reporting completion, include the two-line pair `**Next work:** <specific task or "none">` and `**Recommended next command:** <one command or route>` so the next caller has a concrete handoff.
+- Normally read-only and should not create or modify tracked repository files.
+- If the user explicitly asks this skill to create or modify tracked files, finish by committing and pushing all intended changes to the repository primary branch (`main` when present, otherwise `master`) before stopping.
+- This contract does not override stricter safety rules about secrets, destructive history changes, release publication/tag confirmation, production deploy confirmation, paid actions, or public visibility changes.

package/base/codex/afps-status/archive/v0.3/SKILL.md

@@ -0,0 +1,104 @@
+---
+name: afps-status
+description: Summarize AFPS product-workflow progress from existing artifacts and recommend the next concrete skill command
+type: analysis
+version: v0.3
+argument-hint: "[optional project path, product path, or focus]"
+---
+
+# AFPS Status
+
+Invoke as `$afps-status`.
+
+Use this skill when the user asks where a product project is in the AFPS workflow, what research/planning/implementation artifact is missing next, whether task docs match product evidence, or which AFPS command should run next.
+
+AFPS here means the product workflow from raw idea through concept scoping, customer discovery/research, lifecycle/growth planning, specs, roadmap/phase work, implementation, validation, and shipping. This is read-mostly reconciliation. It summarizes existing artifacts and recommends a route; it does not create a competing workflow state system.
+
+## Process
+
+1. Resolve target project:
+   - Default to the current working directory.
+   - If `$ARGUMENTS` names a path, inspect that project.
+   - If `$ARGUMENTS` names a product path, app, customer, audience, or focus, prioritize matching artifacts under `research/`, `specs/`, `tasks/`, and `alignment/`.
+   - Confirm whether the target is a git worktree when possible. Continue with filesystem evidence if git is unavailable.
+2. Read project orientation:
+   - `.agents/project.json`
+   - `README.md`, `AGENTS.md`, `CLAUDE.md`
+   - package/workspace manifests and obvious app entrypoints when needed to understand whether implementation exists.
+   - Use `scripts/pack.sh list-packs` when available to determine enabled packs; do not grep `.agents/project.json` directly when choosing installed-pack routes.
+3. Inspect AFPS evidence from existing artifacts:
+   - Product-path state: `research/.progress.yaml`, including legacy `active_path` normalized mentally to `active_paths`.
+   - Concept artifacts: `research/idea-brief*.md`, app-scoped `research/*/idea-brief*.md`, and concept/interview notes.
+   - Discovery artifacts: customer-discovery docs such as `research/icp.md`, competitive analysis, customer feedback, journey/lifecycle maps, value-prop canvas, positioning, lean canvas, market evidence, and assumption/risk trackers.
+   - Lifecycle/growth artifacts: onboarding, activation, retention, conversion, monetization, GTM, growth model, metrics, PMF, and experiment docs.
+   - Product/spec artifacts: `specs/`, `spec.md`, app/feature specs, UX/UI/prototype/UAT/consolidation notes, and alignment pages under `alignment/`.
+   - Execution artifacts: `tasks/roadmap.md`, `tasks/todo.md`, `tasks/manual-todo.md`, `tasks/record-todo.md`, `tasks/recurring-todo.md`, `tasks/history.md`, `tasks/phases/`, and recent validation notes.
+   - Git evidence: `git status --short`, current branch/upstream, last relevant commits, unpushed commits, and changed files.
+4. Reconcile evidence instead of trusting one file:
+   - Distinguish missing artifacts, stale artifacts, contradictory artifacts, completed work, active implementation tasks, manual blockers, unvalidated implementation, and unshipped local changes.
+   - Treat `research/.progress.yaml` as a manifest of product/app/customer focus, not as the source of truth over concrete artifacts.
+   - If product-path manifest entries are missing or stale, report the exact proposed update in prose. Do not write `research/.progress.yaml` unless the user explicitly asks for mutation.
+   - If task docs contradict research/spec/code/git evidence, call out the contradiction and route to reconciliation rather than choosing whichever artifact is newest.
+5. Classify AFPS stage:
+   - `unscoped`: no concept brief or the concept is too unclear for customer discovery.
+   - `concept-ready`: concept exists but discovery pack/skills are not enabled.
+   - `discovery-needed`: concept exists and discovery skills are enabled, but customer discovery is absent or not specific enough.
+   - `research-incomplete`: customer discovery exists but market, competitive, value, positioning, journey, or lifecycle evidence is missing.
+   - `lifecycle-gap`: discovery exists but onboarding, conversion, activation, retention, monetization, GTM, or metrics questions block spec quality.
+   - `spec-needed`: research is sufficient but durable product/spec artifacts are absent or stale.
+   - `roadmap-needed`: research/spec artifacts exist but `tasks/roadmap.md` or `tasks/todo.md` is missing, stale, contradictory, or not actionable.
+   - `execution-ready`: a clear unchecked implementation task exists with no blocking manual task.
+   - `ship-needed`: implementation changes are present, completed, or unpushed but validation, task review, commit, push, or deploy packaging is pending.
+   - `reconcile-needed`: artifacts conflict enough that the next step should be reconciliation before new research or implementation.
+6. Choose the next route with these rules:
+   - No concept brief or unclear concept: `$idea-scope-brief`
+   - Concept exists but business discovery is missing: `npx skillpacks install business-discovery` from the project shell.
+   - Concept exists and discovery is enabled, but no customer-discovery evidence: `$customer-discovery`
+   - Customer discovery exists but market/value evidence is missing: the most specific discovery command, usually `$competitive-analysis`, `$value-prop-canvas`, or `$positioning`
+   - Journey/lifecycle/growth questions are missing after discovery: recommend the relevant installed command, or install the required pack first, such as `npx skillpacks install customer-lifecycle` from the project shell, or `npx skillpacks install business-growth` from the project shell.
+   - Research/specs exist but task queue is stale or absent: `$roadmap`
+   - Clear executable task exists: `$exec`
+   - Implementation is done but unvalidated, dirty, uncommitted, unpushed, or otherwise unshipped: `$ship`
+   - Contradictory research/spec/task evidence: `$reconcile-research` when business-ops is enabled, `$spec-drift` when agent-work-admin is enabled, otherwise `$codebase-status` with a focused prompt naming the contradiction.
+7. Validate command availability before recommending pack-local routes:
+   - Use `scripts/pack.sh list-packs` when present to detect enabled packs.
+   - If the best command lives in an uninstalled pack, recommend the package install command instead of the unavailable command: `npx skillpacks install <pack>` from the project shell.
+   - If `scripts/pack.sh` is missing or pack lookup fails, silently fall back to the global/default route and mention the degraded lookup only if it changes confidence.
+
+## Output
+
+Produce a concise structured report with:
+
+- **Overview:** repo path, product/app focus, git status, enabled packs, and whether AFPS evidence is single-path or multi-path.
+- **Artifact Map:** concept, customer discovery/research, lifecycle/growth, specs/prototypes/UAT, tasks, alignment pages, and shipping evidence with present/missing/stale status.
+- **AFPS Stage:** one stage label from the workflow above, with confidence and evidence.
+- **Contradictions And Gaps:** conflicting artifacts, missing product-path manifest updates, stale task queues, manual blockers, validation/shipping gaps, and uncertainty.
+- **Recommended Route:** the next concrete work item and why it is the narrowest route.
+
+End with exactly:
+
+```md
+**Next work:** <specific AFPS step or blocker>
+**Recommended next command:** <one command or route>
+```
+
+## Constraints
+
+- Read-only by default. Do not modify workflow state, task docs, research docs, specs, or git state unless the user explicitly asks for mutation.
+- Do not create a new AFPS state file or schema. Use existing artifacts, especially `research/.progress.yaml`, `research/`, `specs/`, `tasks/`, `alignment/`, and git.
+- Propose missing `research/.progress.yaml` updates in the report instead of writing them by default.
+- Do not run expensive tests, installs, web research, deploys, or external-account actions during status synthesis.
+- Do not treat `tasks/record-todo.md` or `tasks/recurring-todo.md` as execution queues unless an item has clearly been promoted into `tasks/todo.md`.
+- Do not route agent-executable repo work to `$guide`; reserve guided/manual routes for human-only blockers.
+- Do not create or modify GitHub Actions workflows.
+
+## Alignment Page
+
+When this skill produces durable deliverables (research, specs, plans, reports, prototypes, or any document output), build a full-depth HTML alignment page following `ALIGNMENT-PAGE.md` in this skill's directory. Output: `alignment/afps-status-{topic}.html`.
+
+## Default Shipping Contract
+
+- **Default next-step routing:** when reporting completion, include the two-line pair `**Next work:** <specific task or "none">` and `**Recommended next command:** <one command or route>` so the next caller has a concrete handoff.
+- Normally read-only and should not create or modify tracked repository files.
+- If the user explicitly asks this skill to create or modify tracked files, finish by committing and pushing all intended changes to the repository primary branch (`main` when present, otherwise `master`) before stopping.
+- This contract does not override stricter safety rules about secrets, destructive history changes, release publication/tag confirmation, production deploy confirmation, paid actions, or public visibility changes.

package/{global/claude → base/codex}/animation-design-planner/ALIGNMENT-PAGE.md

@@ -57,7 +57,9 @@ The tier is set per skill via `visual_tier` in SKILL.md frontmatter (or detected
 
 **Report-only research gates.** For report-only or pre-approval research skills, the first `review` alignment page must explicitly contain proposed research scope, source plan, assumptions/confidence, recommended output path, proposed file changes, and approval gates before synthesized research begins and before any working packet, canonical research, spec, or task file is created or updated.
 
-**Staged research workflow.** Heavy report-first research uses a scope-first three-stage approval workflow. Stage 1 is minimal scope discovery only: inspect enough repository, user, and source context to propose research scope, source plan, assumptions, output paths, and approval questions. Build the `review` alignment page before synthesized research. The page must render the proposed scope, available source categories, known context, assumptions/confidence, proposed working-packet and canonical output paths, and research-scope approval gates. Stop for final compiled response YAML approval of the research scope. Do not synthesize findings, rank candidates, recommend a path, or create working packets, canonical research, spec, or task files in Stage 1. Stage 2 starts only after final compiled response YAML approves the research scope with no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Perform the synthesized research, run required source/code checks, and write only a non-canonical working packet. Flat mode uses `research/_working/preliminary-animation-design-planner-research.md`; product-path mode uses `research/{slug}/_working/preliminary-animation-design-planner-research.md`. Existing raw evidence or search-log outputs may remain as supporting evidence when the skill contract already requires them, but synthesized deliverables stay in the working packet. Update the same `review` alignment page so it renders the full preliminary packet, evidence matrix, assumptions/confidence register, source coverage gaps, proposed canonical file changes, and artifact approval gates. Partial compiled responses revise the working packet and review page, then remain in Stage 2. Stage 3 consumes final compiled response YAML for artifact approval only when it has `approval_status: ready-for-agent-review` and no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Apply approved edits first, archive the working packet to `docs/history/archive/YYYY-MM-DD/HHMMSS/<original-working-path>`, remove the active working packet, write the approved canonical artifacts to the unchanged output paths, and convert the page to `confirmed` with the approval record preserved.
+**Staged research workflow.** Heavy report-first research uses a scope-first three-stage approval workflow. Stage 1 is minimal scope discovery only: inspect enough repository, user, and source context to propose research scope, source plan, assumptions, output paths, and approval questions. Build the `review` alignment page before synthesized research. The page must render the proposed scope, available source categories, known context, assumptions/confidence, proposed working-packet and canonical output paths, research-scope approval gates, and a `Stage 2 Preview / Expected Review Format` section that shows the future Stage 2 review shape before research starts. Stop for final compiled response YAML approval of the research scope. Do not synthesize findings, rank candidates, recommend a path, or create working packets, canonical research, spec, or task files in Stage 1. Stage 2 starts only after final compiled response YAML approves the research scope with no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Perform the synthesized research, run required source/code checks, and write only a non-canonical working packet. Flat mode uses `research/_working/preliminary-animation-design-planner-research.md`; product-path mode uses `research/{slug}/_working/preliminary-animation-design-planner-research.md`. Existing raw evidence or search-log outputs may remain as supporting evidence when the skill contract already requires them, but synthesized deliverables stay in the working packet. Update the same `review` alignment page so it renders the complete working-packet substance as structured HTML review UI: purpose-built sections, tables, matrices, gates, cards, and tier-appropriate charts or diagrams that preserve every packet section, finding, caveat, and decision detail without summary loss. Raw Markdown packet text may appear only as a supplemental source view after the rendered review UI; do not make a `Full Preliminary Packet` or `Full Working Packet` raw Markdown dump, giant `<pre><code>` block, link-only view, or source-only view the primary review surface. Include the evidence matrix, assumptions/confidence register, source coverage gaps, proposed canonical file changes, and artifact approval gates. Partial compiled responses revise the working packet and review page, then remain in Stage 2. Stage 3 consumes final compiled response YAML for artifact approval only when it has `approval_status: ready-for-agent-review` and no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Apply approved edits first, archive the working packet to `docs/history/archive/YYYY-MM-DD/HHMMSS/<original-working-path>`, remove the active working packet, write the approved canonical artifacts to the unchanged output paths, and convert the page to `confirmed` with the approval record preserved.
+
+**Stage 2 review-page template.** Stage 1 scope-review pages must include a `Stage 2 Preview / Expected Review Format` section that previews the exact section sequence, table shapes, evidence treatment, visual density, and approval gates the user will see after research; make it specific enough for the user to flag preferred content formats, grouping, labels, visuals, and evidence density before the agent does heavy research. After scope approval and research, the Stage 2 review page must include these sections as structured HTML, not as raw Markdown dumps: `Research Scope Approved` status block with approved scope, source plan, output paths, and unresolved caveats; `Executive Findings` or a skill-specific top-findings section with confidence labels; `Evidence Matrix` mapping claim, evidence/source/path, inference, confidence, assumptions, and decision impact; `Working Packet Review` with the complete working-packet substance rendered as purpose-built HTML sections, lists, tables, matrices, cards, and tier-appropriate charts or diagrams; `Alternatives / Rejected or Lower-Confidence Findings`; `Source Coverage & Gaps`; `Assumptions / Confidence Register`; `Proposed Canonical Artifacts & File Changes`; a required `User Format Preferences` gate asking whether the layout, tables, grouping, visuals, labels, and evidence density match expectations; and a required `Final Artifact Approval` gate for Stage 3 readiness. Raw Markdown packet text, search logs, or source notes may appear only as supplemental source views after the rendered review UI and never replace the Stage 2 review sections.
 
 **Prototype tier rendering.** This skill's alignment page uses the `prototype` tier. In addition to charts and diagrams, functional interactive components (clickable flows, live CSS previews, drag interactions) are permitted. Prototypes are ephemeral previews, not production code. Each interactive component must include a reset button that restores initial state. Interactive components must be self-contained within the HTML file with no external dependencies. Include all visual tier requirements (chart snippets, table fallbacks, aria-labels, toggles) plus: state isolation (no localStorage/sessionStorage persistence), clear "this is a preview" labeling, and graceful degradation when JavaScript is disabled.
 

package/{global → base}/codex/animation-design-planner/CHANGELOG.md

@@ -1,5 +1,10 @@
 # Changelog
 
+## v0.1 - 2026-06-13
+
+- Removed direct execution-loop command handoffs from non-exec routing; route through approved YAML, task, or roadmap artifacts instead.
+
+
 ## v0.0 - 2026-06-05 (subskill expansion)
 
 - Expanded CSS transitions subskill: sequencing/orchestration, will-change lifecycle, forced reflow triggers, exit animation patterns