@hegemonart/get-design-done 1.48.0 → 1.50.0

package/.claude-plugin/marketplace.json

@@ -5,14 +5,14 @@
   },
   "metadata": {
     "description": "Get Design Done — 5-stage agent-orchestrated design pipeline with 9 connections, handoff-first workflow, bidirectional Figma write-back, 22+ specialized agents, queryable knowledge layer (intel store, dependency analysis, learnings extraction), and a self-improvement loop (reflector, frontmatter + budget feedback, global-skills layer). v1.20.0 ships the SDK foundation: gdd-state MCP server (11 typed tools), lockfile-safe STATE.md mutations, event stream, and resilience primitives (jittered-backoff, rate-guard, error-classifier, iteration-budget) for rate-limit + 429 + context-overflow recovery. Full CI/CD pipeline (Node 22/24 × Linux/macOS/Windows) and release automation (auto-tag + GitHub Release + release-time smoke test).",
-    "version": "1.48.0"
+    "version": "1.50.0"
   },
   "plugins": [
     {
       "name": "get-design-done",
       "source": "./",
       "description": "Agent-orchestrated 5-stage design pipeline: Brief → Explore → Plan → Design → Verify. 22+ specialized agents, 9 connections (Figma, Refero, Preview, Storybook, Chromatic, Figma Writer, Graphify, Pinterest, Claude Design), Claude Design handoff, bidirectional Figma write-back, and a queryable intel store (.design/intel/) for dependency and learnings queries. Standalone commands: style, darkmode, compare, figma-write, graphify, handoff, analyze-dependencies, skill-manifest, extract-learnings. Embeds NNG heuristics, WCAG thresholds, typographic systems, motion framework, and anti-pattern catalog. Ships with a full CI/CD pipeline (Node 22/24 × Linux/macOS/Windows) and release automation. Optimization layer (v1.0.4.1, retroactive): gdd-router + gdd-cache-manager skills, PreToolUse budget-enforcer hook, tier-aware agent frontmatter, lazy checker gates, streaming synthesizer, /gdd:warm-cache + /gdd:optimize commands, and cost telemetry at .design/telemetry/costs.jsonl — targeting 50-70% per-task token-cost reduction with no quality-floor regression. v1.20.0 SDK foundation: gdd-state MCP server (11 typed tools), lockfile-safe STATE.md mutations, event stream at .design/telemetry/events.jsonl, resilience primitives (jittered-backoff, rate-guard, error-classifier, iteration-budget) with rate-limit + 429 + context-overflow recovery, and TypeScript toolchain.",
-      "version": "1.48.0",
+      "version": "1.50.0",
       "author": {
         "name": "hegemonart"
       },

package/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "get-design-done",
   "short_name": "gdd",
-  "version": "1.48.0",
+  "version": "1.50.0",
   "description": "Agent-orchestrated 5-stage design pipeline: Brief → Explore → Plan → Design → Verify. 22+ specialized agents, 9 connections (Figma, Refero, Preview, Storybook, Chromatic, Figma Writer, Graphify, Pinterest, Claude Design), handoff-first workflow via Claude Design bundles, bidirectional Figma write-back (annotations, Code Connect), queryable intel store (`.design/intel/`) for O(1) design surface lookups, and self-improvement loop (reflector agent, frontmatter + budget feedback, global-skills layer at `~/.claude/gdd/global-skills/`). Standalone commands: style, darkmode, compare, figma-write, graphify, handoff, analyze-dependencies, skill-manifest, extract-learnings, reflect, apply-reflections. Embeds NNG heuristics, WCAG thresholds, typographic systems, motion framework, and anti-pattern catalog. Ships with a full CI/CD pipeline (Node 22/24 × Linux/macOS/Windows, lint + schema + frontmatter + stale-ref + shellcheck + gitleaks + injection-scan + blocking size-budget) and release automation (auto-tag + GitHub Release + release-time smoke test). Optimization layer (v1.0.4.1, retroactive): gdd-router + gdd-cache-manager skills, PreToolUse budget-enforcer hook, tier-aware agent frontmatter, lazy checker gates, streaming synthesizer, /gdd:warm-cache + /gdd:optimize commands, and cost telemetry at .design/telemetry/costs.jsonl — targeting 50-70% per-task token-cost reduction with no quality-floor regression. v1.20.0 SDK foundation: gdd-state MCP server (11 typed tools), lockfile-safe STATE.md mutations, event stream at .design/telemetry/events.jsonl, resilience primitives (jittered-backoff, rate-guard, error-classifier, iteration-budget) with rate-limit + 429 + context-overflow recovery, and TypeScript toolchain. v1.27.7 ships gdd-mcp (Phase 27.7): 12 read-only MCP tools for sub-3s priming. v1.28.0 (Phase 28): Foundational References Tier 2 — 5 new reference files (color-theory, composition, proportion-systems, i18n, contrast-advanced), 2 verifier i18n probes + 1 explore i18n-readiness probe, 12 additive cross-link insertions across 10 existing references, 2 orthogonal audit-scoring lens-tags (composition_alignment + i18n_readiness).",
   "author": {
     "name": "hegemonart",
@@ -71,7 +71,13 @@
     "flutter",
     "email",
     "print",
-    "pdf"
+    "pdf",
+    "worktree-safe",
+    "anti-slop",
+    "confidence-gate",
+    "anti-slop-rubric",
+    "skill-composition",
+    "skill-graph"
   ],
   "skills": [
     "./skills/"

package/CHANGELOG.md

@@ -4,6 +4,99 @@ All notable changes to get-design-done are documented here. Versions follow [sem
 
 ---
 
+## [1.50.0] - 2026-06-03
+
+### Phase 50 - Authoring Contract v3
+
+Two cross-repo-validated additions to the authoring contract. A verb-based anti-slop rubric catches a different
+class of failure than the noun-based 7-pillar audit (the pillars ask "is the typography wrong?", the verb axes ask
+"is it generically AI-default?"). And a machine-parseable skill-composition manifest fills the "no skill calls
+another skill" gap with a DAG validator and an auto-generated skill graph. Planned and executed via the GSD pipeline
+(3 parallel executor subagents). No new runtime dependency, no new egress. This closes the 45-to-50 release run.
+
+### Breaking changes
+
+- **Skill descriptions move to a multi-paragraph v3 form** (`<what>. Use when <triggers>. Activates for requests
+  involving <kw1>, <kw2>, <kw3>.`). Both the v2 and v3 forms are accepted for one minor version (transition window);
+  `/gdd:health` reports adoption ("Skills: N/88 in v3 form"). The 1024-char cap is unchanged. A new boilerplate-cohort
+  lint (`validate:skill-frontmatter`) fails CI if three or more skills share an identical opening sentence.
+- **Two new CI gates guard the composition graph.** `validate:composition-graph` fails on a cycle or a dangling
+  `composes_with`/`next_skills` reference; `build:skill-graph:check` fails if `reference/skill-graph.md` drifts from
+  `skills.json`. Authors adding composition edges must keep the graph acyclic and the generated graph current.
+
+### Added
+
+- **`reference/anti-slop-rubric.md`**: 5 orthogonal verb axes (Directness, Distinctness, Hierarchy, Authenticity,
+  Density), 1-10 each; `sum < 35/50` routes a finding to `design-debt-crawler` as `category: aesthetic-slop`.
+  `design-auditor` emits `verb_axes_scored` as a lens-tag (no pillar change, mirrors `emotion_levels`).
+- **`reference/visual-tells.md` v2**: the 8 Phase-49 categories plus 5 more (stock-photo-people, badge-spam,
+  oversized-single-word, motion-without-content-intent, narrator-from-a-distance-UI), each cross-linked to its
+  primary verb axis.
+- **Skill composition manifest**: optional `composes_with`/`next_skills` frontmatter (documented in the skills
+  schema), `scripts/validate-composition-graph.cjs` (cycle + dangling-ref detection), and an auto-generated
+  `reference/skill-graph.md` (mermaid, grouped by lifecycle stage) via `scripts/generate-skill-graph.cjs`.
+- **`reference/skill-authoring-contract.md` v3** (description form + transition window + composition fields) +
+  **`/gdd:new-skill`** scaffolder (`scripts/lib/manifest/scaffolder.cjs`, @clack/prompts) that emits a v3-compliant
+  skill, with `composes_with` suggestions by lifecycle stage.
+- **Description migration**: 18 high-traffic skills (brief, explore, plan, design, verify, audit, scan, discover, do,
+  ship, health, progress, live, connections, darkmode, compare, fast, quick) moved to the v3 form; the rest follow
+  gradually under the transition window. `/gdd:health` + `/gdd:progress` surface adoption and composition-graph readiness.
+
+### Notes
+
+- 6-manifest lockstep at **v1.50.0** + `OFF_CADENCE_VERSIONS.add('1.50.0')` + 37 `manifests-version.txt` baselines +
+  plugin keywords (`anti-slop-rubric`, `skill-composition`, `skill-graph`). Re-locked: skill-list (88), registry (175),
+  registry-diff, phase-42 count (112), 6 `*-after.md` byte snapshots (brief/design/explore/verify + health/progress),
+  the phase-28.5 distribution + warn count (4 -> 5, progress crossed 100 lines), tarball golden 907 -> 912 (+5).
+- The verb axes are an orthogonal lens (no new pillar, no scoring-math change). `composes_with`/`next_skills` are
+  optional in v3 (mandatory deferred to v4). Out of scope: rubric auto-fix, LLM-judge of axes, skill body migration.
+
+---
+
+## [1.49.0] - 2026-06-03
+
+### Phase 49 - Quick Anti-Slop Floor
+
+Three small, atomic safety and policy primitives identified in the cross-repo synthesis, each low-risk and
+high-signal: a worktree redirect that ends the recurring `.planning/` leak, a free anti-slop regex pass on every
+front-end file write, and a reviewer confidence gate that stops severity inflation. Planned and executed via the
+GSD pipeline (3 parallel executor subagents). No new runtime dependency, no new egress.
+
+### Breaking changes
+
+- **`.design/` and `.planning/` writes redirect to the main repo root inside a git worktree.** `scripts/lib/worktree-resolve.cjs`
+  detects a worktree (`git rev-parse --git-dir` vs `--git-common-dir`) and the gdd-state write path (`resolveStatePath`,
+  used by all 11 state tools) now resolves STATE there, with a one-line stderr notice. Outside a worktree, behavior is
+  unchanged. Tooling that assumed `.design/` always lived under `process.cwd()` should resolve through the helper.
+- **Findings now carry a `confidence` field and design-fixer filters on it.** design-auditor, design-verifier, and
+  design-debt-crawler emit `confidence: 0.0-1.0` per finding; design-fixer drops `## Tentative` findings and routes
+  BLOCKER/MAJOR findings below 0.8 confidence to user review instead of auto-fix. Consumers of these findings should
+  read the new field.
+
+### Added
+
+- **`scripts/lib/worktree-resolve.cjs`** (resolveRepoRoot / isWorktree / resolveDesignRoot / resolvePlanningRoot;
+  graceful fallback, injectable exec) wired into the state write path + a one-line worktree note in the 7
+  artifact-writer agents.
+- **`hooks/gdd-design-quality-check.js`**: an advisory PostToolUse hook scanning `Write`/`Edit`/`MultiEdit` to
+  `.tsx`/`.vue`/`.svelte`/`.astro` for 8 default-AI-aesthetic tells (gradient spam, generic CTAs, centered-everything,
+  font-inter default, purple/violet default, glassmorphism spam, isometric fallback, decorative motion). WARN-only,
+  emits a `design_quality_warn` event. Catalogued in **`reference/visual-tells.md`** (8 named categories with diagnostic
+  regex + remediation).
+- **Reviewer confidence gate**: a 4-question Pre-Report Gate + the `confidence` field across the three audit agents,
+  a `scripts/lib/confidence-route.cjs` routing helper (`fix` / `user-review` / `drop`), and
+  **`reference/reviewer-confidence-gate.md`** (template + rationale + 4 before/after examples).
+
+### Notes
+
+- 6-manifest lockstep at **v1.49.0** + `OFF_CADENCE_VERSIONS.add('1.49.0')` + 37 `manifests-version.txt` baselines +
+  plugin keywords (`worktree-safe`, `anti-slop`, `confidence-gate`). Baselines re-locked: hook-list (19),
+  resilience-primitives (39 `scripts/lib/*.cjs`), registry (173), tarball golden 902 -> 907 (+5).
+- WARN-only hook (never blocks); auto-fix of matched tells is out of scope (proposal-only); the verb-based anti-slop
+  rubric and a wider tell catalog are deferred to Phase 50.
+
+---
+
 ## [1.48.0] - 2026-06-03
 
 ### Phase 48 - Audit & Pillar Expansion

package/README.md

@@ -257,6 +257,10 @@ All 14 runtimes receive their native artifact layout (`skills/`, `command/`, `ag
 
 **Audit and pillar expansion (v1.48.0).** Four audit-side gaps close at once. The copy pillar gets a real rubric (`reference/copy-quality.md` + `copy-auditor`): microcopy, error and empty-state text, ARIA and alt text, voice alignment, with an i18n overflow lens. A project-wide `design-debt-crawler` walks an existing codebase (not just the current cycle), enumerates raw color literals, anti-patterns, untokenized components, and contrast/density issues, and writes a priority-scored `.design/debt/DEBT-CATALOG.md`. A `brief-auditor` grades the brief against five anti-patterns (vague verbs, missing audience, immeasurable success criteria, scope creep, missing anti-goals) and surfaces a non-blocking `/gdd:discuss brief` pointer. And the Stage 4.5 quality-gate gains an `a11y` failure class so `axe` / `pa11y` / `lighthouse` regressions route to `design-fixer` like any other gate failure. **No new runtime dependency.**
 
+**Quick anti-slop floor (v1.49.0).** Three small safety primitives. A worktree redirect (`scripts/lib/worktree-resolve.cjs`) sends `.design/` and `.planning/` writes to the main repo root when GDD runs inside a git worktree, so artifacts never leak into an ephemeral checkout. A design-quality PostToolUse hook (`gdd-design-quality-check.js`) runs a free regex pass on every `.tsx`/`.vue`/`.svelte`/`.astro` write and warns on eight default-AI-aesthetic tells (gradient spam, generic CTAs, centered-everything, font-inter defaults, purple/violet defaults, glassmorphism spam, isometric fallbacks, decorative motion), catalogued in `reference/visual-tells.md`. And a reviewer confidence gate adds a `confidence: 0.0-1.0` field plus a 4-question Pre-Report Gate to every audit finding: HIGH and CRITICAL findings need at least 0.8 confidence and cited proof, low-confidence findings stay tentative and never reach `design-fixer`. The hook is WARN-only and there is **no new runtime dependency**.
+
+**Authoring contract v3 (v1.50.0).** Two additions. A verb-based anti-slop rubric (`reference/anti-slop-rubric.md`) scores five orthogonal axes (Directness, Distinctness, Hierarchy, Authenticity, Density); a sum below 35/50 routes a finding to the debt crawler as `aesthetic-slop`. It rides as a lens-tag on the existing 7-pillar audit, so it catches "generically AI-default" where the pillars catch "wrong". And a machine-parseable skill-composition manifest: optional `composes_with` / `next_skills` frontmatter, a DAG validator (`validate:composition-graph` fails on cycles or dangling refs), and an auto-generated `reference/skill-graph.md`. Skill descriptions move to a multi-paragraph v3 form (`<what>. Use when <triggers>. Activates for requests involving <kw>.`) with both forms accepted during a transition window, a boilerplate-cohort lint, and a `/gdd:new-skill` scaffolder. **No new runtime dependency.**
+
 Verify with:
 
 ```

package/SKILL.md

@@ -2,7 +2,7 @@
 name: get-design-done
 short_name: gdd
 description: "Master design pipeline for Claude Code. 5-stage workflow: Brief → Explore → Plan → Design → Verify. Run 'brief' first in any new project to capture the design problem, then 'explore' to inventory the codebase and interview for context. Invoke without arguments for status and auto-routing."
-argument-hint: "[brief|explore|plan|design|verify|handoff|map|next|help|status|style|darkmode|live|compare|figma-write|graphify|discuss|list-assumptions|progress|health|todo|stats|note|plant-seed|add-backlog|review-backlog|scan|discover|settings|update|reapply-patches|audit|pause|resume|new-cycle|debug|quick|new-project|complete-cycle|fast|do|ship|undo|pr-branch|sketch|sketch-wrap-up|spike|spike-wrap-up|reflect|apply-reflections|analyze-dependencies|extract-learnings|skill-manifest|pin|unpin|list-pins|warm-cache|optimize|cache-manager|watch-authorities|check-update|benchmark|recall|timeline|continue|zoom-out]"
+argument-hint: "[brief|explore|plan|design|verify|handoff|map|next|help|status|style|darkmode|live|compare|figma-write|graphify|discuss|list-assumptions|progress|health|todo|stats|note|plant-seed|add-backlog|review-backlog|scan|discover|settings|update|reapply-patches|audit|pause|resume|new-cycle|debug|quick|new-project|complete-cycle|fast|do|ship|undo|pr-branch|sketch|sketch-wrap-up|spike|spike-wrap-up|reflect|apply-reflections|analyze-dependencies|extract-learnings|skill-manifest|pin|unpin|list-pins|new-skill|warm-cache|optimize|cache-manager|watch-authorities|check-update|benchmark|recall|timeline|continue|zoom-out]"
 user-invocable: true
 ---
 
@@ -93,6 +93,7 @@ Each stage produces artifacts in `.design/` inside the current project.
 | `pin <skill>` | `get-design-done:gdd-pin` | Phase 46 - write standalone shortcut aliases for a gdd skill across every installed harness dir (so `/audit` resolves alongside `/gdd:audit`); metadata comes from the skills.json catalogue |
 | `unpin <skill>` | `get-design-done:gdd-unpin` | Phase 46 - remove pinned aliases for a skill (only files carrying the gdd-pinned-skill marker) |
 | `list-pins` | `get-design-done:gdd-list-pins` | Phase 46 - show pinned aliases per harness with their source skill and last-pinned timestamp |
+| `new-skill <name>` | `get-design-done:gdd-new-skill` | Phase 50 - interactive scaffolder for a new Phase 28.5 + v3-compliant skill (multi-paragraph description, lifecycle stage, optional composes_with); writes source/skills/<name>/SKILL.md |
 | `quality-gate` | `get-design-done:quality-gate` | Phase 25 - parallel lint/type/test/visual command runner; classifies failures via quality-gate-runner agent |
 | `turn-closeout` | `get-design-done:turn-closeout` | Phase 25 - Stop-hook mirror skill; finalizes per-turn STATE blocks and emits closeout events |
 | `bandit-status` | `get-design-done:bandit-status` | Phase 27.5 - read-only diagnostic surface for the bandit posterior; per-(agent, bin, delegate, tier) snapshots (alpha, beta, mean, stddev, count, last-used). Use `/gdd:bandit-reset` to mutate. |

package/agents/design-auditor.md

@@ -47,6 +47,9 @@ Minimum expected files:
 - `.design/tasks/` - what was actually done (glob all task files)
 - **Domain-index navigation (Phase 45):** the 7 entry-points `reference/{typography,color,spatial,motion,interaction,responsive,ux-writing}.md` index every fragment below. For a pillar, load the relevant domain index first, then drill into the specific fragments it lists only as the pillar needs them - this is the cheap navigation layer over the detailed fragments.
 - `reference/audit-scoring.md` - existing 7-category scoring rubric (understand, do not duplicate)
+- `reference/anti-slop-rubric.md` - the five verb axes scored after the pillar pass (see Anti-slop scoring section)
+- `reference/visual-tells.md` - default-AI tell catalog; each tell names the verb axis it degrades
+- `reference/reviewer-confidence-gate.md` - Pre-Report Gate, the `confidence` field, and the routing rule applied to every finding
 - `reference/brand-voice.md` - voice axes, archetype library, and tone-by-context table (use when auditing Pillar 1: Copy)
 - `reference/gestalt.md` - 8 Gestalt principles with scoring rubrics (use when auditing Pillar 2: Visual Hierarchy)
 - `reference/visual-hierarchy-layout.md` - Z-order, whitespace, grids, and reading-order patterns (use when auditing Pillar 2: Visual Hierarchy)
@@ -321,6 +324,24 @@ grep -rEn "w-4 h-4|w-5 h-5|w-6 h-6" src/ --include="*.tsx" --include="*.jsx" 2>/
 
 ---
 
+## Anti-slop scoring
+
+After the 7-pillar pass, apply the verb-axis lens from `reference/anti-slop-rubric.md`. This is **orthogonal** and **v2-compatible additive** under `scoring_contract_version: v2` (see the contract note above): it adds NO eighth scored pillar, leaves the reserved Pillar 8 unscored, and changes neither the /28 total here nor the weighted 0-100 score in `reference/audit-scoring.md`.
+
+Score five axes 1-10 each per the rubric (do not inline the scales or examples; the rubric is the source of truth):
+
+- **Directness** - does copy and CTA name the specific product, verb, and outcome?
+- **Distinctness** - is the palette and type a recorded brand decision, not the default reach?
+- **Hierarchy** - one focal point and an obvious reading order, not flat competing weight?
+- **Authenticity** - real product and shipped copy, not stock scenes, lorem, or badge spam?
+- **Density** - density chosen for the content, not inflated to fill space?
+
+Emit the result as a lens-tag on the relevant finding: `verb_axes_scored: {directness, distinctness, hierarchy, authenticity, density}`. Record which `reference/visual-tells.md` categories matched as evidence. The lens-tag is registered in `reference/audit-scoring.md` under Lens-Tags (Orthogonal).
+
+When `directness + distinctness + hierarchy + authenticity + density < 35` (of 50), the work reads as generically AI-default even if pillars pass: flag an `aesthetic-slop` debt item for `agents/design-debt-crawler.md` (per `reference/debt-categories.md`) and note it in the Priority Fix List with the per-axis scores. A sum at or above 35 is not a pillar pass; it only means no aesthetic-slop routing.
+
+---
+
 ## Domain checklist addendum (Tier-3)
 
 If DESIGN-CONTEXT.md carries a `<domain>` line (set by `design-context-builder` Step 0F - `finance` / `healthcare` / `gaming` / `civic`), **also** run that pack's `## Audit checklist` from `reference/domains/<domain>-patterns.md` and fold its findings into the relevant pillar:
@@ -357,6 +378,10 @@ For each of the 7 pillars:
 3. Assign a score (1–4) with specific evidence
 4. Identify the top gap for this pillar (one concrete, actionable finding)
 
+### Step 3.5: Pre-Report Gate + confidence
+
+Before writing any finding into the Priority Fix List or Detailed Findings, run the four-question Pre-Report Gate from `reference/reviewer-confidence-gate.md`: (a) can you cite `file:line`, (b) can you state the failure mode in one sentence, (c) did you read context beyond the matched line, (d) is the implied severity defensible? Stamp every priority-fix finding with a `confidence` value (`0.0-1.0`): `>= 0.8` when all four pass, `0.5-0.8` for partial evidence, `< 0.5` for an unconfirmed pattern match (common for the code-only Visual Hierarchy and Color pillars, where runtime cannot be seen). Move every `< 0.5` finding into a `## Tentative` section instead of the Priority Fix List, so a low-confidence guess never escalates to remediation. Confidence is independent of the 1-4 pillar scores and does not change them.
+
 ### Step 4: Write DESIGN-AUDIT.md
 
 Write `.design/DESIGN-AUDIT.md` using the output format below.
@@ -414,11 +439,19 @@ supplement_note: "Supplements 7-category 0-10 system in reference/audit-scoring.
 
 ## Priority Fix List
 
-Listed by impact. Top 3 fixes the verifier should weight heavily.
+Listed by impact. Top 3 fixes the verifier should weight heavily. Each finding carries a `confidence` value (see `reference/reviewer-confidence-gate.md`); findings below `0.5` go in `## Tentative`, not here.
+
+1. **[Pillar N: specific issue]** (confidence: [0.0-1.0]) [user impact] [concrete fix with file reference]
+2. **[Pillar N: specific issue]** (confidence: [0.0-1.0]) [user impact] [concrete fix with file reference]
+3. **[Pillar N: specific issue]** (confidence: [0.0-1.0]) [user impact] [concrete fix with file reference]
+
+---
+
+## Tentative
+
+Low-confidence findings (`confidence < 0.5`, per `reference/reviewer-confidence-gate.md`): pattern matches not confirmed by reading context, or runtime-only concerns the code-only pass cannot verify. Surfaced for human review; never auto-escalated to design-fixer.
 
-1. **[Pillar N — specific issue]** — [user impact] — [concrete fix with file reference]
-2. **[Pillar N — specific issue]** — [user impact] — [concrete fix with file reference]
-3. **[Pillar N — specific issue]** — [user impact] — [concrete fix with file reference]
+- [Pillar N: finding] (confidence: [N], unconfirmed because [reason])
 
 ---
 

package/agents/design-context-builder.md

@@ -561,6 +561,8 @@ Iterate until the user confirms. Then write the artifact.
 
 ## Output: .design/DESIGN-CONTEXT.md
 
+Before writing any `.design/` artifact, resolve the main repo root via `scripts/lib/worktree-resolve.cjs` (`resolveDesignRoot`) so a worktree run writes to the main checkout and does not leak.
+
 Create `.design/` directory if needed. Write `.design/DESIGN-CONTEXT.md`:
 
 ```markdown

package/agents/design-debt-crawler.md

@@ -60,6 +60,8 @@ listed file before acting. Minimum expected files:
 
 - @reference/debt-categories.md
 - @reference/anti-patterns.md
+- @reference/anti-slop-rubric.md
+- @reference/reviewer-confidence-gate.md
 
 `reference/debt-categories.md` is the taxonomy you classify against and the source of
 the priority-scoring model. `reference/anti-patterns.md` is the BAN-NN and SLOP-NN
@@ -157,6 +159,25 @@ grep -rEn "No data|No results|Nothing here|went wrong|error occurred" src/ \
 Flag meaningful images without `alt`, icon-only controls without an accessible name,
 placeholder used as the only label, and generic empty or error copy.
 
+**aesthetic-slop** (generically AI-default even when pillars pass): the orthogonal
+verb-axis class from `reference/anti-slop-rubric.md`. `agents/design-auditor.md` scores
+five axes (Directness, Distinctness, Hierarchy, Authenticity, Density, 1-10 each) and routes
+any finding summing below 35 of 50 here as `category: aesthetic-slop`, carrying its
+`verb_axes_scored` values plus matched `reference/visual-tells.md` categories as evidence.
+
+### Step 2.5: Pre-Report Gate + confidence
+
+Before cataloging any finding, run the four-question Pre-Report Gate from
+`reference/reviewer-confidence-gate.md`: (a) can you cite `file:line`, (b) can you state the
+failure mode in one sentence, (c) did you read context beyond the matched line (the token
+definition, the call site), and (d) is the class assignment defensible? Stamp every catalog
+row with a `confidence` value (`0.0-1.0`): `>= 0.8` when all four pass, `0.5-0.8` when evidence
+is partial, `< 0.5` for a pattern match you could not confirm (for example an unresolved
+contrast pair or a literal that may be inside a token definition). Move every `< 0.5` finding
+into a `## Tentative` section instead of the ranked findings table, so a low-confidence guess
+never escalates to remediation. Confidence is independent of priority: a high-priority debt
+item can still be low confidence and belongs in `## Tentative` until confirmed.
+
 ### Step 3: Group and score
 
 Group findings by the seven debt classes. For each finding, assign the three priority
@@ -212,17 +233,27 @@ note: "Project-scoped retroactive debt catalog. Does NOT read STATE.md completed
 | density-spacing | N | P |
 | typography-drift | N | P |
 | a11y-text | N | P |
+| aesthetic-slop | N | P |
 
 ---
 
 ## Findings (ranked by priority)
 
-| Priority | Class | Location | Finding | V × E × P | Suggested command |
-|----------|-------|----------|---------|-----------|-------------------|
-| 18 | color-literal | src/Card.tsx:42 | Raw #1a73e8 instead of token | 3×3×2 | `/gdd:fast "replace #1a73e8 with semantic token in Card.tsx"` |
-| 12 | anti-pattern | src/Hero.tsx:8 | BAN-02 gradient text on heading | 3×2×2 | `/gdd:fast "remove BAN-02 gradient text in Hero.tsx"` |
+| Priority | Class | Location | Finding | V × E × P | Confidence | Suggested command |
+|----------|-------|----------|---------|-----------|------------|-------------------|
+| 18 | color-literal | src/Card.tsx:42 | Raw #1a73e8 instead of token | 3×3×2 | 0.9 | `/gdd:fast "replace #1a73e8 with semantic token in Card.tsx"` |
+| 12 | anti-pattern | src/Hero.tsx:8 | BAN-02 gradient text on heading | 3×2×2 | 0.85 | `/gdd:fast "remove BAN-02 gradient text in Hero.tsx"` |
+
+(One row per finding with `confidence >= 0.5`. The Suggested command column always carries a `/gdd:fast "<finding>"` string. Findings below `0.5` go in `## Tentative` below, not in this table.)
+
+---
+
+## Tentative
+
+Findings with `confidence < 0.5` (pattern matches not confirmed by reading context, per
+`reference/reviewer-confidence-gate.md`). Listed for human review; never auto-escalated.
 
-(One row per finding. The Suggested command column always carries a `/gdd:fast "<finding>"` string.)
+- [class] [location]: [finding] (confidence: [N], unconfirmed because [reason])
 
 ---
 

package/agents/design-executor.md

@@ -395,6 +395,8 @@ Apply these rules automatically during execution. Track all deviations in the ta
 
 ## Task Output - .design/tasks/task-NN.md
 
+Before writing any `.design/` artifact, resolve the main repo root via `scripts/lib/worktree-resolve.cjs` (`resolveDesignRoot`) so a worktree run writes to the main checkout and does not leak.
+
 After completing the task's implementation work, write `.design/tasks/task-NN.md` (where NN = task_id from prompt context). Create `.design/tasks/` directory first if it does not exist.
 
 Format (locked - do not alter structure):

package/agents/design-fixer.md

@@ -48,6 +48,8 @@ The orchestrating stage supplies a `<required_reading>` block in the prompt. Rea
 
 **Invariant:** read all listed files FIRST, before making any changes.
 
+**Worktree-root invariant:** before writing any `.design/` artifact (for example a `<blocker>` entry to `.design/STATE.md`), resolve the main repo root via `scripts/lib/worktree-resolve.cjs` so a worktree run writes to the canonical `.design/` and does not leak artifacts into the worktree checkout.
+
 ---
 
 ## Prompt Context Fields
@@ -88,7 +90,8 @@ Parse every entry in that section. The `G-NN` identifier, severity classificatio
 4. Filter by severity based on `auto_mode`:
    - Always include: `BLOCKER`, `MAJOR`
    - Include only if `auto_mode=true`: `MINOR`, `COSMETIC`
-5. Build an ordered list: BLOCKER first, then MAJOR, then (if included) MINOR, COSMETIC.
+5. **Confidence routing filter (Phase 49, see `reference/reviewer-confidence-gate.md`).** Drop any gap that sits under a `## Tentative` heading: those never reach you. Then drop any `BLOCKER` or `MAJOR` gap whose `confidence` field is below `0.8` and route it to user review instead of auto-fix, since a high-severity gap without strong evidence is exactly the inflated-severity case the gate exists to catch. A gap missing its `confidence` field is treated as below the floor. The shared decision lives in `scripts/lib/confidence-route.cjs` (`route({ severity, confidence, tentative })` returns `'fix' | 'user-review' | 'drop'`); fix only the gaps it routes to `'fix'`.
+6. Build an ordered list: BLOCKER first, then MAJOR, then (if included) MINOR, COSMETIC.
 
 If no in-scope gaps are found (e.g., verifier found only MINOR gaps and `auto_mode=false`), emit `## FIX COMPLETE` immediately with "No in-scope gaps to fix."
 

package/agents/design-planner.md

@@ -227,6 +227,8 @@ Before finalizing task list:
 
 ## Output Format
 
+Before writing any `.design/` artifact, resolve the main repo root via `scripts/lib/worktree-resolve.cjs` (`resolveDesignRoot`) so a worktree run writes to the main checkout and does not leak.
+
 Write `.design/DESIGN-PLAN.md` with this exact structure:
 
 ```markdown

package/agents/design-reflector.md

@@ -62,6 +62,8 @@ Minimum expected inputs (skip gracefully if absent, note what's missing):
 
 ## Output
 
+Before writing any `.design/` artifact, resolve the main repo root via `scripts/lib/worktree-resolve.cjs` (`resolveDesignRoot`) so a worktree run writes to the main checkout and does not leak.
+
 Write `.design/reflections/<cycle-slug>.md`. If `--dry-run` is set in the spawning prompt, print proposals to stdout only - do not write the file.
 
 If the capability-gap pattern scan emitted any events during this run, include a `## Capability gaps emitted` heading listing each `event_id` with the source signal kind (`intel` | `posterior` | `trajectory`) and the `suggested_kind` (`agent` | `skill`) per event. Plan 29-03 reads these events from `.design/gep/events.jsonl` to cluster recurring `capability_gap` events for `/gdd:apply-reflections`.

package/agents/design-research-synthesizer.md

@@ -161,6 +161,8 @@ Read .design/STATE.md
 
 ## Output
 
+Before writing any `.design/` artifact, resolve the main repo root via `scripts/lib/worktree-resolve.cjs` (`resolveDesignRoot`) so a worktree run writes to the main checkout and does not leak.
+
 Single file: `.design/DESIGN-CONTEXT.md`.
 
 ## Record

package/agents/design-verifier.md

@@ -33,6 +33,7 @@ The orchestrating stage supplies a `<required_reading>` block in the prompt. Rea
 - `.design/DESIGN-CONTEXT.md` - goals, must-haves, brand direction, references
 - `.design/tasks/` - what was actually done (glob all task files)
 - `reference/audit-scoring.md` - scoring rubric for category weights
+- `reference/reviewer-confidence-gate.md` - Pre-Report Gate, the `confidence` field, and the gap routing rule
 - `reference/heuristics.md` - NNG heuristics H-01..H-10 scoring guide
 - `reference/review-format.md` - visual UAT presentation format
 - `reference/accessibility.md` - WCAG checklist for accessibility scoring
@@ -40,6 +41,8 @@ The orchestrating stage supplies a `<required_reading>` block in the prompt. Rea
 - `connections/chromatic.md` - Chromatic CLI connection spec (probe, baseline management, fallback)
 - `connections/storybook.md` - Storybook HTTP probe and a11y integration details
 
+**Worktree-root invariant:** before writing `.design/DESIGN-VERIFICATION.md` (or any `.design/` artifact), resolve the main repo root via `scripts/lib/worktree-resolve.cjs` so a worktree run writes to the canonical `.design/` and does not leak artifacts into the worktree checkout.
+
 ## Prompt Context Fields
 
 The stage embeds these fields in its prompt:
@@ -440,6 +443,8 @@ Classify each gap:
 - `MINOR` - noticeable issue; fix if time allows
 - `COSMETIC` - polish only; defer to later
 
+**Pre-Report Gate (Phase 49, see `reference/reviewer-confidence-gate.md`).** Before emitting each gap, answer the four questions: (a) can you cite `file:line`, (b) can you state the failure mode in one sentence, (c) did you read context beyond the modified file, (d) is the severity defensible? Stamp every gap with a `confidence` field (`0.0-1.0`): `>= 0.8` when all four pass, `0.5-0.8` when evidence is partial, `< 0.5` for an unconfirmed hunch. A BLOCKER or MAJOR requires `confidence >= 0.8` plus a `file:line` citation plus a one-sentence failure mode; below that, lower the severity or move it to `## Tentative`. Confidence is independent of severity. Move every `< 0.5` gap into a `## Tentative` section so it is surfaced but never reaches `design-fixer`.
+
 For each gap, emit an entry in the locked gap format:
 
 ```
@@ -452,6 +457,7 @@ For each gap, emit an entry in the locked gap format:
 - Actual: [what is true]
 - Location: [file:line or UI element]
 - Suggested fix: [one-line hint]
+- confidence: [0.0-1.0]
 ```
 
 Order gaps: BLOCKER first, then MAJOR, MINOR, COSMETIC. Number sequentially (G-01, G-02, ...).
@@ -464,21 +470,7 @@ If zero gaps found: skip this section entirely - do NOT emit `## GAPS FOUND`.
 
 **Skip if `chromatic` is `not_configured` or `unavailable` in STATE.md `<connections>`.**
 
-If `.design/chromatic-results.json` exists:
-1. Read .design/chromatic-results.json
-2. Check if this is a first run (all entries have status: "new"):
-   → First run: emit "Baseline established - no regressions detected (first run creates baseline)."
-3. For subsequent runs, narrate changes:
-   For each story entry in results:
-     - status "unchanged" → PASS <StoryTitle>:<StoryName>
-     - status "changed" → CHANGED <StoryTitle>:<StoryName> (visual change detected - review on chromatic.com)
-     - status "new" → NEW <StoryTitle>:<StoryName> (first snapshot - not a regression)
-     - status "error" → ERROR <StoryTitle>:<StoryName> - investigate
-4. Emit summary: "Total: N stories. X unchanged. Y changed. Z new. W errors."
-5. If Y > 0 (changed stories): flag as "VISUAL REGRESSION CANDIDATES - review required on chromatic.com before merging"
-6. Append narration to DESIGN-VERIFICATION.md ## Visual Regression section (create section if absent)
-
-If .design/chromatic-results.json does not exist: skip; emit no note.
+If `.design/chromatic-results.json` exists, read it and narrate. First run (all entries `status: "new"`): emit "Baseline established - no regressions detected (first run creates baseline)." Subsequent runs, per story entry: `unchanged` → PASS, `changed` → CHANGED (review on chromatic.com), `new` → NEW (first snapshot, not a regression), `error` → ERROR (investigate). Emit summary "Total: N stories. X unchanged. Y changed. Z new. W errors." If any changed (Y > 0), flag "VISUAL REGRESSION CANDIDATES - review required on chromatic.com before merging". Append the narration to the DESIGN-VERIFICATION.md `## Visual Regression` section (create it if absent). If the file does not exist: skip; emit no note.
 
 ---
 

package/dist/claude-code/.claude/skills/audit/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: gdd-audit
-description: "Run a design audit by spawning design-auditor, design-integration-checker, and (optionally) design-verifier + design-reflector agents, then printing a consolidated 6-pillar score summary. Use when the user wants to score the current design, retroactively verify a completed cycle, or quickly re-check after a fix."
+description: "Run a design audit by spawning design-auditor, design-integration-checker, and (optionally) design-verifier + design-reflector agents, then printing a consolidated 6-pillar score summary. Use when the user wants to score the current design, retroactively verify a completed cycle, or quickly re-check after a fix. Activates for requests involving scoring an existing design, retroactively reviewing quality, or re-checking after a fix."
 argument-hint: "[--retroactive] [--quick] [--no-reflect]"
 tools: Read, Write, Task, Glob, Bash
 ---

package/dist/claude-code/.claude/skills/brief/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: gdd-brief
-description: "Stage 1 of 5 design intake that captures problem statement, audience, constraints, success metrics, and scope into .design/BRIEF.md, and bootstraps .design/STATE.md if missing. Use when starting a new design cycle and before /gdd:explore."
+description: "Stage 1 of 5 design intake that captures problem statement, audience, constraints, success metrics, and scope into .design/BRIEF.md, and bootstraps .design/STATE.md if missing. Use when starting a new design cycle and before /gdd:explore. Activates for requests involving capturing a problem statement, defining audience and constraints, or starting a new design brief."
 argument-hint: "[--re-brief to redo intake on existing project]"
 tools: Read, Write, AskUserQuestion, mcp__gdd_state__frontmatter_update, mcp__gdd_state__set_status, mcp__gdd_state__update_progress, mcp__gdd_state__get
 ---

package/dist/claude-code/.claude/skills/compare/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: gdd-compare
-description: "Compute the delta between the `DESIGN.md` baseline (from scan) and the `DESIGN-VERIFICATION.md` result (from verify), reporting per-category score delta, anti-pattern delta (resolved vs new), must-have pass/fail change, and design drift (regressions without covering tasks in `DESIGN-PLAN.md`). Use after `verify` to measure whether a design pipeline cycle actually improved the design. Writes `.design/COMPARE-REPORT.md`."
+description: "Compute the delta between the `DESIGN.md` baseline (from scan) and the `DESIGN-VERIFICATION.md` result (from verify), reporting per-category score delta, anti-pattern delta (resolved vs new), must-have pass/fail change, and design drift (regressions without covering tasks in `DESIGN-PLAN.md`). Use after `verify` to measure whether a design pipeline cycle actually improved the design. Writes `.design/COMPARE-REPORT.md`. Activates for requests involving diffing a design baseline against verification output, or a before-after design delta."
 argument-hint: ""
 user-invocable: true
 ---

package/dist/claude-code/.claude/skills/connections/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: gdd-connections
-description: "Interactive onboarding wizard for the 33 external integrations the pipeline supports - probes all (`figma`, `refero`, `preview`, `storybook`, `chromatic`, `graphify`, `pinterest`, `claude-design`, `paper-design`, `pencil-dev`, `21st-dev`, `magic-patterns`, `lazyweb`, `mobbin`, `slack`, `discord`, `linear`, `jira`, `notion`, `lottie`, `rive`, `framer`, `penpot`, `webflow`, `v0-dev`, `plasmic`, `builder-io`, `launchdarkly`, `statsig`, `growthbook`, `usertesting`, `maze`, `hotjar`), recommends based on project type, walks the user through setup (auto-run MCP install or copy-command fallback), writes results to `STATE.md <connections>`. Use after `/gdd:new-project` or whenever the user wants to add, inspect, or skip a connection. Re-runnable anytime."
+description: "Interactive onboarding wizard for the 33 external integrations the pipeline supports - probes all (`figma`, `refero`, `preview`, `storybook`, `chromatic`, `graphify`, `pinterest`, `claude-design`, `paper-design`, `pencil-dev`, `21st-dev`, `magic-patterns`, `lazyweb`, `mobbin`, `slack`, `discord`, `linear`, `jira`, `notion`, `lottie`, `rive`, `framer`, `penpot`, `webflow`, `v0-dev`, `plasmic`, `builder-io`, `launchdarkly`, `statsig`, `growthbook`, `usertesting`, `maze`, `hotjar`), recommends based on project type, walks the user through setup (auto-run MCP install or copy-command fallback), writes results to `STATE.md <connections>`. Use after `/gdd:new-project` or whenever the user wants to add, inspect, or skip a connection. Re-runnable anytime. Activates for requests involving setting up external integrations, probing Figma or preview or storybook, or onboarding tools."
 argument-hint: "[list | <connection-name> | --auto]"
 user-invocable: true
 tools: Read, Write, Bash, Glob, Grep, AskUserQuestion, ToolSearch

package/dist/claude-code/.claude/skills/darkmode/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: gdd-darkmode
-description: "Audit a project's dark mode implementation - detects architecture (CSS custom props, Tailwind `dark:` prefix, or JS class toggle), runs architecture-specific contrast / token-override / anti-pattern / meta-property checks, and writes a prioritized fix list to `.design/DARKMODE-AUDIT.md`. Use when the user wants to verify dark mode quality without re-running the full design pipeline. Read-only - no score writeback to `DESIGN.md`."
+description: "Audit a project's dark mode implementation - detects architecture (CSS custom props, Tailwind `dark:` prefix, or JS class toggle), runs architecture-specific contrast / token-override / anti-pattern / meta-property checks, and writes a prioritized fix list to `.design/DARKMODE-AUDIT.md`. Use when the user wants to verify dark mode quality without re-running the full design pipeline. Read-only - no score writeback to `DESIGN.md`. Activates for requests involving auditing dark mode, checking dark-theme contrast, or dark-mode anti-patterns."
 argument-hint: ""
 user-invocable: true
 ---

package/dist/claude-code/.claude/skills/design/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: design
-description: "Stage 4 of 5 orchestrator that reads DESIGN-PLAN.md, partitions tasks by wave + parallel-safe flag, and spawns design-executor agents with the appropriate isolation (worktree for parallel batches, in-place for sequential tail). Use when DESIGN-PLAN.md is approved and ready for implementation."
+description: "Stage 4 of 5 orchestrator that reads DESIGN-PLAN.md, partitions tasks by wave + parallel-safe flag, and spawns design-executor agents with the appropriate isolation (worktree for parallel batches, in-place for sequential tail). Use when DESIGN-PLAN.md is approved and ready for implementation. Activates for requests involving implementing UI, building components, or turning a plan into working interface code."
 argument-hint: "[--auto] [--parallel] [--variants N]"
 user-invocable: true
 tools: Read, Write, Bash, Grep, Glob, Task, AskUserQuestion, mcp__gdd_state__get, mcp__gdd_state__transition_stage, mcp__gdd_state__update_progress, mcp__gdd_state__set_status, mcp__gdd_state__add_blocker, mcp__gdd_state__resolve_blocker, mcp__gdd_state__checkpoint

package/dist/claude-code/.claude/skills/discover/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: discover
-description: "Stage 1.5 of 4 orchestrator that probes Figma / Refero / Pinterest connections, spawns design-context-builder (auto-detect + interview) and (via lazy gate) design-context-checker (6-dimension validator), producing .design/DESIGN-CONTEXT.md. Use after /gdd:scan when a fast-path context build is wanted instead of the full /gdd:explore."
+description: "Stage 1.5 of 4 orchestrator that probes Figma / Refero / Pinterest connections, spawns design-context-builder (auto-detect + interview) and (via lazy gate) design-context-checker (6-dimension validator), producing .design/DESIGN-CONTEXT.md. Use after /gdd:scan when a fast-path context build is wanted instead of the full /gdd:explore. Activates for requests involving detecting an existing design system, inventorying tokens and components, or onboarding a brownfield repo."
 argument-hint: "[--auto]"
 user-invocable: true
 ---

package/dist/claude-code/.claude/skills/do/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: gdd-do
-description: "Natural-language design task router. Parses your intent, maps to the right gdd command(s), confirms before executing."
+description: "Natural-language design task router. Parses your intent, maps to the right gdd command(s), confirms before executing. Activates for requests involving a natural-language design request, routing intent to the right command, or not knowing which skill to use."
 argument-hint: "<natural language description>"
 tools: Read, Write, AskUserQuestion
 ---

package/dist/claude-code/.claude/skills/explore/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: gdd-explore
-description: "Stage 2 of 5 - unified exploration merging inventory grep + design interview. Probes 6 connections, scans the codebase, conducts the AskUserQuestion interview, and writes .design/DESIGN.md + DESIGN-DEBT.md + DESIGN-CONTEXT.md. Use after /gdd:brief to map the existing system and lock decisions before planning."
+description: "Stage 2 of 5 - unified exploration merging inventory grep + design interview. Probes 6 connections, scans the codebase, conducts the AskUserQuestion interview, and writes .design/DESIGN.md + DESIGN-DEBT.md + DESIGN-CONTEXT.md. Use after /gdd:brief to map the existing system and lock decisions before planning. Activates for requests involving researching design direction, gathering references, or exploring visual options."
 argument-hint: "[--skip-interview] [--skip-scan]"
 tools: Read, Write, Bash, Grep, Glob, Task, AskUserQuestion, mcp__gdd_state__get, mcp__gdd_state__transition_stage, mcp__gdd_state__probe_connections, mcp__gdd_state__update_progress, mcp__gdd_state__set_status, mcp__gdd_state__add_blocker, mcp__gdd_state__checkpoint, mcp__gdd_state__add_decision
 ---

package/dist/claude-code/.claude/skills/fast/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: gdd-fast
-description: "Trivial inline design task. No subagents, no planning documents, no pipeline stages. Just do the thing described."
+description: "Trivial inline design task. No subagents, no planning documents, no pipeline stages. Just do the thing described. Activates for requests involving a single quick design fix, a one-shot change, or a fast targeted edit."
 argument-hint: "<task description>"
 tools: Read, Write, Edit, Bash, Grep, Glob
 disable-model-invocation: true

package/dist/claude-code/.claude/skills/health/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: gdd-health
-description: "Reports .design/ artifact health - staleness, missing files, token drift, broken state transitions."
+description: "Reports .design/ artifact health - staleness, missing files, token drift, broken state transitions. Activates for requests involving checking .design artifact health, staleness, token drift, or broken state transitions."
 tools: Read, Bash, Glob, Grep, mcp__gdd_state__get
 disable-model-invocation: true
 ---
@@ -90,7 +90,7 @@ After the health table, surface the Phase 28.5 skill-authoring contract drift si
 - `Skill-length: <total> total | <clean> clean | <warnings> warn (>=100) | <blockers> block (>=250)`
 - If blockers > 0: list each blocker as a row `- <name> (<lines> lines)`. Else: print `All skills within contract.`
 
-Thresholds: warn >=100, block >=250 (D-01). Strict description-format off by default (D-02). See `./health-skill-length-report.md` for the JSON shape and threshold rationale.
+Thresholds: warn >=100, block >=250 (D-01). Strict description-format off by default (D-02). Then add two compact Phase 50 lines from `scripts/lib/manifest/skills.json`: `Skills: <n>/<total> in v3 description form` (descriptions matching `/Activates for requests involving/i`) and `Composition: <edges> edges | <cycles> cycles` (`composes_with`/`next_skills` fan-out; cycles via `scripts/validate-composition-graph.cjs` when present, else `0`). See `./health-skill-length-report.md` for the JSON shape and threshold rationale.
 
 ## Do Not
 

package/dist/claude-code/.claude/skills/live/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: gdd-live
-description: "Live in-browser design mode. The user picks a DOM element on a running dev server (via the Claude Preview MCP), the agent generates N design variants in one batch, they hot-swap in place through HMR or preview_eval using a data-gdd-variant marker, the user accepts or discards, and the whole pick-generate-accept loop persists to .design/live-sessions so it survives a crash or resume. Use when the user wants to iterate on the look of a live component against a real running server, asks to try variants on a page, or runs the live command with a url; falls back to a screenshot-only degraded mode on harnesses without MCP support."
+description: "Live in-browser design mode. The user picks a DOM element on a running dev server (via the Claude Preview MCP), the agent generates N design variants in one batch, they hot-swap in place through HMR or preview_eval using a data-gdd-variant marker, the user accepts or discards, and the whole pick-generate-accept loop persists to .design/live-sessions so it survives a crash or resume. Use when the user wants to iterate on the look of a live component against a real running server, asks to try variants on a page, or runs the live command with a url; falls back to a screenshot-only degraded mode on harnesses without MCP support. Activates for requests involving in-browser design iteration, picking an element on a dev server, or generating variants with hot-swap."
 argument-hint: "[--variants N] [--resume <session-id>] [url]"
 tools: Read, Write, Edit, Bash, Glob, Grep, Task
 user-invocable: true