@hegemonart/get-design-done 1.57.1 → 1.57.3

package/.claude-plugin/marketplace.json

@@ -4,15 +4,15 @@
     "name": "hegemonart"
   },
   "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": "1.57.1"
+    "description": "Get Design Done — 5-stage agent-orchestrated design pipeline (Brief → Explore → Plan → Design → Verify) for AI coding agents. 61 agents, 94 skills, 42 connection integrations, two MCP servers, opt-in SQLite state backbone, bidirectional Figma write-back, and a reflector-driven self-improvement loop. Cross-runtime install for Claude Code, Codex, Cursor, OpenCode, Gemini, and more.",
+    "version": "1.57.3"
   },
   "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": "1.57.1",
+      "description": "Agent-orchestrated 5-stage design pipeline (Brief → Explore → Plan → Design → Verify) for AI coding agents. 61 specialized agents, 94 skills, 42 connection integrations (Figma, Refero, Preview, Storybook, Chromatic, Graphify, Linear, Jira, Notion, …), bidirectional Figma write-back, queryable intel store, opt-in SQLite state backbone, and a reflector-driven self-improvement loop. Two MCP servers (gdd-state for typed STATE mutators, gdd-mcp for 13 read-only project-priming tools), tier-aware routing with cost telemetry, and defense-in-depth hooks (protected paths, MCP circuit breaker, injection scanner, budget enforcer). Cross-runtime install for Claude Code, Codex, Cursor, OpenCode, Gemini, Copilot, and more.",
+      "version": "1.57.3",
       "author": {
         "name": "hegemonart"
       },
@@ -21,63 +21,48 @@
       "license": "MIT",
       "category": "design",
       "keywords": [
+        "claude",
+        "claude-code",
+        "claude-code-plugin",
+        "plugin",
+        "mcp",
+        "mcp-server",
+        "agent-sdk",
+        "parallel-agents",
         "design",
+        "design-system",
+        "design-system-sync",
         "ui",
         "ux",
         "frontend",
         "pipeline",
         "orchestration",
-        "skill",
-        "design-system",
+        "figma",
+        "figma-write",
         "accessibility",
         "wcag",
-        "nng",
         "typography",
         "motion",
         "anti-patterns",
         "audit",
-        "visual-regression",
         "storybook",
         "graphify",
-        "playwright",
-        "figma-write",
-        "handoff",
-        "claude-design",
-        "pinterest",
-        "bidirectional",
         "knowledge-graph",
         "intel-store",
-        "tested",
-        "ci",
-        "cicd",
-        "release-automation",
-        "gitleaks",
-        "shellcheck",
-        "safety-hardening",
-        "protected-paths",
-        "decision-injector",
-        "reference-registry",
-        "mcp-circuit-breaker",
-        "schema-validation",
-        "cost-optimization",
-        "cache-aware",
-        "budget",
+        "self-improvement",
+        "reflection",
+        "anti-slop",
+        "confidence-gate",
+        "skill-composition",
+        "skill-graph",
+        "worktree-safe",
         "headless",
         "cli",
         "codex",
+        "cursor",
         "gemini",
-        "mcp",
-        "parallel-agents",
-        "agent-sdk",
-        "figma",
-        "extractor",
-        "design-system-sync",
-        "swift",
-        "compose",
-        "flutter",
-        "email",
-        "print",
-        "pdf"
+        "tested",
+        "ci"
       ]
     }
   ]

package/.claude-plugin/plugin.json

@@ -1,8 +1,8 @@
 {
   "name": "get-design-done",
   "short_name": "gdd",
-  "version": "1.57.1",
-  "description": "Agent-orchestrated 5-stage design pipeline: Brief → Explore → Plan → Design → Verify. 59 specialized agents, 88 skills, 41 connection integrations (Figma, Refero, Preview, Storybook, Chromatic, Graphify, Slack, Linear, Jira, Notion, and more), 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).",
+  "version": "1.57.3",
+  "description": "Agent-orchestrated 5-stage design pipeline (Brief → Explore → Plan → Design → Verify) for AI coding agents. 61 specialized agents, 94 skills, 42 connection integrations (Figma, Refero, Preview, Storybook, Chromatic, Graphify, Linear, Jira, Notion, …), bidirectional Figma write-back, queryable intel store for O(1) design-surface lookups, opt-in SQLite state backbone, and a reflector-driven self-improvement loop. Two MCP servers (`gdd-state` for typed STATE mutators, `gdd-mcp` for 13 read-only project-priming tools), tier-aware agent routing with cost telemetry, defense-in-depth hooks (protected paths, MCP circuit breaker, injection scanner, budget enforcer), and a cross-runtime install layer for Claude Code, Codex, Cursor, OpenCode, Gemini, Copilot, and more.",
   "author": {
     "name": "hegemonart",
     "url": "https://github.com/hegemonart"
@@ -11,73 +11,48 @@
   "repository": "https://github.com/hegemonart/get-design-done",
   "license": "MIT",
   "keywords": [
+    "claude",
+    "claude-code",
+    "claude-code-plugin",
+    "plugin",
+    "mcp",
+    "mcp-server",
+    "agent-sdk",
+    "parallel-agents",
     "design",
+    "design-system",
+    "design-system-sync",
     "ui",
     "ux",
     "frontend",
     "pipeline",
-    "skill",
-    "design-system",
+    "orchestration",
+    "figma",
+    "figma-write",
     "accessibility",
     "wcag",
-    "nng",
     "typography",
     "motion",
     "anti-patterns",
     "audit",
-    "visual-regression",
     "storybook",
     "graphify",
-    "playwright",
-    "figma-write",
-    "handoff",
-    "claude-design",
-    "pinterest",
-    "bidirectional",
     "knowledge-graph",
     "intel-store",
     "self-improvement",
     "reflection",
-    "safety-hardening",
-    "protected-paths",
-    "decision-injector",
-    "reference-registry",
-    "mcp-circuit-breaker",
-    "tested",
-    "ci",
-    "cicd",
-    "release-automation",
-    "gitleaks",
-    "shellcheck",
-    "schema-validation",
-    "cost-optimization",
-    "cache-aware",
-    "budget",
+    "anti-slop",
+    "confidence-gate",
+    "skill-composition",
+    "skill-graph",
+    "worktree-safe",
     "headless",
     "cli",
     "codex",
+    "cursor",
     "gemini",
-    "mcp",
-    "parallel-agents",
-    "agent-sdk",
-    "mcp-server",
-    "context-loading",
-    "cross-session",
-    "figma",
-    "extractor",
-    "design-system-sync",
-    "swift",
-    "compose",
-    "flutter",
-    "email",
-    "print",
-    "pdf",
-    "worktree-safe",
-    "anti-slop",
-    "confidence-gate",
-    "anti-slop-rubric",
-    "skill-composition",
-    "skill-graph"
+    "tested",
+    "ci"
   ],
   "skills": [
     "./skills/"

package/CHANGELOG.md

@@ -4,6 +4,137 @@ All notable changes to get-design-done are documented here. Versions follow [sem
 
 ---
 
+## [1.57.3] - 2026-06-04
+
+### Polish residuals - closes remaining POLISH-PLAN items + dist/ deduplication
+
+Continuation of the v1.57.2 grooming wave. Closes the open POLISH-PLAN items that v1.57.2 deferred, plus a structural cleanup the user noticed during PR review. Additive only; no breaking changes. 5,007/5,007 tests pass.
+
+### Removed
+
+- **`agents/prototype-gate.md`** - orphan agent (no skill dispatched it, no hook fired it). Functionality is absorbed by `sketch-wrap-up` and `spike-wrap-up`.
+- **`skills/scan/` + `skills/discover/`** + their `source/skills/` mirrors. Deprecated aliases of `/gdd:explore` for several releases; the root SKILL.md command table no longer carries them. Counts drop 96 -> 94 skills.
+- **`hooks/run-hook.cmd`** - obsolete after the v1.57.2 `.sh` -> `.cjs` SessionStart hook port (all 4 SessionStart hooks now run via `node`, no Windows-bash wrapper needed).
+- **`scripts/lib/worktree-resolve.cjs#resolvePlanningRoot`** - unused export per the audit. Zero production callers across `scripts/ sdk/ hooks/ agents/ skills/`.
+- **`skills/new-cycle/milestone-completeness-rubric.md`** - plugin-internal release-process rubric that was shipping to users via `skills/`. Moved to `docs/MAINTAINER-NOTES.md` so it stops landing in user `~/.claude/skills/` installs.
+- **6 stale `docs/i18n/README.*.md` translations** (de / fr / it / ja / ko / zh-CN). Frozen at v1.24.0 per the v1.57.2 audit. The English README will be rewritten separately. Removed the multilingual nav line from the main README.
+- **`dist/claude-code/` from `package.json#files` + git tracking** - the directory was a byte-identical duplicate of `skills/` (120 files; Claude Code reads `./skills/` directly via `package.json#skills`). `dist/` now fully gitignored; the on-disk dir is a deterministic build artifact rebuilt by `npm run build:skills` on demand. Saves ~120 duplicate-file entries from every npm tarball (tarball-manifest baseline shrank 1001 -> 879 lines).
+- **`.DS_Store` macOS cruft** swept from `skills/`, `test/`, `dist/` + added `**/.DS_Store` to `.gitignore`.
+
+### Added
+
+- **`scripts/check-codex-plugin-drift.cjs`** + `npm run validate:codex-plugin` + `test/suite/codex-plugin-drift.test.cjs` - new CI gate that asserts the committed `.codex-plugin/plugin.json` and `.cursor-plugin/plugin.json` byte-match the generator output from `scripts/build-distribution-bundles.cjs`. Mirrors the baseline-ratchet pattern of `check-feature-counts.cjs`; supports `--rebaseline` for legitimate generator changes. Closes the "committed vs generated SoT" open question from POLISH-PLAN.md by making the generator authoritative and the committed snapshot a verified mirror.
+- **`source/skills/README.md`** + **`skills/README.md`** - documents `source/skills/` as the canonical home for skill BODY content. `scripts/lib/manifest/skills.json` remains the SoT for universal frontmatter fields (`name`, `description`, `argument-hint`, `tools`, `user-invocable`, `disable-model-invocation`). `skills/` is a byte-stable build artifact (npm distribution path); `dist/<harness>/` is a build-time output for non-Claude harness channels.
+- **`docs/MAINTAINER-NOTES.md`** - relocated home for `milestone-completeness-rubric.md` (moved from `skills/new-cycle/`).
+- **Phase 58 entry in `.planning/ROADMAP.md`** - Composition-Graph Mandatory Rollout. Goal: backfill `composes_with` on the remaining 74 of 96 skills (this release added 13 more, bringing the total from 9 to 22 wired skills). Scope: 6 plans across 3 waves (audit + allowlist; backfill + contract bump + scaffolder; closeout). Target v1.58.0.
+- **`composes_with` edges on 13 additional high-traffic skills** (`scripts/lib/manifest/skills.json`): apply-reflections, brief, compare, complete-cycle, darkmode, debug, discuss, explore, figma-extract, figma-write, live, map, new-cycle, new-project, progress. `reference/skill-graph.md` regenerated (96 -> 94 nodes after scan/discover removal, 34 edges, 0 cycles).
+- **`connections/cursor.md`** got a documented sibling-drop fix (followup from v1.57.2's H6 documentation).
+
+### Changed
+
+- **`source/skills/style/SKILL.md`** - removed user-facing `.planning/STATE.md` reference (was "a pre-roadmap decision recorded in `.planning/STATE.md`" -> now neutral "deliberate namespace decision"). Built artifacts in `skills/` and `dist/claude-code/` propagated.
+- **`reference/model-tiers.md`** - softened the agent-name prefix convention (`gdd-*` = housekeeping; `design-*` = pipeline) into a soft naming hint rather than enforced rule. Added explicit "prefix is not a tier signal" clarifier above the Per-Agent Tier Map. Fixed gdd-intel-updater rationale that mentioned `.planning/intel/` (the agent actually writes `.design/intel/`).
+- **`agents/README.md` Naming Convention** - replaced the implicit "all agents use `design-` prefix" claim with neutral language acknowledging the mix of `design-*` / `gdd-*` / bare prefixes. No enforcement; no expected pattern.
+- **`reference/runtime-models.md`** - the 10 unverified entries (kilo, copilot, cursor, windsurf, antigravity, augment, trae, codebuddy, cline, opencode) reformatted: dropped the `<TODO: confirm at ...>` URL wrapper, kept the plain URL, added explicit `"verified": false` field on provenance. The 4 verified entries (claude, codex, gemini, qwen) get `"verified": true`. Schema (`reference/schemas/runtime-models.schema.json`) gained the optional `verified` boolean field.
+- **`scripts/lib/manifest/skills.json` + `reference/skill-graph.md`** - graph regenerated (now 94 skills, 34 composition edges, 0 cycles).
+- **`.github/workflows/release.yml`** - added `cursor-marketplace` channel to the distribution-bundles build step (was missing from the release CI; the converter existed but wasn't wired into the release run).
+- **Skill count claims** synchronized to filesystem truth across all 5 surfaces (plugin.json + marketplace.json + README.md): 96 -> 94 skills.
+- **`scripts/build-skills.cjs` `--check` mode** - dropped the `dist/claude-code/` drift assertion (the dir is no longer committed; only `skills/` is the canonical built artifact under git).
+- **`test/suite/phase-42-build.test.cjs` 42-build-06** - repurposed from "dist/claude-code/ mirrors skills/" to "dist/claude-code/ is NOT committed" (preserves the gate against accidental re-introduction).
+
+### Test infrastructure
+
+- Forward-propagated `manifests-version.txt` baselines from `1.57.2` -> `1.57.3` across 37 phase fixture dirs.
+- `semver-compare.test.cjs` registers `OFF_CADENCE_VERSIONS.add('1.57.3')` with multi-line rationale comment matching the v1.57.2 pattern.
+- Tarball manifest baseline regenerated via `npm pack --dry-run --json` (1001 -> 879 lines after dist/claude-code/ removal + scan/discover/prototype-gate/milestone-rubric deletes).
+- Skill frontmatter regenerated via `npm run generate:skill-frontmatter` (3 drifted entries on bootstrap-ds, compare, synthesize).
+- 23 test failures from the deletes (count drift, baseline drift, em-dash lint, codex-plugin-drift) all resolved.
+
+---
+
+## [1.57.2] - 2026-06-04
+
+### Polish wave - 24 commits closing the v1.57 audit + 5 new CI gates
+
+A single grooming wave: closes ~80% of the gap between what the plugin claims and what it does, plus structural CI gates that prevent the same drift from coming back. 5,007/5,007 tests pass; all 16 CI checks green. No breaking changes - additive only.
+
+### Fixed (8 ship-blockers)
+
+- **`scripts/injection-patterns.cjs` was excluded from the npm tarball** via `.npmignore`. `hooks/gdd-read-injection-scanner.ts` calls `createRequire()` to load it at runtime, so the scanner was a silent no-op for every shipped install (PostToolUse:Read security check disabled). Now in `package.json#files`; verified via `npm pack --dry-run`.
+- **`gdd-sdk stage audit` errored without hinting at the real top-level subcommand.** The error now suggests "did you mean `gdd-sdk audit`?" - `audit` is a top-level subcommand, not a pipeline stage.
+- **Codex Plugin Generator shipped `longDescription: "<div align=\"center\">"`** (the README's HTML wrapper). The README-first-paragraph scan now skips HTML wrappers, GitHub callouts, nav rows, and badge clusters.
+- **2 hooks (`gdd-sessionstart-recap.js`, `gdd-precompact-snapshot.js`) resolved paths at module load** via `process.cwd()` instead of `payload.cwd` - broken in worktrees. Now thread `payload.cwd` through a `computePaths()` factory.
+- **`hooks/gdd-mcp-circuit-breaker.js` substring-matched `'timeout'` / `'failed'` against the entire stringified MCP response.** False-positives on legitimate successful Figma payloads (e.g. a node literally named "TimeoutBanner" or a summary line "2 of 5 nodes failed to update"). Now uses the structured `isError` / `is_error` envelope as the primary signal and only inspects dedicated error-message fields for timeout-vs-error classification. +4 regression tests.
+- **Windows SessionStart hooks (4 `.sh` scripts) failed without Git Bash on PATH.** Ported `scripts/bootstrap.sh`, `hooks/update-check.sh`, `hooks/first-run-nudge.sh`, `hooks/inject-using-gdd.sh` to Node `.cjs` modules. `hooks/hooks.json` rewired to `node …cjs`. One source of truth, no drift surface.
+- **`hooks/gdd-protected-paths.js` had 4 bypass vectors** in `extractBashTargets()`: chained commands (`rm safe.txt && rm reference/protected.md` extracted only `safe.txt`), multi-arg destructive verbs, `$(…)` subshell substitution, `` `…` `` backtick substitution. Rewrote as a 3-pass walker that recurses into subshells, splits on `&&`/`||`/`;`/`|`, and collects ALL non-flag args per segment. +12 regression tests.
+- **`skills/figma-write/SKILL.md` used invented `<agent>design-figma-writer</agent>` dispatch syntax** that Claude Code does not parse. The entire Figma write-back skill was a silent no-op since it was first authored. Replaced with the canonical `Task("design-figma-writer", "...")` block. Added `test/suite/skill-dispatch-syntax.test.cjs` regression gate that sweeps every SKILL.md.
+
+### Added (5 new CI gates - structural drift prevention)
+
+- **`npm run validate:feature-counts`** (`scripts/check-feature-counts.cjs`): walks the filesystem and asserts every shipped surface's count claims (`plugin.json` / `marketplace.json` / `README.md` / `SKILL.md`) match reality (61 agents / 96 skills / 42 connections / 13 MCP tools).
+- **`npm run validate:registry-tiers`** (`scripts/validate-registry-tiers.cjs`): asserts every `registry.json` entry's `tier` field is one of `L0|L1|L2|L3`. Detects model-tier paste-errors (haiku/sonnet/opus accidentally placed in the cache-tier slot).
+- **`npm run validate:no-internal-refs`** (`scripts/validate-no-internal-refs.cjs`): ratcheted baseline at 1,749 hits across 286 files. Fails when any file regresses beyond its baseline count of Phase NN / Plan NN-MM / .planning/ / D-NN references. `--rebaseline` ratchets after legitimate cleanup.
+- **`npm run validate:cache-tiers`** (`scripts/check-cache-tiers.cjs`): SHA-256 of `reference/meta-rules.md` + `reference/shared-preamble.md` (the L0 cache prefix imported by 58 of 62 agents). Drift fails the build. See `reference/cache-tier-doctrine.md`.
+- **`npm run validate:skill-surface`** (`test/suite/skill-surface-sync.test.cjs`): asserts every `skills/` dir on disk is documented in at least one of SKILL.md's three surfaces (argument-hint / Command Reference table / Jump Mode).
+
+### Added (Batch D wirings - 8 aspirational features made real)
+
+- **`skills/paper-write/`** (new): paper.design canvas write-back (modes: annotate / tokenize / roundtrip). Modeled on `skills/figma-write/`.
+- **`skills/pencil-write/`** (new): pencil.dev `.pen` file write-back (modes: annotate / roundtrip). File-based - no MCP.
+- **`hooks/gdd-intel-trigger.js`** (new): PostToolUse hook that fires `scripts/build-intel.cjs --incremental` in the background when Edit/Write touches `(skills|agents|reference|source/skills)/.*\.(md|json)`. 5-minute lock dedups rapid sequential edits. Opt-out via `GDD_DISABLE_INTEL_TRIGGER=1`.
+- **`design-component-generator` dispatch** wired into `skills/design/SKILL.md`. Fires opt-in when STATE.md `<connections>` shows a generator connection available (21st-dev / magic-patterns / plasmic / builder-io / v0-dev) and the plan has a `task_type: component` task without matching `src/components/*.tsx`.
+- **`design-context-reviewer` + gate** wired into `skills/explore/` Step 2.6. Cheap Haiku gate runs first; full 9-check graph review fires only when gate says "review needed".
+- **`design-research-synthesizer` opts into peer-CLI delegation** (`delegate_to: gemini-research`) - first agent in the 61-agent fleet. Bandit posterior now collects real arm data on `(design-research-synthesizer, *, gemini)` tuples.
+- **`touches-pattern-miner` wired into `apply-reflections`**: archived task-file `Touches:` signatures now surface as auto-crystallization proposals via `discoverTouchesPatternProposals()`.
+- **`design-planner` + `design-verifier` emit JSON output contracts** per `reference/output-contracts/{planner,verifier}-decision.schema.json` (fenced ```json block before the prose body). Typed envelope consumption by `scripts/lib/parse-contract.cjs#parsePlannerDecision` / `parseVerifierDecision`. DESIGN-PLAN.md and DESIGN-VERIFICATION.md continue to include both formats.
+
+### Added (Batch H - Phase 57 wire-ups)
+
+- **Phase 56 calibration loop wired end-to-end.** `hooks/gdd-risk-gate.js` now calls `updateCalibration` after every scored decision (allow/block/review/require_confirmation → accepted true/false). `detectDrift` now fires from production traffic, not synthetic data. +9 regression tests.
+- **`scripts/lib/state/query-surface.cjs` backup-guard hardening**: `_safeBackup(srcPath, bakPath)` returns true only when the backup file exists AND is non-empty after `copyFileSync`. `backupCycle()`, `demigrate()`, `recover()` now gate `fs.unlinkSync` behind it. +7 regression tests covering happy path / missing source / zero-byte copy / mocked failing copy.
+- **`scripts/lib/state/state-store.cjs` `migrate()` async + JSDoc.** The underlying `migrateToSqlite` was already async; the wrapper now awaits it. Comprehensive JSDoc covers degraded paths, error semantics, idempotency, opt-in via `force`, dual-channel result shapes. +4 sqlite-path regression tests.
+
+### Removed
+
+- **`scripts/lib/audit-aggregator/index.cjs`** (219 LOC + 15 unit tests). Shipped in Plan 23-04; zero production callers across `scripts/ sdk/ hooks/ agents/ skills/`. With Phase 56 risk-gate owning post-action consolidation and design-verifier owning audit aggregation natively, the module was dead-on-arrival.
+- **`scripts/lib/hedge-ensemble.cjs`** (AdaNormalHedge implementation). Shipped in Plan 23.5-02; never wired into `adaptive_mode='hedge'` or any production path. `isHedgeEnabled()` now always returns false.
+
+### Changed (manifests + docs)
+
+- **Manifest count claims synchronized across all 11 surfaces** to filesystem truth: 61 agents / 96 skills / 42 connections / 13 MCP tools. plugin.json + marketplace.json descriptions trimmed from 2000+ chars to ~700 (dropped sprawling per-version history - see CHANGELOG for that).
+- **README rewritten from 968 lines to 623 lines.** Removed 30 per-version "Highlights" chronicle sections (all verified present in CHANGELOG before deletion). Product surface kept verbatim; release chronicle moves to CHANGELOG.
+- **agents/README.md authoring contract cleaned**: 13 Phase NN refs + 11 Plan NN-MM refs + 3 dangling `.planning/phases/` cross-refs + 4 CONTEXT D-NN shorthand refs removed.
+- **L0 cache prefix sanitized**: `reference/shared-preamble.md` "GSD Agent" → "GDD Agent" identity (every agent's first byte block). `reference/meta-rules.md` Phase NN refs stripped from the commit-scope guidance that propagates into every user repo.
+- **`reference/STATE-TEMPLATE.md` HTML comments scrubbed** - three `<!-- Phase 25 -->` comments inside the `==== BEGIN/END TEMPLATE ====` block were being copied verbatim into every user's `.design/STATE.md` at scan entry.
+- **`reference/registry.json` description-field sweep**: ~90 "Phase NN" prefixes stripped from description fields that load into router prompts.
+- **7 schema files cleaned of Phase / .planning refs** in description fields (they ship via `generated.d.ts` to user IDE autocomplete).
+- **9 skill `description:` frontmatter fields cleaned** (router LLM-signal surface): bandit-status, openrouter-status, state, override, peers, debug, report-issue, scan, discover.
+- **`agents/design-verifier.md` H2 headings renamed** `## Phase 1..5` → `## Stage 1..5` (those headings bleed into user `.design/DESIGN-VERIFICATION.md` output and collided with internal GDD-roadmap nomenclature).
+- **`gsd-health` references** in `skills/report-issue/SKILL.md`, `source/skills/report-issue/SKILL.md`, `scripts/lib/issue-reporter/report-flow.cjs` → `/gdd:health` (the actual command).
+- **`benchmark` agents output paths** moved from `.planning/benchmarks/` to `.design/benchmarks/` (`.planning/` is the plugin's own development workspace and must never appear in a user repo's writes).
+- **`connections/connections.md` matrix stage columns** `scan|discover` → `brief|explore` (the actual current 5-stage pipeline).
+- **`runtime-models.md` added "Verification status" banner** flagging 10 of 14 entries as unverified placeholder fills (BYOK / multi-provider; Anthropic-default mapping).
+- **`reference/cache-tier-doctrine.md`** (new): codifies the L0/L1/L2/L3 cache-tier contract that the new gates enforce.
+- **`reference/intel-schema.md`** documented the `agent-tiers.json` slice and softened the misleading "kept current" claim.
+- **`agents/design-research-synthesizer.md`** + **`agents/design-planner.md`** + **`agents/design-verifier.md`** gained delegate_to / Output Contract sections (see "Added" above).
+- **42nd connection added**: `connections/cursor.md` documents the cursor install path + the documented sibling-drop limitation (Cursor `installMultiArtifact` doesn't enumerate `<skill>/<sibling>.md` files; the fix requires extending the StagedArtifact contract and is deferred with explicit doc trail).
+- **`hooks/budget-enforcer.js` → `.ts` references updated** across 11 docs files (Plan 20-13 conversion landed; docs lagged).
+- **Pipeline phrasing corrected**: `brief → plan → implement → verify` (4 surfaces) → `brief → explore → plan → design → verify` (the actual 5-stage pipeline).
+- **2 stale "Executor B pending" / "Executor A hasn't run" strings** updated to present tense (the SQLite migration shipped in v1.57.0).
+- **Composition graph edges added** for 5 high-traffic skills (compare, complete-cycle, darkmode, new-cycle, new-project) via `scripts/lib/manifest/skills.json`. `reference/skill-graph.md` regenerated.
+
+### Test infrastructure
+
+- **`startsWith('design-')` filter widened to all agents** in 5 test files. Coverage jumped from 30 design-* agents to 61 (all). `agent-frontmatter` alone went from 60 tests to 122.
+- **7 Phase 28.8 baseline skips closed.** Disambiguated "runtime" (14 Tier-1 install targets) vs "registry entry" (16 entries with 2 Tier-2 channels codex-plugin + cursor-marketplace).
+- **`insight-line.schema tier:"haiku"` paste-error fixed** to L2 + new CI gate prevents recurrence.
+
+### Security
+
+- 3 CodeQL alerts closed: `scripts/bootstrap.cjs` git arg-injection (added `--` separator + leading-`-` validation), `scripts/build-distribution-bundles.cjs` multi-character HTML strip (loop iteration + `/s` flag).
+
+---
+
 ## [1.57.1] - 2026-06-03
 
 ### Fixed
@@ -28,6 +159,14 @@ degrade real users who have the module). No new dependency; the markdown floor i
   no `event_id`, extra fields); `hooks/gdd-risk-gate.js` now emits the schema-correct shape, and an Ajv validation test
   guards it. The **dashboard risk column** read the wrong fields and case-mismatched the action vocabulary, so it was
   permanently blank; it is now wired and case-correct.
+- **The Phase 56 calibration loop was unwired.** `scripts/lib/risk/calibration.cjs` was a complete library - rolling-50
+  window, `updateCalibration`, `detectDrift`, `recordRiskOutcome` - but no caller invoked it outside its own tests, so
+  drift detection could only fire from synthetic data. `hooks/gdd-risk-gate.js` now calls `updateCalibration` on every
+  scored call when the writer agent is known (`payload.agent` or `GDD_AGENT`): `block` records `accepted:false`; `allow`,
+  `review`, and `require_confirmation` record `accepted:true`. The store accrues from real traffic, so `detectDrift` flags
+  `under_scoring` / `over_scoring` from production behaviour. Best-effort (a calibration write never breaks a tool call);
+  no-op when the agent is unknown so an "unknown" bucket cannot pool the signal. `user_undo` / `post_apply_correct` are
+  left unresolved at the PreToolUse boundary by design; a later PostToolUse pass can resolve them.
 - **`budget-enforcer` PreToolUse blocks** used `message` instead of `stopReason`, so the block reason was invisible to
   the user; they now use `stopReason`. The **read-injection scanner** loads its pattern file fail-open (a missing file
   no longer crashes the hook). Three package-root walk-ups now match the scoped package name.