@hegemonart/get-design-done 1.43.0 → 1.44.0

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": "1.43.0"
+    "version": "1.44.0"
   },
   "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": "1.43.0",
+      "version": "1.44.0",
       "author": {
         "name": "hegemonart"
       },

package/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "get-design-done",
   "short_name": "gdd",
-  "version": "1.43.0",
+  "version": "1.44.0",
   "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",

package/CHANGELOG.md

@@ -4,6 +4,52 @@ All notable changes to get-design-done are documented here. Versions follow [sem
 
 ---
 
+## [1.44.0] - 2026-06-02
+
+### Phase 44 - Harness Capability Matrix
+
+Verifying support for a harness used to mean reading five reference files plus the README, with no "is
+this still current?" stamp anywhere. Phase 44 consolidates it into a generated `HARNESSES.md` backed by
+one source of truth, with an honest status taxonomy and a freshness gate. Planned and executed via the GSD
+pipeline (parallel research + pattern-mapper subagents, then parallel executor agents). No new runtime
+dependency, no new egress.
+
+### Breaking changes
+
+- **A harness freshness gate now runs in CI.** `npm run check:harness-freshness` warns at 60 days and
+  fails at 180 days for harnesses marked `tested` (others report `n/a` and never fail). A `tested` harness
+  whose `last_verified` stamp goes stale will fail the build until re-verified with
+  `npm run verify:harness <id>`. CI also gains `npm run build:harnesses:check` (HARNESSES.md drift gate)
+  and `npm run validate:manifest`. Contributors editing harness support must edit
+  `scripts/lib/manifest/harnesses.json` and regenerate `HARNESSES.md`; see `CONTRIBUTING.md`.
+
+### Added
+
+- **`HARNESSES.md`** at repo root - the human-readable capability matrix (skill discovery, command syntax,
+  MCP, placeholder substitution, install path, status) + per-harness deep-dive links + a `Last verified`
+  stamp. GENERATED by `scripts/generate-harnesses-md.cjs` from the SoT; CI drift-gates it.
+- **Harness matrix as a view of the Phase 41.5 SoT** - `scripts/lib/manifest/harnesses.json` records gain
+  a `capability_matrix` + `last_verified` + `fragment_links`; the manifest schema + `validate:manifest`
+  gate them. Unified with Phase 42's `harness-configs.cjs` (a `phase-44-harness-agreement` test fails on
+  any ID or command-syntax disagreement).
+- **`scripts/lib/harness-freshness.cjs`** (shippable, pure, status-aware) + `scripts/check-harness-freshness.cjs`
+  (CLI) + `gdd:health` check #8 (`harness_freshness`).
+- **`scripts/verify-harness.cjs <id>`** - runs the Phase 42 compile + smoke, then atomically stamps
+  `last_verified` and regenerates `HARNESSES.md`.
+- **Honest status taxonomy** - `claude` is `tested`; the five peer-CLI runtimes (codex, gemini, cursor,
+  copilot, qwen) are `experimental`; the other eight are `untested`. The five reference fragments stay as
+  appendices, cross-linked from the matrix (a cross-link checker fails generation on a broken anchor).
+
+### Notes
+
+- 6-manifest lockstep at **v1.44.0** + `OFF_CADENCE_VERSIONS.add('1.44.0')` + 37 `manifests-version.txt`
+  baselines forward-propagated 1.43.0 -> 1.44.0.
+- `gdd_health` now returns 8 checks (harness_freshness added). The generator, freshness CLI, and verify
+  script are maintainer-only (not shipped); only `scripts/lib/harness-freshness.cjs` ships. Tarball golden
+  868 -> 869 (+`scripts/lib/harness-freshness.cjs`). `HARNESSES.md` is repo-root, not in the npm tarball.
+
+---
+
 ## [1.43.0] - 2026-06-02
 
 ### Phase 43 - Editorial Quality Floor

package/README.md

@@ -247,6 +247,8 @@ All 14 runtimes receive their native artifact layout (`skills/`, `command/`, `ag
 
 **Editorial quality floor (v1.43.0).** A tool that audits design quality should hold its own prose to the same bar. `npm run lint:prose` is a CI gate that fails on em dashes, prose double hyphens, and AI-prose tells (`load-bearing`, `leverage`, `robust`, `seamless`, ...) across the README, `SKILL.md`, `source/skills/`, `agents/`, `CHANGELOG.md`, and `reference/` (bodies and frontmatter descriptions). Fenced/inline code, HTML comments, and Cyrillic-majority files are skipped. The ruleset lives in `STYLE.md`, generated from the shared denylist at `scripts/lib/manifest/prose-denylist.json`. See `CONTRIBUTING.md`. **No new runtime dependency.**
 
+**Harness capability matrix (v1.44.0).** The full per-harness support matrix (skill discovery, command syntax, MCP, install path, status) lives in **[`HARNESSES.md`](HARNESSES.md)** at the repo root, generated from `scripts/lib/manifest/harnesses.json` (the single source of truth; CI drift-gates it). Each harness carries an honest status (`tested` / `experimental` / `untested`) and a `last_verified` stamp; a freshness gate warns at 60 days and fails at 180 for `tested` harnesses, surfaced in `/gdd:health`. The 14-harness count above is the same SoT the matrix reads, so it cannot drift. The five deep-dive reference files (`reference/codex-tools.md`, `reference/gemini-tools.md`, `reference/peer-cli-capabilities.md`, `reference/peer-protocols.md`, `reference/runtime-models.md`) remain as appendices linked from the matrix. **No new runtime dependency.**
+
 Verify with:
 
 ```

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

@@ -67,7 +67,7 @@ Token PRESENCE only is detected (D-10) - the token value is never read, logged,
 
 The `gdd_health` MCP surface also reports a `skill_discipline` check (Phase 32) confirming the using-gdd SessionStart bootstrap is live - detail is one of three exact strings:
 - `skill-discipline: ready` - `skills/using-gdd/SKILL.md` exists AND `hooks/hooks.json` SessionStart wires `inject-using-gdd.sh` (status `ok`).
-- `skill-discipline: missing using-gdd` (skill absent) or `skill-discipline: hook not wired` (skill present, no SessionStart inject) - both `warn`.
+- `skill-discipline: missing using-gdd` (skill absent) or `skill-discipline: hook not wired` (skill present, no SessionStart inject) - both `warn`. The MCP surface also reports a `harness_freshness` check (Phase 44): per-harness `last_verified` age, status-aware (only `tested` harnesses warn at 60d / fail at 180d; others `n/a`). Full taxonomy in `HARNESSES.md`; refresh with `npm run verify:harness <id>`.
 
 ## Check MCP registration (gdd-mcp)
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@hegemonart/get-design-done",
-  "version": "1.43.0",
+  "version": "1.44.0",
   "description": "A design-quality pipeline for AI coding agents: brief, plan, implement, and verify UI work against your design system.",
   "author": "Hegemon",
   "homepage": "https://github.com/hegemonart/get-design-done",
@@ -65,6 +65,10 @@
     "lint:design": "node bin/gdd-detect test/fixtures/detect/negative --json",
     "build:style": "node scripts/generate-style-md.cjs",
     "build:style:check": "node scripts/generate-style-md.cjs --check",
+    "build:harnesses": "node scripts/generate-harnesses-md.cjs",
+    "build:harnesses:check": "node scripts/generate-harnesses-md.cjs --check",
+    "check:harness-freshness": "node scripts/check-harness-freshness.cjs",
+    "verify:harness": "node scripts/verify-harness.cjs",
     "sync:rule-catalogue": "node scripts/sync-rule-catalogue.cjs --check",
     "validate:manifest": "node scripts/validate-manifest.cjs --check",
     "validate:schemas": "node --experimental-strip-types scripts/validate-schemas.ts",

package/scripts/lib/harness-freshness.cjs

@@ -0,0 +1,59 @@
+// Phase 44 - harness freshness (shippable pure module). Read by health-mirror + check-harness-freshness.cjs.
+'use strict';
+
+const { readHarnesses } = require('./manifest/index.cjs');
+
+const WARN_DAYS = 60;
+const FAIL_DAYS = 180;
+const MS_PER_DAY = 86400000;
+
+/**
+ * Returns the age of a last_verified timestamp in fractional days.
+ * Returns Infinity when the timestamp is absent or unparseable.
+ * @param {string|null|undefined} last_verified
+ * @param {number} nowMs
+ * @returns {number}
+ */
+function ageInDays(last_verified, nowMs) {
+  if (!last_verified) return Infinity;
+  const t = Date.parse(last_verified);
+  if (!Number.isFinite(t)) return Infinity;
+  return (nowMs - t) / MS_PER_DAY;
+}
+
+/**
+ * Evaluate freshness for every harness in the manifest (or a supplied list).
+ *
+ * STATUS-AWARE (D-04): only `tested` harnesses can warn/fail on a stale
+ * last_verified date.  experimental / untested / known-broken harnesses
+ * make no freshness promise — their freshness is always 'n/a'.
+ *
+ * @param {{ nowMs?: number, harnesses?: object[] }} [opts]
+ * @returns {{ id: string, status: string, last_verified: string|null, age_days: number|null, freshness: string }[]}
+ */
+function checkFreshness({ nowMs, harnesses } = {}) {
+  const list = harnesses || readHarnesses().harnesses || [];
+  const now = typeof nowMs === 'number' ? nowMs : Date.now();
+
+  return list.map((h) => {
+    const status = (h.capability_matrix && h.capability_matrix.status) || 'untested';
+    const age = ageInDays(h.last_verified, now);
+
+    // Only `tested` harnesses carry a freshness obligation.
+    // All other statuses → 'n/a' (never a build failure).
+    let freshness = 'n/a';
+    if (status === 'tested') {
+      freshness = age >= FAIL_DAYS ? 'fail' : age >= WARN_DAYS ? 'warn' : 'ok';
+    }
+
+    return {
+      id: h.id,
+      status,
+      last_verified: h.last_verified || null,
+      age_days: Number.isFinite(age) ? Math.floor(age) : null,
+      freshness,
+    };
+  });
+}
+
+module.exports = { checkFreshness, ageInDays, WARN_DAYS, FAIL_DAYS };

package/scripts/lib/health-mirror/index.cjs

@@ -51,6 +51,7 @@ const fs = require('node:fs');
 const path = require('node:path');
 
 const { getDisableReason } = require('../issue-reporter/kill-switch.cjs');
+const { checkFreshness, WARN_DAYS, FAIL_DAYS } = require('../harness-freshness.cjs');
 
 function fileExists(p) {
   try {
@@ -211,6 +212,32 @@ async function getHealthChecks(rootDir) {
     checks.push({ name: 'skill_discipline', status, detail });
   }
 
+  // 8. harness_freshness — per-harness last_verified age (Phase 44). PURE: reads the manifest SoT via the
+  // shippable harness-freshness module; status-aware (only `tested` harnesses can warn/fail). NEVER throws.
+  {
+    let status = 'ok';
+    let detail;
+    try {
+      const results = checkFreshness();
+      const failing = results.filter((r) => r.freshness === 'fail');
+      const warning = results.filter((r) => r.freshness === 'warn');
+      const tested = results.filter((r) => r.status === 'tested');
+      if (failing.length) {
+        status = 'fail';
+        detail = `harness freshness: ${failing.length} stale (>${FAIL_DAYS}d): ${failing.map((r) => r.id).join(', ')}`;
+      } else if (warning.length) {
+        status = 'warn';
+        detail = `harness freshness: ${warning.length} aging (>${WARN_DAYS}d): ${warning.map((r) => r.id).join(', ')}`;
+      } else {
+        detail = `harness freshness: ${tested.length} tested harness(es) current`;
+      }
+    } catch {
+      status = 'warn';
+      detail = 'harness freshness: unavailable';
+    }
+    checks.push({ name: 'harness_freshness', status, detail });
+  }
+
   return { checks };
 }
 

package/scripts/lib/manifest/harnesses.json

@@ -7,85 +7,351 @@
       "id": "claude",
       "name": "Claude Code",
       "config_dir": ".claude",
-      "runtime_models_ref": "reference/runtime-models.md#claude"
+      "runtime_models_ref": "reference/runtime-models.md#claude",
+      "capability_matrix": {
+        "skill_discovery": true,
+        "frontmatter_fields_supported": [
+          "name",
+          "description",
+          "argument-hint",
+          "tools",
+          "disable-model-invocation"
+        ],
+        "command_syntax": "/gdd:<skill>",
+        "mcp_support": true,
+        "placeholder_substitution": true,
+        "install_path": "dist/claude-code/.claude/skills/",
+        "status": "tested"
+      },
+      "last_verified": "2026-06-02",
+      "capability_notes": "Host runtime. Marketplace-registered, end-to-end documented, Phase 42 golden baseline.",
+      "fragment_links": [
+        "reference/runtime-models.md#claude---claude-code"
+      ]
     },
     {
       "id": "codex",
       "name": "OpenAI Codex CLI",
       "config_dir": ".codex",
-      "runtime_models_ref": "reference/runtime-models.md#codex"
+      "runtime_models_ref": "reference/runtime-models.md#codex",
+      "capability_matrix": {
+        "skill_discovery": true,
+        "frontmatter_fields_supported": [
+          "name",
+          "description",
+          "tools"
+        ],
+        "command_syntax": "/gdd-<skill>",
+        "mcp_support": true,
+        "placeholder_substitution": true,
+        "install_path": "dist/codex/.codex/skills/",
+        "status": "experimental"
+      },
+      "last_verified": null,
+      "capability_notes": "Peer-CLI delegation target (ASP). Flat /gdd- command namespace. MCP auto-registered.",
+      "fragment_links": [
+        "reference/runtime-models.md#codex---openai-codex-cli",
+        "reference/codex-tools.md#tool-name-mapping",
+        "reference/peer-cli-capabilities.md#codex-asp",
+        "reference/peer-protocols.md#asp---app-server-protocol-codex"
+      ]
     },
     {
       "id": "gemini",
       "name": "Gemini CLI",
       "config_dir": ".gemini",
-      "runtime_models_ref": "reference/runtime-models.md#gemini"
+      "runtime_models_ref": "reference/runtime-models.md#gemini",
+      "capability_matrix": {
+        "skill_discovery": true,
+        "frontmatter_fields_supported": [
+          "name",
+          "description",
+          "tools"
+        ],
+        "command_syntax": "/gdd:<skill>",
+        "mcp_support": true,
+        "placeholder_substitution": true,
+        "install_path": "dist/gemini/.gemini/skills/",
+        "status": "experimental"
+      },
+      "last_verified": null,
+      "capability_notes": "",
+      "fragment_links": [
+        "reference/runtime-models.md#gemini---gemini-cli",
+        "reference/gemini-tools.md#tool-name-mapping",
+        "reference/peer-cli-capabilities.md#gemini-acp",
+        "reference/peer-protocols.md#acp---agent-client-protocol"
+      ]
     },
     {
       "id": "qwen",
       "name": "Qwen Code",
       "config_dir": ".qwen",
-      "runtime_models_ref": "reference/runtime-models.md#qwen"
+      "runtime_models_ref": "reference/runtime-models.md#qwen",
+      "capability_matrix": {
+        "skill_discovery": true,
+        "frontmatter_fields_supported": [
+          "name",
+          "description",
+          "tools"
+        ],
+        "command_syntax": "/gdd:<skill>",
+        "mcp_support": false,
+        "placeholder_substitution": true,
+        "install_path": "dist/qwen/.qwen/skills/",
+        "status": "experimental"
+      },
+      "last_verified": null,
+      "capability_notes": "",
+      "fragment_links": [
+        "reference/runtime-models.md#qwen---qwen-code",
+        "reference/peer-cli-capabilities.md#qwen-acp",
+        "reference/peer-protocols.md#acp---agent-client-protocol"
+      ]
     },
     {
       "id": "kilo",
       "name": "Kilo Code",
       "config_dir": ".kilo",
-      "runtime_models_ref": "reference/runtime-models.md#kilo"
+      "runtime_models_ref": "reference/runtime-models.md#kilo",
+      "capability_matrix": {
+        "skill_discovery": true,
+        "frontmatter_fields_supported": [
+          "name",
+          "description",
+          "tools"
+        ],
+        "command_syntax": "/gdd:<skill>",
+        "mcp_support": false,
+        "placeholder_substitution": true,
+        "install_path": "dist/kilo/.kilo/skills/",
+        "status": "untested"
+      },
+      "last_verified": null,
+      "capability_notes": "",
+      "fragment_links": [
+        "reference/runtime-models.md#kilo---kilo-code"
+      ]
     },
     {
       "id": "copilot",
       "name": "GitHub Copilot CLI",
       "config_dir": ".copilot",
-      "runtime_models_ref": "reference/runtime-models.md#copilot"
+      "runtime_models_ref": "reference/runtime-models.md#copilot",
+      "capability_matrix": {
+        "skill_discovery": true,
+        "frontmatter_fields_supported": [
+          "name",
+          "description",
+          "tools"
+        ],
+        "command_syntax": "/gdd:<skill>",
+        "mcp_support": false,
+        "placeholder_substitution": true,
+        "install_path": "dist/copilot/.copilot/skills/",
+        "status": "experimental"
+      },
+      "last_verified": null,
+      "capability_notes": "",
+      "fragment_links": [
+        "reference/runtime-models.md#copilot---github-copilot-cli",
+        "reference/peer-cli-capabilities.md#copilot-acp",
+        "reference/peer-protocols.md#acp---agent-client-protocol"
+      ]
     },
     {
       "id": "cursor",
       "name": "Cursor",
       "config_dir": ".cursor",
-      "runtime_models_ref": "reference/runtime-models.md#cursor"
+      "runtime_models_ref": "reference/runtime-models.md#cursor",
+      "capability_matrix": {
+        "skill_discovery": true,
+        "frontmatter_fields_supported": [
+          "name",
+          "description",
+          "tools"
+        ],
+        "command_syntax": "/gdd:<skill>",
+        "mcp_support": false,
+        "placeholder_substitution": true,
+        "install_path": "dist/cursor/.cursor/skills/",
+        "status": "experimental"
+      },
+      "last_verified": null,
+      "capability_notes": "",
+      "fragment_links": [
+        "reference/runtime-models.md#cursor---cursor",
+        "reference/peer-cli-capabilities.md#cursor-acp",
+        "reference/peer-protocols.md#acp---agent-client-protocol"
+      ]
     },
     {
       "id": "windsurf",
       "name": "Windsurf (Cascade)",
       "config_dir": ".windsurf",
-      "runtime_models_ref": "reference/runtime-models.md#windsurf"
+      "runtime_models_ref": "reference/runtime-models.md#windsurf",
+      "capability_matrix": {
+        "skill_discovery": true,
+        "frontmatter_fields_supported": [
+          "name",
+          "description",
+          "tools"
+        ],
+        "command_syntax": "/gdd:<skill>",
+        "mcp_support": false,
+        "placeholder_substitution": true,
+        "install_path": "dist/windsurf/.windsurf/skills/",
+        "status": "untested"
+      },
+      "last_verified": null,
+      "capability_notes": "",
+      "fragment_links": [
+        "reference/runtime-models.md#windsurf---windsurf"
+      ]
     },
     {
       "id": "antigravity",
       "name": "Antigravity",
       "config_dir": ".antigravity",
-      "runtime_models_ref": "reference/runtime-models.md#antigravity"
+      "runtime_models_ref": "reference/runtime-models.md#antigravity",
+      "capability_matrix": {
+        "skill_discovery": true,
+        "frontmatter_fields_supported": [
+          "name",
+          "description",
+          "tools"
+        ],
+        "command_syntax": "/gdd:<skill>",
+        "mcp_support": false,
+        "placeholder_substitution": true,
+        "install_path": "dist/antigravity/.antigravity/skills/",
+        "status": "untested"
+      },
+      "last_verified": null,
+      "capability_notes": "",
+      "fragment_links": [
+        "reference/runtime-models.md#antigravity---antigravity"
+      ]
     },
     {
       "id": "augment",
       "name": "Augment",
       "config_dir": ".augment",
-      "runtime_models_ref": "reference/runtime-models.md#augment"
+      "runtime_models_ref": "reference/runtime-models.md#augment",
+      "capability_matrix": {
+        "skill_discovery": true,
+        "frontmatter_fields_supported": [
+          "name",
+          "description",
+          "tools"
+        ],
+        "command_syntax": "/gdd:<skill>",
+        "mcp_support": false,
+        "placeholder_substitution": true,
+        "install_path": "dist/augment/.augment/skills/",
+        "status": "untested"
+      },
+      "last_verified": null,
+      "capability_notes": "",
+      "fragment_links": [
+        "reference/runtime-models.md#augment---augment"
+      ]
     },
     {
       "id": "trae",
       "name": "Trae",
       "config_dir": ".trae",
-      "runtime_models_ref": "reference/runtime-models.md#trae"
+      "runtime_models_ref": "reference/runtime-models.md#trae",
+      "capability_matrix": {
+        "skill_discovery": true,
+        "frontmatter_fields_supported": [
+          "name",
+          "description",
+          "tools"
+        ],
+        "command_syntax": "/gdd:<skill>",
+        "mcp_support": false,
+        "placeholder_substitution": true,
+        "install_path": "dist/trae/.trae/skills/",
+        "status": "untested"
+      },
+      "last_verified": null,
+      "capability_notes": "",
+      "fragment_links": [
+        "reference/runtime-models.md#trae---trae"
+      ]
     },
     {
       "id": "codebuddy",
       "name": "CodeBuddy",
       "config_dir": ".codebuddy",
-      "runtime_models_ref": "reference/runtime-models.md#codebuddy"
+      "runtime_models_ref": "reference/runtime-models.md#codebuddy",
+      "capability_matrix": {
+        "skill_discovery": true,
+        "frontmatter_fields_supported": [
+          "name",
+          "description",
+          "tools"
+        ],
+        "command_syntax": "/gdd:<skill>",
+        "mcp_support": false,
+        "placeholder_substitution": true,
+        "install_path": "dist/codebuddy/.codebuddy/skills/",
+        "status": "untested"
+      },
+      "last_verified": null,
+      "capability_notes": "",
+      "fragment_links": [
+        "reference/runtime-models.md#codebuddy---codebuddy"
+      ]
     },
     {
       "id": "cline",
       "name": "Cline",
       "config_dir": ".cline",
-      "runtime_models_ref": "reference/runtime-models.md#cline"
+      "runtime_models_ref": "reference/runtime-models.md#cline",
+      "capability_matrix": {
+        "skill_discovery": true,
+        "frontmatter_fields_supported": [
+          "name",
+          "description",
+          "tools"
+        ],
+        "command_syntax": "/gdd:<skill>",
+        "mcp_support": false,
+        "placeholder_substitution": true,
+        "install_path": "dist/cline/.cline/skills/",
+        "status": "untested"
+      },
+      "last_verified": null,
+      "capability_notes": "Installs into .clinerules at install time (clinerules-embed special case); dist/cline/ is the compile artifact only.",
+      "fragment_links": [
+        "reference/runtime-models.md#cline---cline"
+      ]
     },
     {
       "id": "opencode",
       "name": "OpenCode",
       "config_dir": ".opencode",
-      "runtime_models_ref": "reference/runtime-models.md#opencode"
+      "runtime_models_ref": "reference/runtime-models.md#opencode",
+      "capability_matrix": {
+        "skill_discovery": true,
+        "frontmatter_fields_supported": [
+          "name",
+          "description",
+          "tools"
+        ],
+        "command_syntax": "/gdd:<skill>",
+        "mcp_support": false,
+        "placeholder_substitution": true,
+        "install_path": "dist/opencode/.opencode/skills/",
+        "status": "untested"
+      },
+      "last_verified": null,
+      "capability_notes": "",
+      "fragment_links": [
+        "reference/runtime-models.md#opencode---opencode"
+      ]
     }
   ]
 }

package/scripts/lib/manifest/schemas/harnesses.schema.json

@@ -30,6 +30,38 @@
           "name": {
             "type": "string",
             "minLength": 1
+          },
+          "last_verified": {
+            "type": ["string", "null"],
+            "description": "YYYY-MM-DD of the last verify-harness run; null if never verified (Phase 44)."
+          },
+          "capability_notes": {
+            "type": "string"
+          },
+          "fragment_links": {
+            "type": "array",
+            "items": { "type": "string" }
+          },
+          "capability_matrix": {
+            "type": "object",
+            "description": "Phase 44 harness capability matrix (a view of this SoT; HARNESSES.md is generated from it).",
+            "additionalProperties": true,
+            "required": ["status", "command_syntax", "install_path"],
+            "properties": {
+              "skill_discovery": { "type": "boolean" },
+              "frontmatter_fields_supported": {
+                "type": "array",
+                "items": { "type": "string" }
+              },
+              "command_syntax": { "type": "string", "minLength": 1 },
+              "mcp_support": { "type": "boolean" },
+              "placeholder_substitution": { "type": "boolean" },
+              "install_path": { "type": "string", "minLength": 1 },
+              "status": {
+                "type": "string",
+                "enum": ["tested", "experimental", "untested", "known-broken"]
+              }
+            }
           }
         }
       }

package/sdk/mcp/gdd-mcp/server.js

@@ -136,6 +136,107 @@ var require_kill_switch = __commonJS({
   }
 });
 
+// scripts/lib/manifest/loader.cjs
+var require_loader = __commonJS({
+  "scripts/lib/manifest/loader.cjs"(exports2, module2) {
+    "use strict";
+    var fs = require("node:fs");
+    var path = require("node:path");
+    var MANIFEST_DIR = __dirname;
+    var _cache = /* @__PURE__ */ new Map();
+    function reset() {
+      _cache.clear();
+    }
+    function load(name13, opts) {
+      const o = opts || {};
+      const dir = o.dir || MANIFEST_DIR;
+      const fallback = Object.prototype.hasOwnProperty.call(o, "fallback") ? o.fallback : {};
+      const abs = path.join(dir, `${name13}.json`);
+      let stat;
+      try {
+        stat = fs.statSync(abs);
+      } catch {
+        if (!o.quiet) process.stderr.write(`manifest: ${name13}.json not found \u2014 using empty fallback (a consumer phase may not have shipped its data yet)
+`);
+        return fallback;
+      }
+      const cached = _cache.get(abs);
+      if (cached && cached.mtimeMs === stat.mtimeMs) return cached.data;
+      try {
+        const data = JSON.parse(fs.readFileSync(abs, "utf8"));
+        _cache.set(abs, { mtimeMs: stat.mtimeMs, data });
+        return data;
+      } catch (e) {
+        if (!o.quiet) process.stderr.write(`manifest: ${name13}.json parse error (${e.message}) \u2014 using empty fallback
+`);
+        return fallback;
+      }
+    }
+    module2.exports = { load, reset, MANIFEST_DIR };
+  }
+});
+
+// scripts/lib/manifest/index.cjs
+var require_manifest = __commonJS({
+  "scripts/lib/manifest/index.cjs"(exports2, module2) {
+    "use strict";
+    var loader = require_loader();
+    function readHarnesses(opts) {
+      return loader.load("harnesses", { ...opts, fallback: { schema_version: 1, generated_at: null, harnesses: [] } });
+    }
+    function readSkills(opts) {
+      return loader.load("skills", { ...opts, fallback: { schema_version: 1, skills: [] } });
+    }
+    function readProseDenylist(opts) {
+      return loader.load("prose-denylist", { ...opts, fallback: { schema_version: 1, tells: [] } });
+    }
+    module2.exports = {
+      readHarnesses,
+      readSkills,
+      readProseDenylist,
+      reset: loader.reset,
+      MANIFEST_DIR: loader.MANIFEST_DIR
+    };
+  }
+});
+
+// scripts/lib/harness-freshness.cjs
+var require_harness_freshness = __commonJS({
+  "scripts/lib/harness-freshness.cjs"(exports2, module2) {
+    "use strict";
+    var { readHarnesses } = require_manifest();
+    var WARN_DAYS = 60;
+    var FAIL_DAYS = 180;
+    var MS_PER_DAY = 864e5;
+    function ageInDays(last_verified, nowMs) {
+      if (!last_verified) return Infinity;
+      const t = Date.parse(last_verified);
+      if (!Number.isFinite(t)) return Infinity;
+      return (nowMs - t) / MS_PER_DAY;
+    }
+    function checkFreshness({ nowMs, harnesses } = {}) {
+      const list = harnesses || readHarnesses().harnesses || [];
+      const now = typeof nowMs === "number" ? nowMs : Date.now();
+      return list.map((h) => {
+        const status = h.capability_matrix && h.capability_matrix.status || "untested";
+        const age = ageInDays(h.last_verified, now);
+        let freshness = "n/a";
+        if (status === "tested") {
+          freshness = age >= FAIL_DAYS ? "fail" : age >= WARN_DAYS ? "warn" : "ok";
+        }
+        return {
+          id: h.id,
+          status,
+          last_verified: h.last_verified || null,
+          age_days: Number.isFinite(age) ? Math.floor(age) : null,
+          freshness
+        };
+      });
+    }
+    module2.exports = { checkFreshness, ageInDays, WARN_DAYS, FAIL_DAYS };
+  }
+});
+
 // scripts/lib/health-mirror/index.cjs
 var require_health_mirror = __commonJS({
   "scripts/lib/health-mirror/index.cjs"(exports2, module2) {
@@ -143,6 +244,7 @@ var require_health_mirror = __commonJS({
     var fs = require("node:fs");
     var path = require("node:path");
     var { getDisableReason } = require_kill_switch();
+    var { checkFreshness, WARN_DAYS, FAIL_DAYS } = require_harness_freshness();
     function fileExists(p) {
       try {
         return fs.statSync(p).isFile();
@@ -270,6 +372,29 @@ var require_health_mirror = __commonJS({
         }
         checks.push({ name: "skill_discipline", status, detail });
       }
+      {
+        let status = "ok";
+        let detail;
+        try {
+          const results = checkFreshness();
+          const failing = results.filter((r) => r.freshness === "fail");
+          const warning = results.filter((r) => r.freshness === "warn");
+          const tested = results.filter((r) => r.status === "tested");
+          if (failing.length) {
+            status = "fail";
+            detail = `harness freshness: ${failing.length} stale (>${FAIL_DAYS}d): ${failing.map((r) => r.id).join(", ")}`;
+          } else if (warning.length) {
+            status = "warn";
+            detail = `harness freshness: ${warning.length} aging (>${WARN_DAYS}d): ${warning.map((r) => r.id).join(", ")}`;
+          } else {
+            detail = `harness freshness: ${tested.length} tested harness(es) current`;
+          }
+        } catch {
+          status = "warn";
+          detail = "harness freshness: unavailable";
+        }
+        checks.push({ name: "harness_freshness", status, detail });
+      }
       return { checks };
     }
     function sessionStartWiresInject(rootDir) {

package/skills/health/SKILL.md

@@ -67,7 +67,7 @@ Token PRESENCE only is detected (D-10) - the token value is never read, logged,
 
 The `gdd_health` MCP surface also reports a `skill_discipline` check (Phase 32) confirming the using-gdd SessionStart bootstrap is live - detail is one of three exact strings:
 - `skill-discipline: ready` - `skills/using-gdd/SKILL.md` exists AND `hooks/hooks.json` SessionStart wires `inject-using-gdd.sh` (status `ok`).
-- `skill-discipline: missing using-gdd` (skill absent) or `skill-discipline: hook not wired` (skill present, no SessionStart inject) - both `warn`.
+- `skill-discipline: missing using-gdd` (skill absent) or `skill-discipline: hook not wired` (skill present, no SessionStart inject) - both `warn`. The MCP surface also reports a `harness_freshness` check (Phase 44): per-harness `last_verified` age, status-aware (only `tested` harnesses warn at 60d / fail at 180d; others `n/a`). Full taxonomy in `HARNESSES.md`; refresh with `npm run verify:harness <id>`.
 
 ## Check MCP registration (gdd-mcp)