@hegemonart/get-design-done 1.28.7 → 1.28.8

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": "1.28.7"
+    "version": "1.28.8"
   },
   "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": "1.28.7",
+      "version": "1.28.8",
       "author": {
         "name": "hegemonart"
       },

package/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "get-design-done",
   "short_name": "gdd",
-  "version": "1.28.7",
+  "version": "1.28.8",
   "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 +4,41 @@ All notable changes to get-design-done are documented here. Versions follow [sem
 
 ---
 
+## [1.28.8] - 2026-05-19
+
+### Phase 28.8 — Tier-2 Distribution Channels
+
+Three new structured distribution channels alongside the Phase 28.7 file-drop install paths. v1.28.8 ships manifest code + bundle generators + doctor mode integration for all three channels; live publish + live install field-tests run post-merge as maintainer steps (D-09 revised, D-16). Off-cadence decimal sub-phase from v1.28.7 parent — sequence 1.28.0 → 1.28.5 → 1.28.6 → 1.28.7 → 1.28.8. 12 plans across Wave A (research + lint check) / Wave B (manifests + converters + doctors) / Wave C (bundle builder + Tier-2 doctor aggregation) / Wave D (closeout).
+
+### Added
+
+- **Tier-2 distribution channels** — three new structured channels alongside the Phase 28.7 file-drop install paths:
+  - **agentskills.io compliance lint** (`scripts/lint-agentskills-spec.cjs`, Workstream A). The open SKILL.md spec adopted by ~38 tools is now enforced against `skills/` on every change. Per D-13 the recommendation was lint-only (our Phase 28.5 frontmatter contract already matches the 2 required spec fields `name` + `description`). 38 PASS / 32 WARN / 0 FAIL across the current `skills/` tree.
+  - **Cursor Marketplace** — `.cursor-plugin/plugin.json` manifest at repo root + `scripts/lib/install/converters/cursor-marketplace.cjs` bundle generator. New `kind: 'cursor-marketplace'` in `scripts/lib/install/runtimes.cjs`. Doctor reports application status: `not-submitted` / `submitted-pending` / `approved-published` / `rejected` (B2). Per D-04 + D-16: publisher application gated by Cursor team review — maintainer submits post-merge.
+  - **Codex Plugin** — `.codex-plugin/plugin.json` manifest at repo root + `scripts/lib/install/converters/codex-plugin.cjs` bundle generator. New `kind: 'codex-plugin'` in `runtimes.cjs`. Install today via `codex plugin marketplace add hegemonart/get-design-done` against any GitHub URL (D-03). Per D-14: catalog discovery reuses the existing `.claude-plugin/marketplace.json` — no separate Codex catalog file authored.
+- `scripts/build-distribution-bundles.cjs` — shared source / per-channel bundle builder (X1). Produces `dist/cursor-marketplace/`, `dist/codex-plugin/`, `dist/agentskills-io/` from one `skills/` tree (D-06 single source of truth).
+- `scripts/doctor-tier2.cjs` — Tier-2 status aggregator surfaced via `scripts/install.cjs --doctor` (X2).
+- Cross-runtime agentskills.io compat verification reports under `.planning/research/agentskills-io-compat/<runtime>.md` (A2) — 5 runtime reports (Codex, Kilo, Augment, Hermes, Qwen).
+- `docs/cursor-marketplace-field-test.md` + `docs/codex-plugin-field-test.md` — maintainer-facing field-test playbooks (post-merge live publish + install verification per D-09 revised).
+- Wave A research deep-reads at `.planning/research/`: `agentskills-io-2026-05-19.md`, `cursor-marketplace-2026-05-19.md`, `codex-plugins-2026-05-19.md`.
+
+### Changed
+
+- `scripts/install.cjs --doctor` now includes a **Tier-2 Distribution Channels** section aggregating: agentskills.io lint pass/fail (Workstream A), Cursor Marketplace publisher-application status (B2), Codex Plugin manifest + install verification (C2). Single consolidated tier-2 status block per X2.
+- `scripts/lint-agentskills-spec.cjs` gained a `--summary` mode for CI integration.
+- 5 skill renames + 13 cross-reference rewrites across the `skills/` tree per A1+ / A1++ alignment with the agentskills.io schema.
+
+### Documentation
+
+- `docs/cursor-marketplace-field-test.md`, `docs/codex-plugin-field-test.md` — added.
+- `README.md` + 6 translated READMEs (de/fr/it/ja/ko/zh-CN) updated with Tier-2 install paths per adopted channel (agentskills.io cross-runtime portability note, Cursor Marketplace pending-application note, Codex `codex plugin marketplace add hegemonart/get-design-done`).
+
+### Backward compatibility
+
+- Per D-05: Phase 28.7 file-drop install (`scripts/lib/install/converters/cursor.cjs`, `scripts/lib/install/converters/codex.cjs`) is UNCHANGED. Tier-2 channels are additive opt-in surfaces — existing install paths continue to work exactly as in v1.28.7.
+
+---
+
 ## [1.28.7] — 2026-05-19
 
 ### Phase 28.7 — Multi-Runtime Install (Pragmatic Port from gsd-build)

package/README.de.md

@@ -197,6 +197,20 @@ claude plugin install get-design-done@get-design-done
 
 </details>
 
+### Tier-2 Distribution Channels (v1.28.8+)
+
+Zusätzlich zu den Phase-28.7-Datei-Installationspfaden oben (Standard, weiterhin funktionsfähig) fügt v1.28.8 drei neue Tier-2-Vertriebskanäle hinzu:
+
+- **agentskills.io Plattform-übergreifende Portabilität.** Unsere `skills/` sind spec-konform nach dem [agentskills.io](https://agentskills.io) Standard. Runtimes, die agentskills.io-Kompatibilität beanspruchen (Codex, Kilo, Augment, Hermes, Qwen), können unsere Skills direkt konsumieren.
+- **Cursor Marketplace.** Installation via Cursor Marketplace-UI; Veröffentlichung steht aus, abhängig von der Cursor-Team-Prüfung — siehe `docs/cursor-marketplace-field-test.md`.
+- **Codex Plugin.** Installation via Codex GitHub-URL Plugin-Add:
+
+  ```bash
+  codex plugin marketplace add hegemonart/get-design-done
+  ```
+
+Vollständige Details siehe [README.md](README.md) (Englisch, autoritativ).
+
 
 ## Wie es funktioniert
 

package/README.fr.md

@@ -197,6 +197,20 @@ claude plugin install get-design-done@get-design-done
 
 </details>
 
+### Tier-2 Distribution Channels (v1.28.8+)
+
+En complément des chemins d'installation par dépôt de fichiers de la Phase 28.7 ci-dessus (par défaut, toujours fonctionnels), la v1.28.8 ajoute trois nouveaux canaux de distribution Tier-2 :
+
+- **Portabilité multi-runtime via agentskills.io.** Nos `skills/` sont conformes à la spécification [agentskills.io](https://agentskills.io). Les runtimes revendiquant la compatibilité agentskills.io (Codex, Kilo, Augment, Hermes, Qwen) peuvent consommer nos skills directement.
+- **Cursor Marketplace.** Installation via l'interface marketplace de Cursor ; publication en attente de la revue de l'équipe Cursor — voir `docs/cursor-marketplace-field-test.md`.
+- **Codex Plugin.** Installation via l'ajout de plugin par URL GitHub de Codex :
+
+  ```bash
+  codex plugin marketplace add hegemonart/get-design-done
+  ```
+
+Pour les détails complets, voir [README.md](README.md) (anglais, autoritatif).
+
 
 ## Comment ça marche
 

package/README.it.md

@@ -197,6 +197,20 @@ claude plugin install get-design-done@get-design-done
 
 </details>
 
+### Tier-2 Distribution Channels (v1.28.8+)
+
+Oltre ai percorsi di installazione file-drop della Fase 28.7 sopra (predefiniti, continuano a funzionare), v1.28.8 aggiunge tre nuovi canali di distribuzione Tier-2:
+
+- **Portabilità cross-runtime tramite agentskills.io.** I nostri `skills/` sono conformi alla specifica [agentskills.io](https://agentskills.io). I runtime che dichiarano compatibilità agentskills.io (Codex, Kilo, Augment, Hermes, Qwen) possono consumare i nostri skills direttamente.
+- **Cursor Marketplace.** Installazione tramite l'interfaccia marketplace di Cursor; pubblicazione in attesa della revisione del team Cursor — vedere `docs/cursor-marketplace-field-test.md`.
+- **Codex Plugin.** Installazione tramite l'aggiunta plugin per URL GitHub di Codex:
+
+  ```bash
+  codex plugin marketplace add hegemonart/get-design-done
+  ```
+
+Per i dettagli completi, vedere [README.md](README.md) (inglese, autorevole).
+
 
 ## Come funziona
 

package/README.ja.md

@@ -197,6 +197,20 @@ claude plugin install get-design-done@get-design-done
 
 </details>
 
+### Tier-2 Distribution Channels (v1.28.8+)
+
+上記のフェーズ28.7のファイルドロップインストールパス（デフォルトで引き続き動作）に加え、v1.28.8 は 3 つの新しい Tier-2 配信チャネルを追加します:
+
+- **agentskills.io によるクロスランタイム互換性。** 当方の `skills/` は [agentskills.io](https://agentskills.io) 仕様に準拠しています。agentskills.io 互換を宣言するランタイム（Codex、Kilo、Augment、Hermes、Qwen）はこのチャネル経由で直接スキルを利用できます。
+- **Cursor Marketplace。** Cursor のマーケットプレイス UI からインストール。公開は Cursor チームレビュー承認待ち — `docs/cursor-marketplace-field-test.md` を参照。
+- **Codex Plugin。** Codex の GitHub URL プラグイン追加経由でインストール:
+
+  ```bash
+  codex plugin marketplace add hegemonart/get-design-done
+  ```
+
+詳細は [README.md](README.md)（英語、正本）を参照してください。
+
 
 ## 仕組み
 

package/README.ko.md

@@ -197,6 +197,20 @@ claude plugin install get-design-done@get-design-done
 
 </details>
 
+### Tier-2 Distribution Channels (v1.28.8+)
+
+위의 Phase 28.7 파일 드롭 설치 경로(기본값, 계속 작동)에 더해, v1.28.8은 세 가지 새로운 Tier-2 배포 채널을 추가합니다:
+
+- **agentskills.io 크로스 런타임 호환성.** 우리 `skills/`는 [agentskills.io](https://agentskills.io) 사양을 준수합니다. agentskills.io 호환성을 표방하는 런타임(Codex, Kilo, Augment, Hermes, Qwen)이 이 채널을 통해 직접 스킬을 소비할 수 있습니다.
+- **Cursor Marketplace.** Cursor 마켓플레이스 UI를 통한 설치; Cursor 팀 리뷰 승인 대기 중 — `docs/cursor-marketplace-field-test.md` 참조.
+- **Codex Plugin.** Codex의 GitHub URL 플러그인 추가를 통한 설치:
+
+  ```bash
+  codex plugin marketplace add hegemonart/get-design-done
+  ```
+
+자세한 내용은 [README.md](README.md)(영어, 정본)을 참조하세요.
+
 
 ## 작동 방식
 

package/README.md

@@ -225,6 +225,22 @@ This is what the npx installer does for you — `npx` just collapses two command
 
 </details>
 
+### Tier-2 Distribution Channels (v1.28.8+)
+
+Beyond the Phase 28.7 file-drop install paths above (which remain the default and continue to work exactly as before), v1.28.8 adds three Tier-2 distribution channels for discovery-driven install:
+
+- **agentskills.io cross-runtime portability.** Our `skills/` are spec-compliant per the [agentskills.io](https://agentskills.io) standard (lint-only path per Phase 28.8 D-13; Phase 28.5 frontmatter contract already matches the 2 required spec fields `name` + `description`; current lint score 38 PASS / 32 WARN / 0 FAIL). Runtimes that claim agentskills.io compatibility (Codex, Kilo, Augment, Hermes, Qwen) can consume our skills directly via that channel — see `.planning/research/agentskills-io-compat/<runtime>.md` for per-runtime verification reports.
+- **Cursor Marketplace.** Install via Cursor's marketplace UI. Publisher application submitted to Cursor post-merge; live link pending Cursor team review approval (no published SLA) — see `docs/cursor-marketplace-field-test.md` for current status. Manifest at `.cursor-plugin/plugin.json`.
+- **Codex Plugin.** Install via Codex's GitHub-URL plugin add:
+
+  ```bash
+  codex plugin marketplace add hegemonart/get-design-done
+  ```
+
+  Works today against any GitHub URL with `.codex-plugin/plugin.json`. Per Phase 28.8 D-14: catalog discovery reuses `.claude-plugin/marketplace.json` — no separate Codex catalog file required.
+
+Tier-1 file-drop paths above and Tier-2 channels here are **additive opt-in** — both work independently per Phase 28.8 D-05 backward-compat discipline.
+
 
 ## How It Works
 

package/README.zh-CN.md

@@ -196,6 +196,20 @@ claude plugin install get-design-done@get-design-done
 
 </details>
 
+### Tier-2 Distribution Channels (v1.28.8+)
+
+除了上述 Phase 28.7 文件释放安装路径（默认且继续工作）之外，v1.28.8 新增三个 Tier-2 分发渠道：
+
+- **agentskills.io 跨运行时可移植性。** 我们的 `skills/` 符合 [agentskills.io](https://agentskills.io) 规范。声明兼容 agentskills.io 的运行时（Codex、Kilo、Augment、Hermes、Qwen）可以通过此渠道直接使用我们的技能。
+- **Cursor Marketplace.** 通过 Cursor 市场 UI 安装；发布等待 Cursor 团队审核批准 — 详见 `docs/cursor-marketplace-field-test.md`。
+- **Codex Plugin.** 通过 Codex 的 GitHub URL 插件添加进行安装:
+
+  ```bash
+  codex plugin marketplace add hegemonart/get-design-done
+  ```
+
+完整细节请见 [README.md](README.md)（英文，权威版本）。
+
 
 ## 工作流程
 

package/SKILL.md

@@ -31,11 +31,11 @@ Each stage produces artifacts in `.design/` inside the current project.
 | `map` | `get-design-done:gdd-map` | Parallel codebase mapping — spawns 5 mappers → `.design/map/*.md` + `.design/DESIGN-MAP.md` |
 | `next` | `get-design-done:gdd-next` | Route to the next pipeline stage based on STATE.md |
 | `help` | `get-design-done:gdd-help` | List all commands with one-line descriptions |
-| `style [ComponentName]` | `get-design-done:style` | Generate component handoff doc → .design/DESIGN-STYLE-[Name].md |
-| `darkmode` | `get-design-done:darkmode` | Audit dark mode architecture + contrast + anti-patterns → .design/DARKMODE-AUDIT.md |
-| `compare` | `get-design-done:compare` | Delta between DESIGN.md baseline and DESIGN-VERIFICATION.md → .design/COMPARE-REPORT.md |
-| `figma-write <mode>` | `get-design-done:figma-write` | Write design decisions to Figma (annotate/tokenize/mappings) |
-| `graphify <subcommand>` | `get-design-done:graphify` | Manage Graphify knowledge graph (build/query/status/diff) |
+| `style [ComponentName]` | `get-design-done:gdd-style` | Generate component handoff doc → .design/DESIGN-STYLE-[Name].md |
+| `darkmode` | `get-design-done:gdd-darkmode` | Audit dark mode architecture + contrast + anti-patterns → .design/DARKMODE-AUDIT.md |
+| `compare` | `get-design-done:gdd-compare` | Delta between DESIGN.md baseline and DESIGN-VERIFICATION.md → .design/COMPARE-REPORT.md |
+| `figma-write <mode>` | `get-design-done:gdd-figma-write` | Write design decisions to Figma (annotate/tokenize/mappings) |
+| `graphify <subcommand>` | `get-design-done:gdd-graphify` | Manage Graphify knowledge graph (build/query/status/diff) |
 | `discuss [topic] [--all] [--spec] [--cycle <name>]` | `get-design-done:gdd-discuss` | Adaptive design interview — spawns design-discussant; appends D-XX decisions to STATE.md |
 | `list-assumptions [--area]` | `get-design-done:gdd-list-assumptions` | Surface implicit design assumptions baked into the codebase |
 | **Audit & Session** | | |
@@ -186,11 +186,11 @@ If `$ARGUMENTS` is a stage or command name — invoke it directly, no state chec
 /gdd:map       → Skill("get-design-done:gdd-map")       # parallel codebase mapping
 /gdd:next      → Skill("get-design-done:gdd-next")
 /gdd:help      → Skill("get-design-done:gdd-help")
-/gdd:style     → Skill("get-design-done:style")
-/gdd:darkmode     → Skill("get-design-done:darkmode")
-/gdd:compare      → Skill("get-design-done:compare")
-/gdd:figma-write  → Skill("get-design-done:figma-write")
-/gdd:graphify     → Skill("get-design-done:graphify")
+/gdd:style     → Skill("get-design-done:gdd-style")
+/gdd:darkmode     → Skill("get-design-done:gdd-darkmode")
+/gdd:compare      → Skill("get-design-done:gdd-compare")
+/gdd:figma-write  → Skill("get-design-done:gdd-figma-write")
+/gdd:graphify     → Skill("get-design-done:gdd-graphify")
 /gdd:discuss          → Skill("get-design-done:gdd-discuss")
 /gdd:list-assumptions → Skill("get-design-done:gdd-list-assumptions")
 /gdd:progress         → Skill("get-design-done:gdd-progress")

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@hegemonart/get-design-done",
-  "version": "1.28.7",
+  "version": "1.28.8",
   "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",
@@ -38,11 +38,13 @@
     "provenance": true
   },
   "scripts": {
+    "build:bundles": "node scripts/build-distribution-bundles.cjs",
     "test": "node --test --experimental-strip-types \"tests/**/*.test.cjs\" \"tests/**/*.test.ts\"",
     "typecheck": "tsc --noEmit",
     "codegen:schemas": "node --experimental-strip-types scripts/codegen-schema-types.ts",
     "lint:md": "npx --yes markdownlint-cli2 \"**/*.md\" \"#node_modules\" \"#.planning\" \"#.claude\" \"#test-fixture/baselines\"",
     "lint:links": "npx --yes lychee --no-progress --accept 200,206,403,429 \"**/*.md\" || true",
+    "lint:agentskills": "node scripts/lint-agentskills-spec.cjs",
     "validate:schemas": "node --experimental-strip-types scripts/validate-schemas.ts",
     "validate:frontmatter": "node --experimental-strip-types scripts/validate-frontmatter.ts agents/",
     "detect:stale-refs": "node scripts/detect-stale-refs.cjs",