@hegemonart/get-design-done 1.59.6 → 1.59.7

package/.claude-plugin/marketplace.json

@@ -5,14 +5,14 @@
   },
   "metadata": {
     "description": "Get Design Done — 5-stage agent-orchestrated design pipeline (Brief → Explore → Plan → Design → Verify) for AI coding agents. 64 agents, 96 skills, 39 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": "1.59.6"
+    "version": "1.59.7"
   },
   "plugins": [
     {
       "name": "get-design-done",
       "source": "./",
       "description": "Agent-orchestrated 5-stage design pipeline (Brief → Explore → Plan → Design → Verify) for AI coding agents. 64 specialized agents, 96 skills, 39 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": "1.59.6",
+      "version": "1.59.7",
       "author": {
         "name": "hegemonart"
       },

package/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "get-design-done",
   "short_name": "gdd",
-  "version": "1.59.6",
+  "version": "1.59.7",
   "description": "Agent-orchestrated 5-stage design pipeline (Brief → Explore → Plan → Design → Verify) for AI coding agents. 64 specialized agents, 96 skills, 39 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",

package/CHANGELOG.md

@@ -4,6 +4,28 @@ All notable changes to get-design-done are documented here. Versions follow [sem
 
 ---
 
+## [1.59.7] - 2026-06-05
+
+Docs polish following the v1.59 milestone: confident multi-runtime framing, named runtimes, and a full i18n refresh.
+
+### Changed
+
+- **Confident multi-runtime framing.** The README's Multi-Runtime section now leads with "Claude Code is the flagship; the full experience runs there end to end," stating the depth distinction factually (hooks are Claude-specific, MCP-backed connections light up on the MCP-capable hosts) without the prior apologetic "untested / not guaranteed" hedge. The tagline names the main runtimes (Codex, Cursor, Gemini, OpenCode, Copilot, Windsurf, and more) rather than an anonymous count.
+- **All 6 localized READMEs retranslated** from the current product-first English README; the previous translations were stale (old 37-agent / 12-connection structure). Badges, language nav, CLI commands, and the install channels are preserved.
+
+### Removed
+
+- The `gsd-build` / `cc-multi-cli` / `obra-superpowers` "ported from" attribution paragraph from the product README; the attributions remain in `NOTICE`.
+- Two maintainer field-test notes that had leaked into `docs/` (`codex-plugin-field-test.md`, `cursor-marketplace-field-test.md`); the doctor scripts' user-facing guidance was rewired off the dead paths.
+
+### Breaking changes
+
+None.
+
+5,069/5,069 tests pass.
+
+---
+
 ## [1.59.6] - 2026-06-05
 
 Sixth and final point release of the **v1.59 "Audit Closeout & Honesty Pass"** milestone. Product-surface docs, the handoff skill, and the fact-gate. **Milestone complete.**

package/README.md

@@ -6,7 +6,7 @@
 
 **A design-quality pipeline for AI coding agents: brief -> explore -> plan -> design -> verify.**
 
-**Get Design Done keeps AI-generated UI tied to your brief, your design system, your local design knowledge, and your quality gates. Built for Claude Code, with broad install support across 14 AI coding runtimes.**
+**Get Design Done keeps AI-generated UI tied to your brief, your design system, your local design knowledge, and your quality gates. Built for Claude Code, and installs across Codex, Cursor, Gemini, OpenCode, Copilot, Windsurf, and more.**
 
 [![npm version](https://img.shields.io/npm/v/@hegemonart/get-design-done?style=for-the-badge&logo=npm&logoColor=white&color=CB3837)](https://www.npmjs.com/package/@hegemonart/get-design-done)
 [![npm downloads](https://img.shields.io/npm/dm/@hegemonart/get-design-done?style=for-the-badge&logo=npm&logoColor=white&color=CB3837)](https://www.npmjs.com/package/@hegemonart/get-design-done)
@@ -313,16 +313,9 @@ For the full connection list with probe patterns, see [connections/connections.m
 
 ## Multi-Runtime Support
 
-GDD installs across 14 AI coding runtimes: Claude Code, Codex, Cursor, Gemini CLI, OpenCode, Kilo, Copilot, Windsurf, Antigravity, Augment, Trae, Qwen Code, CodeBuddy, and Cline. Each runtime receives its native artifact layout (`skills/`, `command/`, `agents/`, or `.clinerules`) via per-runtime content converters.
+GDD installs across 14 AI coding runtimes: Claude Code, Codex, Cursor, Gemini CLI, OpenCode, Kilo, Copilot, Windsurf, Antigravity, Augment, Trae, Qwen Code, CodeBuddy, and Cline. The same source skills and agents are compiled to each runtime's native layout (`skills/`, `command/`, `agents/`, or `.clinerules`) by per-runtime converters, so the pipeline travels with you across editors.
 
-Be honest about what that breadth means today:
-
-- **Full design-quality gate is Claude Code.** The complete pipeline, with all agents, hooks, and verification, is developed and tested against Claude Code.
-- **Hooks are Claude-only.** The defense-in-depth hooks (protected paths, bash guard, injection scanner, MCP circuit breaker, budget enforcer) run on Claude Code. Other runtimes install the skills and agents but not the hook layer.
-- **MCP-backed connections work on roughly 3 runtimes** (the MCP-capable hosts). On runtimes without MCP support, MCP-only connections fall back to their degraded paths.
-- **The remaining runtimes are install-supported but untested** for the full design-quality flow. Skills and agents are translated to each runtime's shape, but parity with the Claude Code experience is not guaranteed.
-
-The breadth is real: the same source skills are converted to every runtime. The depth of the quality gate is strongest on Claude Code.
+Claude Code is the flagship. The full experience runs there end to end: every agent, the defense-in-depth hooks, and the MCP-backed connections. On the other runtimes you get the same skills and agents in their native shape, MCP-backed connections light up on the MCP-capable hosts, and the hook layer is specific to Claude Code.
 
 ## Safety And Privacy
 
@@ -397,9 +390,7 @@ Read: [CONTRIBUTING.md](CONTRIBUTING.md)
 
 ## License
 
-MIT License. See [LICENSE](LICENSE) for details.
-
-Architecture ported from `gsd-build/get-shit-done` (MIT - see `NOTICE`). Peer-CLI protocol shapes adapted from `greenpolo/cc-multi-cli` (Apache 2.0). Skill-discipline mechanism ported from [`obra/superpowers`](https://github.com/obra/superpowers) (MIT).
+MIT License. See [LICENSE](LICENSE) for details. Third-party attributions are listed in [NOTICE](NOTICE).
 
 ---