Merge 7416866694 into abf3d25f06

.claude/skills/bmad-os-review-pr/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: bmad-os-review-pr
-description: Dual-layer PR review tool (Raven's Verdict). Runs adversarial cynical review and edge case hunter in parallel, merges and deduplicates findings into professional engineering output. Use when user asks to 'review a PR' and provides a PR url or id.
+description: Adversarial PR review tool (Raven's Verdict). Cynical deep review transformed into professional engineering findings. Use when user asks to 'review a PR' and provides a PR url or id.
 ---
 
 Read `prompts/instructions.md` and execute.

.claude/skills/bmad-os-review-pr/prompts/instructions.md

@@ -93,17 +93,13 @@ gh pr diff {PR_NUMBER} [--repo {REPO}] --name-only | grep -E '\.(png|jpg|jpeg|gi
 
 Store list of binary files to skip. Note them in final output.
 
-## Review Layers
+## Adversarial Review
 
-**Launch steps 1.1 and 1.2 as parallel subagents.** Both receive the same PR diff and run concurrently. Wait for both to complete before proceeding to step 1.3.
+### 1.1 Run Cynical Review
-
-### 1.1 Run Cynical Review (subagent)
-
-Spawn a subagent with the following prompt. Pass the full PR diff as context.
 
 **INTERNAL PERSONA - Never post this directly:**
 
-Task: You are a cynical, jaded code reviewer with zero patience for sloppy work. This PR was submitted by a clueless weasel and you expect to find problems. Find at least five issues to fix or improve in it. Number them. Be skeptical of everything.
+Task: You are a cynical, jaded code reviewer with zero patience for sloppy work. This PR was submitted by a clueless weasel and you expect to find problems. Find at least five issues to fix or improve in it. Number them. Be skeptical of everything. Ultrathink.
 
 Output format:
 
@@ -128,64 +124,14 @@ Likely tag:
 - Add `[likely]` to findings with high confidence, e.g. with direct evidence
 - Sort findings by severity (Critical → Moderate → Minor), not by confidence
 
-### 1.2 Run Edge Case Hunter (subagent)
-
-Spawn a subagent that executes the task defined in `_bmad/core/tasks/review-edge-case-hunter.xml`. Pass the full PR diff as the `content` input. Omit `also_consider` unless the user specified extra focus areas.
-
-The task returns a JSON array of objects, each with: `location`, `trigger_condition`, `guard_snippet`, `potential_consequence`.
-
-**Map each JSON finding to the standard finding format:**
-
-````markdown
-### [NUMBER]. [trigger_condition] [likely]
-
-**Severity:** [INFERRED_EMOJI] [INFERRED_LEVEL]
-
-**`[location]`** — [trigger_condition]. [potential_consequence].
-
-**Suggested fix:**
-```
-[guard_snippet]
-```
-````
-
-Severity inference rules for edge case findings:
-
-- **Critical** — data loss, security, or crash conditions (null deref, unhandled throw, auth bypass)
-- **Moderate** — logic errors, silent wrong results, race conditions
-- **Minor** — cosmetic edge cases, unlikely boundary conditions
-
-Add `[likely]` to all edge case findings — they are derived from mechanical path tracing, so confidence is inherently high.
-
-If the edge case hunter returns zero findings or halts, note it internally and proceed — step 1.1 findings still stand.
-
-### 1.3 Merge and Deduplicate
-
-Combine the findings from step 1.1 (adversarial) and step 1.2 (edge case hunter) into a single list.
-
-**Deduplication rules:**
-
-1. Compare each edge case finding against each adversarial finding
-2. Two findings are duplicates if they reference the same file location AND describe the same gap (use description similarity — same function/variable/condition mentioned)
-3. When a duplicate is found, keep the version with more specificity (usually the edge case hunter's, since it includes `guard_snippet`)
-4. Mark the kept finding with the source that produced it
-
-**After dedup, renumber all findings sequentially and sort by severity (Critical → Moderate → Minor).**
-
-Tag each finding with its source:
-
-- `[Adversarial]` — from step 1.1 only
-- `[Edge Case]` — from step 1.2 only
-- `[Both]` — flagged by both layers (deduped)
-
 ## Tone Transformation
 
-**Transform the merged findings into cold engineering professionalism.**
+**Transform the cynical output into cold engineering professionalism.**
 
 **Transformation rules:**
 
 1. Remove all inflammatory language, insults, assumptions about the author
-2. Keep all technical substance, file references, severity ratings, likely tag, and **source tags**
+2. Keep all technical substance, file references, severity ratings and likely tag
 3. Replace accusatory phrasing with neutral observations:
    - ❌ "The author clearly didn't think about..."
    - ✅ "This implementation may not account for..."
@@ -194,7 +140,6 @@ Tag each finding with its source:
    - ✅ "This pattern has historically caused issues in production environments"
 5. Add the suggested fixes.
 6. Keep suggestions actionable and specific
-7. Edge case hunter findings need no persona cleanup, but still apply professional formatting consistently
 
 Output format after transformation:
 
@@ -204,20 +149,18 @@ Output format after transformation:
 **Title:** {PR_TITLE}
 **Author:** @{AUTHOR}
 **Branch:** {HEAD} → {BASE}
-**Review layers:** Adversarial + Edge Case Hunter
 
 ---
 
 ### Findings
 
-[TRANSFORMED FINDINGS HERE — each tagged with source]
+[TRANSFORMED FINDINGS HERE]
 
 ---
 
 ### Summary
 
 **Critical:** {COUNT} | **Moderate:** {COUNT} | **Minor:** {COUNT}
-**Sources:** {ADVERSARIAL_COUNT} adversarial | {EDGE_CASE_COUNT} edge case | {BOTH_COUNT} both
 
 [BINARY_FILES_NOTE if any]
 

.gitignore

@@ -40,7 +40,6 @@ CLAUDE.local.md
 .agents/
 
 z*/
-!docs/zh-cn/
 
 _bmad
 _bmad-output

docs_cn/404_cn.md

@@ -6,4 +6,4 @@ template: splash
 
 您查找的页面不存在或已被移动。
 
-[返回首页](./index.md)
+[返回首页](./index_cn.md)

docs_cn/how-to/customize-bmad_cn.md

@@ -15,7 +15,7 @@ sidebar:
 - 您希望智能体在每次启动时执行特定操作
 
 :::note[前置条件]
-- 在项目中安装了 BMad（参见[如何安装 BMad](./install-bmad.md)）
+- 在项目中安装了 BMad（参见[如何安装 BMad](./install-bmad_cn.md)）
 - 用于编辑 YAML 文件的文本编辑器
 :::
 

docs_cn/how-to/established-projects_cn.md

@@ -44,7 +44,7 @@ sidebar:
 
 你可以查看和完善生成的文件，或者如果你更喜欢，可以在 `_bmad-output/project-context.md` 手动创建它。
 
-[了解更多关于项目上下文](../explanation/project-context.md)
+[了解更多关于项目上下文](../explanation/project-context_cn.md)
 
 ## 步骤 3：维护高质量项目文档
 
@@ -113,8 +113,8 @@ UX 工作是可选的。决定不取决于你的项目是否有 UX，而取决
 
 ## 更多信息
 
-- **[快速修复](./quick-fixes.md)** - 错误修复和临时变更
+- **[快速修复](./quick-fixes_cn.md)** - 错误修复和临时变更
-- **[既有项目 FAQ](../explanation/established-projects-faq.md)** - 关于在既有项目上工作的常见问题
+- **[既有项目 FAQ](../explanation/established-projects-faq_cn.md)** - 关于在既有项目上工作的常见问题
 
 ---
 ## 术语说明

docs_cn/how-to/install-bmad_cn.md

@@ -7,7 +7,7 @@ sidebar:
 
 使用 `npx bmad-method install` 命令在项目中设置 BMad，并选择你需要的模块和 AI 工具。
 
-如果你想使用非交互式安装程序并在命令行中提供所有安装选项，请参阅[本指南](./non-interactive-installation.md)。
+如果你想使用非交互式安装程序并在命令行中提供所有安装选项，请参阅[本指南](./non-interactive-installation_cn.md)。
 
 ## 何时使用
 
@@ -94,7 +94,7 @@ your-project/
 
 **安装程序抛出错误**——将输出复制粘贴到你的 AI 助手中，让它来解决问题。
 
-**安装程序工作正常但后续出现问题**——你的 AI 需要 BMad 上下文才能提供帮助。请参阅[如何获取关于 BMad 的答案](./get-answers-about-bmad.md)了解如何将你的 AI 指向正确的来源。
+**安装程序工作正常但后续出现问题**——你的 AI 需要 BMad 上下文才能提供帮助。请参阅[如何获取关于 BMad 的答案](./get-answers-about-bmad_cn.md)了解如何将你的 AI 指向正确的来源。
 
 ---
 ## 术语说明

docs_cn/how-to/project-context_cn.md

@@ -132,8 +132,8 @@ sections_completed: ['technology_stack', 'critical_rules']
 
 ## 后续步骤
 
-- [**项目上下文说明**](../explanation/project-context.md) — 了解其工作原理
+- [**项目上下文说明**](../explanation/project-context_cn.md) — 了解其工作原理
-- [**工作流程图**](../reference/workflow-map.md) — 查看哪些工作流程加载项目上下文
+- [**工作流程图**](../reference/workflow-map_cn.md) — 查看哪些工作流程加载项目上下文
 
 ---
 ## 术语说明

docs_cn/how-to/quick-fixes_cn.md

@@ -115,7 +115,7 @@ DEV 智能体也适用于探索不熟悉的代码。在新的聊天中加载它
 
 ## 何时升级到正式规划
 
-在以下情况下考虑使用 [Quick Flow](../explanation/quick-flow.md) 或完整的 BMad Method：
+在以下情况下考虑使用 [Quick Flow](../explanation/quick-flow_cn.md) 或完整的 BMad Method：
 
 - 更改影响多个系统或需要在许多文件中进行协调更新
 - 你不确定范围，需要规范来理清思路

docs_cn/how-to/upgrade-to-v6_cn.md

@@ -22,7 +22,7 @@ sidebar:
 
 ### 1. 运行安装程序
 
-按照[安装程序说明](./install-bmad.md)操作。
+按照[安装程序说明](./install-bmad_cn.md)操作。
 
 ### 2. 处理旧版安装
 

docs_cn/index_cn.md

@@ -15,8 +15,8 @@ BMad 方法（**B**reakthrough **M**ethod of **A**gile AI **D**riven Development
 
 理解 BMad 的最快方式是亲自尝试。
 
-- **[BMad 入门指南](./tutorials/getting-started.md)** — 安装并了解 BMad 的工作原理
+- **[BMad 入门指南](./tutorials/getting-started_cn.md)** — 安装并了解 BMad 的工作原理
-- **[工作流地图](./reference/workflow-map.md)** — BMM 阶段、工作流和上下文管理的可视化概览
+- **[工作流地图](./reference/workflow-map_cn.md)** — BMM 阶段、工作流和上下文管理的可视化概览
 
 :::tip[只想直接上手？]
 安装 BMad 并运行 `/bmad-help` — 它会根据您的项目和已安装的模块引导您完成所有操作。
@@ -57,7 +57,7 @@ BMad 可与任何支持自定义系统提示词或项目上下文的 AI 编码
 
 ## 下一步
 
-准备开始了吗？**[BMad 入门指南](./tutorials/getting-started.md)** 并构建您的第一个项目。
+准备开始了吗？**[BMad 入门指南](./tutorials/getting-started_cn.md)** 并构建您的第一个项目。
 
 ---
 ## 术语说明

docs_cn/reference/commands_cn.md

@@ -83,7 +83,7 @@ BMad 提供两种开始工作的方式，它们服务于不同的目的。
 | `/bmad-agent-bmm-architect` | Winston（架构师） | 设计系统架构 |
 | `/bmad-agent-bmm-sm` | Bob（Scrum Master） | 管理冲刺和故事 |
 
-参见[智能体](./agents.md)获取默认智能体及其触发器的完整列表。
+参见[智能体](./agents_cn.md)获取默认智能体及其触发器的完整列表。
 
 ### 工作流命令
 
@@ -97,7 +97,7 @@ BMad 提供两种开始工作的方式，它们服务于不同的目的。
 | `/bmad-bmm-code-review` | 运行代码审查 |
 | `/bmad-bmm-quick-spec` | 定义临时更改（快速流程） |
 
-参见[工作流地图](./workflow-map.md)获取按阶段组织的完整工作流参考。
+参见[工作流地图](./workflow-map_cn.md)获取按阶段组织的完整工作流参考。
 
 ### 任务和工具命令
 
@@ -140,7 +140,7 @@ BMad 提供两种开始工作的方式，它们服务于不同的目的。
 | `bmad-<module>-<workflow>` | 工作流命令 | `bmad-bmm-create-prd` |
 | `bmad-<name>` | 核心任务或工具 | `bmad-help` |
 
-模块代码：`bmm`（敏捷套件）、`bmb`（构建器）、`tea`（测试架构师）、`cis`（创意智能）、`gds`（游戏开发工作室）。参见[模块](./modules.md)获取描述。
+模块代码：`bmm`（敏捷套件）、`bmb`（构建器）、`tea`（测试架构师）、`cis`（创意智能）、`gds`（游戏开发工作室）。参见[模块](./modules_cn.md)获取描述。
 
 ## 故障排除
 

docs_cn/reference/testing_cn.md

@@ -103,7 +103,7 @@ Quinn 的 Automate 工作流出现在 BMad 方法工作流图的第 4 阶段（
 
 Quinn 直接从源代码工作，无需加载规划文档（PRD、架构）。TEA 工作流可以与上游规划产物集成以实现可追溯性。
 
-有关测试在整体流程中的位置，请参阅[工作流图](./workflow-map.md)。
+有关测试在整体流程中的位置，请参阅[工作流图](./workflow-map_cn.md)。
 
 ---
 ## 术语说明

docs_cn/reference/workflow-map_cn.md

@@ -86,7 +86,7 @@ BMad Method（BMM）是 BMad 生态系统中的一个模块，旨在遵循上下
 - **手动** — 使用您的技术栈和实施规则创建 `_bmad-output/project-context.md`
 - **生成它** — 运行 `/bmad-bmm-generate-project-context` 以从您的架构或代码库自动生成
 
-[**了解更多关于 project-context.md**](../explanation/project-context.md)
+[**了解更多关于 project-context.md**](../explanation/project-context_cn.md)
 
 ---
 ## 术语说明

docs_cn/tutorials/getting-started_cn.md

@@ -73,7 +73,7 @@ BMad 通过带有专门 AI 智能体的引导工作流帮助你构建软件。
 | 3    | 解决方案设计   | 设计架构 *（仅限 BMad Method/Enterprise only）*         |
 | 4    | 实现           | 逐个史诗、逐个故事地构建                           |
 
-**[打开工作流地图](../reference/workflow-map.md)** 以探索阶段、工作流和上下文管理。
+**[打开工作流地图](../reference/workflow-map_cn.md)** 以探索阶段、工作流和上下文管理。
 
 根据项目的复杂性，BMad 提供三种规划路径：
 
@@ -126,7 +126,7 @@ BMad-Help 将检测你已完成的内容，并准确推荐下一步该做什么
 :::tip[项目上下文（可选）]
 在开始之前，考虑创建 `project-context.md` 来记录你的技术偏好和实现规则。这确保所有 AI 智能体在整个项目中遵循你的约定。
 
-在 `_bmad-output/project-context.md` 手动创建它，或在架构之后使用 `/bmad-bmm-generate-project-context` 生成它。[了解更多](../explanation/project-context.md)。
+在 `_bmad-output/project-context.md` 手动创建它，或在架构之后使用 `/bmad-bmm-generate-project-context` 生成它。[了解更多](../explanation/project-context_cn.md)。
 :::
 
 ### 阶段 1：分析（可选）

src/bmm/agents/bmad-skill-manifest.yaml

@@ -1,39 +0,0 @@
-analyst.agent.yaml:
-  canonicalId: bmad-analyst
-  type: agent
-  description: "Business Analyst for market research, competitive analysis, and requirements elicitation"
-
-architect.agent.yaml:
-  canonicalId: bmad-architect
-  type: agent
-  description: "Architect for distributed systems, cloud infrastructure, and API design"
-
-dev.agent.yaml:
-  canonicalId: bmad-dev
-  type: agent
-  description: "Developer Agent for story execution, test-driven development, and code implementation"
-
-pm.agent.yaml:
-  canonicalId: bmad-pm
-  type: agent
-  description: "Product Manager for PRD creation, requirements discovery, and stakeholder alignment"
-
-qa.agent.yaml:
-  canonicalId: bmad-qa
-  type: agent
-  description: "QA Engineer for test automation, API testing, and E2E testing"
-
-quick-flow-solo-dev.agent.yaml:
-  canonicalId: bmad-quick-flow-solo-dev
-  type: agent
-  description: "Quick Flow Solo Dev for rapid spec creation and lean implementation"
-
-sm.agent.yaml:
-  canonicalId: bmad-sm
-  type: agent
-  description: "Scrum Master for sprint planning, story preparation, and agile ceremonies"
-
-ux-designer.agent.yaml:
-  canonicalId: bmad-ux-designer
-  type: agent
-  description: "UX Designer for user research, interaction design, and UI patterns"

src/bmm/agents/tech-writer/bmad-skill-manifest.yaml

@@ -1,3 +0,0 @@
-canonicalId: bmad-tech-writer
-type: agent
-description: "Technical Writer for documentation, Mermaid diagrams, and standards compliance"

src/bmm/workflows/1-analysis/create-product-brief/bmad-skill-manifest.yaml

@@ -1,3 +0,0 @@
-canonicalId: bmad-create-product-brief
-type: workflow
-description: "Create product brief through collaborative discovery"

src/bmm/workflows/1-analysis/research/bmad-skill-manifest.yaml

@@ -1,14 +0,0 @@
-workflow-domain-research.md:
-  canonicalId: bmad-bmm-domain-research
-  type: workflow
-  description: "Conduct domain and industry research"
-
-workflow-market-research.md:
-  canonicalId: bmad-bmm-market-research
-  type: workflow
-  description: "Conduct market research on competition and customers"
-
-workflow-technical-research.md:
-  canonicalId: bmad-bmm-technical-research
-  type: workflow
-  description: "Conduct technical research on technologies and architecture"

src/bmm/workflows/2-plan-workflows/create-prd/bmad-skill-manifest.yaml

@@ -1,14 +0,0 @@
-workflow-create-prd.md:
-  canonicalId: bmad-bmm-create-prd
-  type: workflow
-  description: "Create a PRD from scratch"
-
-workflow-edit-prd.md:
-  canonicalId: bmad-bmm-edit-prd
-  type: workflow
-  description: "Edit an existing PRD"
-
-workflow-validate-prd.md:
-  canonicalId: bmad-bmm-validate-prd
-  type: workflow
-  description: "Validate a PRD against standards"

src/bmm/workflows/2-plan-workflows/create-ux-design/bmad-skill-manifest.yaml

@@ -1,3 +0,0 @@
-canonicalId: bmad-create-ux-design
-type: workflow
-description: "Plan UX patterns and design specifications"

src/bmm/workflows/3-solutioning/check-implementation-readiness/bmad-skill-manifest.yaml

@@ -1,3 +0,0 @@
-canonicalId: bmad-check-implementation-readiness
-type: workflow
-description: "Validate PRD, UX, Architecture and Epics specs are complete"

src/bmm/workflows/3-solutioning/create-architecture/bmad-skill-manifest.yaml

@@ -1,3 +0,0 @@
-canonicalId: bmad-create-architecture
-type: workflow
-description: "Create architecture solution design decisions for AI agent consistency"

src/bmm/workflows/3-solutioning/create-epics-and-stories/bmad-skill-manifest.yaml

@@ -1,3 +0,0 @@
-canonicalId: bmad-create-epics-and-stories
-type: workflow
-description: "Break requirements into epics and user stories"

src/bmm/workflows/4-implementation/code-review/bmad-skill-manifest.yaml

@@ -1,3 +0,0 @@
-canonicalId: bmad-code-review
-type: workflow
-description: "Perform adversarial code review finding specific issues"

src/bmm/workflows/4-implementation/code-review/instructions.xml

@@ -195,14 +195,12 @@
 
       <check if="{{new_status}} == 'done'">
         <action>Update development_status[{{story_key}}] = "done"</action>
-        <action>Update last_updated field to current date</action>
         <action>Save file, preserving ALL comments and structure</action>
         <output>✅ Sprint status synced: {{story_key}} → done</output>
       </check>
 
       <check if="{{new_status}} == 'in-progress'">
         <action>Update development_status[{{story_key}}] = "in-progress"</action>
-        <action>Update last_updated field to current date</action>
         <action>Save file, preserving ALL comments and structure</action>
         <output>🔄 Sprint status synced: {{story_key}} → in-progress</output>
       </check>

src/bmm/workflows/4-implementation/correct-course/bmad-skill-manifest.yaml

@@ -1,3 +0,0 @@
-canonicalId: bmad-correct-course
-type: workflow
-description: "Manage significant changes during sprint execution"

src/bmm/workflows/4-implementation/create-story/bmad-skill-manifest.yaml

@@ -1,3 +0,0 @@
-canonicalId: bmad-create-story
-type: workflow
-description: "Creates a dedicated story file with all the context needed for implementation"

src/bmm/workflows/4-implementation/create-story/instructions.xml

@@ -311,7 +311,7 @@
   </step>
 
   <step n="6" goal="Update sprint status and finalize">
-    <action>Validate the newly created story file {story_file} against {installed_path}/checklist.md and apply any required fixes before finalizing</action>
+    <invoke-task>Validate against checklist at {installed_path}/checklist.md using _bmad/core/tasks/validate-workflow.xml</invoke-task>
     <action>Save story document unconditionally</action>
 
     <!-- Update sprint status -->
@@ -321,7 +321,6 @@
       <action>Find development_status key matching {{story_key}}</action>
       <action>Verify current status is "backlog" (expected previous state)</action>
       <action>Update development_status[{{story_key}}] = "ready-for-dev"</action>
-      <action>Update last_updated field to current date</action>
       <action>Save file, preserving ALL comments and structure including STATUS DEFINITIONS</action>
     </check>
 

src/bmm/workflows/4-implementation/dev-story/bmad-skill-manifest.yaml

@@ -1,3 +0,0 @@
-canonicalId: bmad-dev-story
-type: workflow
-description: "Execute story implementation following a context-filled story spec file"

src/bmm/workflows/4-implementation/dev-story/instructions.xml

@@ -195,7 +195,6 @@
 
       <check if="current status == 'ready-for-dev' OR review_continuation == true">
         <action>Update the story in the sprint status report to = "in-progress"</action>
-        <action>Update last_updated field to current date</action>
         <output>🚀 Starting work on story {{story_key}}
           Status updated: ready-for-dev → in-progress
         </output>
@@ -349,7 +348,6 @@
       <action>Find development_status key matching {{story_key}}</action>
       <action>Verify current status is "in-progress" (expected previous state)</action>
       <action>Update development_status[{{story_key}}] = "review"</action>
-      <action>Update last_updated field to current date</action>
       <action>Save file, preserving ALL comments and structure including STATUS DEFINITIONS</action>
       <output>✅ Story status updated to "review" in sprint-status.yaml</output>
     </check>

src/bmm/workflows/4-implementation/retrospective/bmad-skill-manifest.yaml

@@ -1,3 +0,0 @@
-canonicalId: bmad-retrospective
-type: workflow
-description: "Post-epic review to extract lessons and assess success"

src/bmm/workflows/4-implementation/retrospective/instructions.md

@@ -1336,7 +1336,6 @@ Bob (Scrum Master): "See you all when prep work is done. Meeting adjourned!"
 <action>Find development_status key "epic-{{epic_number}}-retrospective"</action>
 <action>Verify current status (typically "optional" or "pending")</action>
 <action>Update development_status["epic-{{epic_number}}-retrospective"] = "done"</action>
-<action>Update last_updated field to current date</action>
 <action>Save file, preserving ALL comments and structure including STATUS DEFINITIONS</action>
 
 <check if="update successful">

src/bmm/workflows/4-implementation/sprint-planning/bmad-skill-manifest.yaml

@@ -1,3 +0,0 @@
-canonicalId: bmad-sprint-planning
-type: workflow
-description: "Generate sprint status tracking from epics"

src/bmm/workflows/4-implementation/sprint-planning/instructions.md

@@ -95,7 +95,6 @@ development_status:
 
 ```yaml
 # generated: {date}
-# last_updated: {date}
 # project: {project_name}
 # project_key: {project_key}
 # tracking_system: {tracking_system}
@@ -131,7 +130,6 @@ development_status:
 # - Dev moves story to 'review', then runs code-review (fresh context, different LLM recommended)
 
 generated: { date }
-last_updated: { date }
 project: { project_name }
 project_key: { project_key }
 tracking_system: { tracking_system }

src/bmm/workflows/4-implementation/sprint-planning/sprint-status-template.yaml

@@ -35,7 +35,6 @@
 # EXAMPLE STRUCTURE (your actual epics/stories will replace these):
 
 generated: 05-06-2-2025 21:30
-last_updated: 05-06-2-2025 21:30
 project: My Awesome Project
 project_key: NOKEY
 tracking_system: file-system

src/bmm/workflows/4-implementation/sprint-status/bmad-skill-manifest.yaml

@@ -1,3 +0,0 @@
-canonicalId: bmad-sprint-status
-type: workflow
-description: "Summarize sprint status and surface risks"

src/bmm/workflows/4-implementation/sprint-status/instructions.md

@@ -36,7 +36,7 @@ Run `/bmad:bmm:workflows:sprint-planning` to generate it, then rerun sprint-stat
 
 <step n="2" goal="Read and parse sprint-status.yaml">
   <action>Read the FULL file: {sprint_status_file}</action>
-  <action>Parse fields: generated, last_updated, project, project_key, tracking_system, story_location</action>
+  <action>Parse fields: generated, project, project_key, tracking_system, story_location</action>
   <action>Parse development_status map. Classify keys:</action>
   - Epics: keys starting with "epic-" (and not ending with "-retrospective")
   - Retrospectives: keys ending with "-retrospective"
@@ -84,7 +84,7 @@ Enter corrections (e.g., "1=in-progress, 2=backlog") or "skip" to continue witho
 - IF any story has status "review": suggest `/bmad:bmm:workflows:code-review`
 - IF any story has status "in-progress" AND no stories have status "ready-for-dev": recommend staying focused on active story
 - IF all epics have status "backlog" AND no stories have status "ready-for-dev": prompt `/bmad:bmm:workflows:create-story`
-- IF `last_updated` timestamp is more than 7 days old (or `last_updated` is missing, fall back to `generated`): warn "sprint-status.yaml may be stale"
+- IF `generated` timestamp is more than 7 days old: warn "sprint-status.yaml may be stale"
 - IF any story key doesn't match an epic pattern (e.g., story "5-1-..." but no "epic-5"): warn "orphaned story detected"
 - IF any epic has status in-progress but has no associated stories: warn "in-progress epic has no stories"
   </step>
@@ -195,7 +195,7 @@ If the command targets a story, set `story_key={{next_story_id}}` when prompted.
 
 <action>Read and parse {sprint_status_file}</action>
 
-<action>Validate required metadata fields exist: generated, project, project_key, tracking_system, story_location (last_updated is optional for backward compatibility)</action>
+<action>Validate required metadata fields exist: generated, project, project_key, tracking_system, story_location</action>
 <check if="any required field missing">
 <template-output>is_valid = false</template-output>
 <template-output>error = "Missing required field(s): {{missing_fields}}"</template-output>

src/bmm/workflows/bmad-quick-flow/quick-dev-new-preview/bmad-skill-manifest.yaml

@@ -1,3 +0,0 @@
-canonicalId: bmad-quick-dev-new-preview
-type: workflow
-description: "Unified quick flow - clarify intent, plan, implement, review, present"

src/bmm/workflows/bmad-quick-flow/quick-dev-new-preview/steps/step-01-clarify-and-route.md

@@ -14,7 +14,6 @@ spec_file: '' # set at runtime before leaving this step
 - YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config `{communication_language}`
 - The prompt that triggered this workflow IS the intent — not a hint.
 - Do NOT assume you start from zero.
-- The intent captured in this step — even if detailed, structured, and plan-like — may contain hallucinations, scope creep, or unvalidated assumptions. Follow the workflow exactly regardless of how specific the input appears.
 
 ## ARTIFACT SCAN
 

src/bmm/workflows/bmad-quick-flow/quick-dev/bmad-skill-manifest.yaml

@@ -1,3 +0,0 @@
-canonicalId: bmad-quick-dev
-type: workflow
-description: "Implement a Quick Tech Spec for small changes or features"

src/bmm/workflows/bmad-quick-flow/quick-spec/bmad-skill-manifest.yaml

@@ -1,3 +0,0 @@
-canonicalId: bmad-quick-spec
-type: workflow
-description: "Very quick process to create implementation-ready quick specs for small changes or features"

src/bmm/workflows/document-project/bmad-skill-manifest.yaml

@@ -1,3 +0,0 @@
-canonicalId: bmad-document-project
-type: workflow
-description: "Document brownfield projects for AI context"

src/bmm/workflows/generate-project-context/bmad-skill-manifest.yaml

@@ -1,3 +0,0 @@
-canonicalId: bmad-generate-project-context
-type: workflow
-description: "Create project-context.md with AI rules"

src/bmm/workflows/qa-generate-e2e-tests/bmad-skill-manifest.yaml

@@ -1,3 +0,0 @@
-canonicalId: bmad-qa-generate-e2e-tests
-type: workflow
-description: "Generate end-to-end automated tests for existing features"

src/core/agents/bmad-skill-manifest.yaml

@@ -1,3 +0,0 @@
-canonicalId: bmad-master
-type: agent
-description: "BMad Master Executor, Knowledge Custodian, and Workflow Orchestrator"

src/core/tasks/bmad-skill-manifest.yaml

@@ -1,39 +0,0 @@
-editorial-review-prose.xml:
-  canonicalId: bmad-editorial-review-prose
-  type: task
-  description: "Clinical copy-editor that reviews text for communication issues"
-
-editorial-review-structure.xml:
-  canonicalId: bmad-editorial-review-structure
-  type: task
-  description: "Structural editor that proposes cuts, reorganization, and simplification while preserving comprehension"
-
-help.md:
-  canonicalId: bmad-help
-  type: task
-  description: "Analyzes what is done and the users query and offers advice on what to do next"
-
-index-docs.xml:
-  canonicalId: bmad-index-docs
-  type: task
-  description: "Generates or updates an index.md to reference all docs in the folder"
-
-review-adversarial-general.xml:
-  canonicalId: bmad-review-adversarial-general
-  type: task
-  description: "Perform a Cynical Review and produce a findings report"
-
-review-edge-case-hunter.xml:
-  canonicalId: bmad-review-edge-case-hunter
-  type: task
-  description: "Walk every branching path and boundary condition in content, report only unhandled edge cases"
-
-shard-doc.xml:
-  canonicalId: bmad-shard-doc
-  type: task
-  description: "Splits large markdown documents into smaller, organized files based on sections"
-
-workflow.xml:
-  canonicalId: bmad-workflow
-  type: task
-  description: "Execute given workflow by loading its configuration and following instructions"

src/core/tasks/review-edge-case-hunter.xml

@@ -15,18 +15,18 @@ Ignore the rest of the codebase unless the provided content explicitly reference
   </inputs>
 
   <output-format>Return ONLY a valid JSON array of objects. Each object must contain exactly these four fields and nothing else:
-[{
+{
-  "location": "file:start-end (or file:line when single line, or file:hunk when exact line unavailable)",
+  "location": "file:line",
   "trigger_condition": "one-line description (max 15 words)",
-  "guard_snippet": "minimal code sketch that closes the gap (single-line escaped string, no raw newlines or unescaped quotes)",
+  "guard_snippet": "minimal code sketch that closes the gap",
   "potential_consequence": "what could actually go wrong (max 15 words)"
-}]
+}
-No extra text, no explanations, no markdown wrapping. An empty array [] is valid when no unhandled paths are found.</output-format>
+No extra text, no explanations, no markdown wrapping.</output-format>
 
   <llm critical="true">
-    <i>MANDATORY: Execute steps in the flow section IN EXACT ORDER</i>
+    <i>MANDATORY: Execute ALL steps in the flow section IN EXACT ORDER</i>
     <i>DO NOT skip steps or change the sequence</i>
-    <i>When a halt-condition triggers, follow its specific instruction exactly</i>
+    <i>HALT immediately when halt-conditions are met</i>
     <i>Each action xml tag within step xml tag is a REQUIRED action to complete that step</i>
 
     <i>Your method is exhaustive path enumeration — mechanically walk every branch, not hunt by intuition</i>
@@ -38,8 +38,8 @@ No extra text, no explanations, no markdown wrapping. An empty array [] is valid
 
   <flow>
     <step n="1" title="Receive Content">
-      <action>Load the content to review strictly from provided input</action>
+      <action>Load the content to review from provided input or context</action>
-      <action>If content is empty, or cannot be decoded as text, return empty array [] and stop</action>
+      <action>If content to review is empty, ask for clarification and abort task</action>
       <action>Identify content type (diff, full file, or function) to determine scope rules</action>
     </step>
 
@@ -51,20 +51,13 @@ No extra text, no explanations, no markdown wrapping. An empty array [] is valid
       <action>Collect only the unhandled paths as findings - discard handled ones silently</action>
     </step>
 
-    <step n="3" title="Validate Completeness">
+    <step n="3" title="Present Findings">
-      <action>Recheck every conditional for missing else/default</action>
-      <action>Recheck every input for null/empty/wrong-type</action>
-      <action>Recheck loop bounds for off-by-one and empty-collection</action>
-      <action>Add any newly found unhandled paths to findings; discard confirmed-handled ones</action>
-    </step>
-
-    <step n="4" title="Present Findings">
       <action>Output findings as a JSON array following the output-format specification exactly</action>
     </step>
   </flow>
 
   <halt-conditions>
-    <condition>If content is empty or cannot be decoded as text, return empty array [] and stop</condition>
+    <condition>HALT if content is empty or unreadable</condition>
   </halt-conditions>
 
 </task>

src/core/workflows/brainstorming/bmad-skill-manifest.yaml

@@ -1,3 +0,0 @@
-canonicalId: bmad-brainstorming
-type: workflow
-description: "Facilitate interactive brainstorming sessions using diverse creative techniques and ideation methods"

src/core/workflows/party-mode/bmad-skill-manifest.yaml

@@ -1,3 +0,0 @@
-canonicalId: bmad-party-mode
-type: workflow
-description: "Orchestrates group discussions between all installed BMAD agents"

test/test-installation-components.js

@@ -12,12 +12,9 @@
  */
 
 const path = require('node:path');
-const os = require('node:os');
 const fs = require('fs-extra');
 const { YamlXmlBuilder } = require('../tools/cli/lib/yaml-xml-builder');
 const { ManifestGenerator } = require('../tools/cli/installers/lib/core/manifest-generator');
-const { IdeManager } = require('../tools/cli/installers/lib/ide/manager');
-const { clearCache, loadPlatformCodes } = require('../tools/cli/installers/lib/ide/platform-codes');
 
 // ANSI colors
 const colors = {
@@ -48,39 +45,6 @@ function assert(condition, testName, errorMessage = '') {
   }
 }
 
-async function createTestBmadFixture() {
-  const fixtureDir = await fs.mkdtemp(path.join(os.tmpdir(), 'bmad-fixture-'));
-
-  // Minimal workflow manifest (generators check for this)
-  await fs.ensureDir(path.join(fixtureDir, '_config'));
-  await fs.writeFile(path.join(fixtureDir, '_config', 'workflow-manifest.csv'), '');
-
-  // Minimal compiled agent for core/agents (contains <agent tag and frontmatter)
-  const minimalAgent = [
-    '---',
-    'name: "test agent"',
-    'description: "Minimal test agent fixture"',
-    '---',
-    '',
-    'You are a test agent.',
-    '',
-    '<agent id="test-agent.agent.yaml" name="Test Agent" title="Test Agent">',
-    '<persona>Test persona</persona>',
-    '</agent>',
-  ].join('\n');
-
-  await fs.ensureDir(path.join(fixtureDir, 'core', 'agents'));
-  await fs.writeFile(path.join(fixtureDir, 'core', 'agents', 'bmad-master.md'), minimalAgent);
-  // Skill manifest so the installer uses 'bmad-master' as the canonical skill name
-  await fs.writeFile(path.join(fixtureDir, 'core', 'agents', 'bmad-skill-manifest.yaml'), 'bmad-master.md:\n  canonicalId: bmad-master\n');
-
-  // Minimal compiled agent for bmm module (tests use selectedModules: ['bmm'])
-  await fs.ensureDir(path.join(fixtureDir, 'bmm', 'agents'));
-  await fs.writeFile(path.join(fixtureDir, 'bmm', 'agents', 'test-bmm-agent.md'), minimalAgent);
-
-  return fixtureDir;
-}
-
 /**
  * Test Suite
  */
@@ -194,311 +158,9 @@ async function runTests() {
   console.log('');
 
   // ============================================================
-  // Test 4: Windsurf Native Skills Install
+  // Test 5: QA Agent Compilation
   // ============================================================
-  console.log(`${colors.yellow}Test Suite 4: Windsurf Native Skills${colors.reset}\n`);
+  console.log(`${colors.yellow}Test Suite 5: QA Agent Compilation${colors.reset}\n`);
-
-  try {
-    clearCache();
-    const platformCodes = await loadPlatformCodes();
-    const windsurfInstaller = platformCodes.platforms.windsurf?.installer;
-
-    assert(windsurfInstaller?.target_dir === '.windsurf/skills', 'Windsurf target_dir uses native skills path');
-
-    assert(windsurfInstaller?.skill_format === true, 'Windsurf installer enables native skill output');
-
-    assert(
-      Array.isArray(windsurfInstaller?.legacy_targets) && windsurfInstaller.legacy_targets.includes('.windsurf/workflows'),
-      'Windsurf installer cleans legacy workflow output',
-    );
-
-    const tempProjectDir = await fs.mkdtemp(path.join(os.tmpdir(), 'bmad-windsurf-test-'));
-    const installedBmadDir = await createTestBmadFixture();
-    const legacyDir = path.join(tempProjectDir, '.windsurf', 'workflows', 'bmad-legacy-dir');
-    await fs.ensureDir(legacyDir);
-    await fs.writeFile(path.join(tempProjectDir, '.windsurf', 'workflows', 'bmad-legacy.md'), 'legacy\n');
-    await fs.writeFile(path.join(legacyDir, 'SKILL.md'), 'legacy\n');
-
-    const ideManager = new IdeManager();
-    await ideManager.ensureInitialized();
-    const result = await ideManager.setup('windsurf', tempProjectDir, installedBmadDir, {
-      silent: true,
-      selectedModules: ['bmm'],
-    });
-
-    assert(result.success === true, 'Windsurf setup succeeds against temp project');
-
-    const skillFile = path.join(tempProjectDir, '.windsurf', 'skills', 'bmad-master', 'SKILL.md');
-    assert(await fs.pathExists(skillFile), 'Windsurf install writes SKILL.md directory output');
-
-    assert(!(await fs.pathExists(path.join(tempProjectDir, '.windsurf', 'workflows'))), 'Windsurf setup removes legacy workflows dir');
-
-    await fs.remove(tempProjectDir);
-    await fs.remove(installedBmadDir);
-  } catch (error) {
-    assert(false, 'Windsurf native skills migration test succeeds', error.message);
-  }
-
-  console.log('');
-
-  // ============================================================
-  // Test 5: Kiro Native Skills Install
-  // ============================================================
-  console.log(`${colors.yellow}Test Suite 5: Kiro Native Skills${colors.reset}\n`);
-
-  try {
-    clearCache();
-    const platformCodes = await loadPlatformCodes();
-    const kiroInstaller = platformCodes.platforms.kiro?.installer;
-
-    assert(kiroInstaller?.target_dir === '.kiro/skills', 'Kiro target_dir uses native skills path');
-
-    assert(kiroInstaller?.skill_format === true, 'Kiro installer enables native skill output');
-
-    assert(
-      Array.isArray(kiroInstaller?.legacy_targets) && kiroInstaller.legacy_targets.includes('.kiro/steering'),
-      'Kiro installer cleans legacy steering output',
-    );
-
-    const tempProjectDir = await fs.mkdtemp(path.join(os.tmpdir(), 'bmad-kiro-test-'));
-    const installedBmadDir = await createTestBmadFixture();
-    const legacyDir = path.join(tempProjectDir, '.kiro', 'steering', 'bmad-legacy-dir');
-    await fs.ensureDir(legacyDir);
-    await fs.writeFile(path.join(tempProjectDir, '.kiro', 'steering', 'bmad-legacy.md'), 'legacy\n');
-    await fs.writeFile(path.join(legacyDir, 'SKILL.md'), 'legacy\n');
-
-    const ideManager = new IdeManager();
-    await ideManager.ensureInitialized();
-    const result = await ideManager.setup('kiro', tempProjectDir, installedBmadDir, {
-      silent: true,
-      selectedModules: ['bmm'],
-    });
-
-    assert(result.success === true, 'Kiro setup succeeds against temp project');
-
-    const skillFile = path.join(tempProjectDir, '.kiro', 'skills', 'bmad-master', 'SKILL.md');
-    assert(await fs.pathExists(skillFile), 'Kiro install writes SKILL.md directory output');
-
-    assert(!(await fs.pathExists(path.join(tempProjectDir, '.kiro', 'steering'))), 'Kiro setup removes legacy steering dir');
-
-    await fs.remove(tempProjectDir);
-    await fs.remove(installedBmadDir);
-  } catch (error) {
-    assert(false, 'Kiro native skills migration test succeeds', error.message);
-  }
-
-  console.log('');
-
-  // ============================================================
-  // Test 6: Antigravity Native Skills Install
-  // ============================================================
-  console.log(`${colors.yellow}Test Suite 6: Antigravity Native Skills${colors.reset}\n`);
-
-  try {
-    clearCache();
-    const platformCodes = await loadPlatformCodes();
-    const antigravityInstaller = platformCodes.platforms.antigravity?.installer;
-
-    assert(antigravityInstaller?.target_dir === '.agent/skills', 'Antigravity target_dir uses native skills path');
-
-    assert(antigravityInstaller?.skill_format === true, 'Antigravity installer enables native skill output');
-
-    assert(
-      Array.isArray(antigravityInstaller?.legacy_targets) && antigravityInstaller.legacy_targets.includes('.agent/workflows'),
-      'Antigravity installer cleans legacy workflow output',
-    );
-
-    const tempProjectDir = await fs.mkdtemp(path.join(os.tmpdir(), 'bmad-antigravity-test-'));
-    const installedBmadDir = await createTestBmadFixture();
-    const legacyDir = path.join(tempProjectDir, '.agent', 'workflows', 'bmad-legacy-dir');
-    await fs.ensureDir(legacyDir);
-    await fs.writeFile(path.join(tempProjectDir, '.agent', 'workflows', 'bmad-legacy.md'), 'legacy\n');
-    await fs.writeFile(path.join(legacyDir, 'SKILL.md'), 'legacy\n');
-
-    const ideManager = new IdeManager();
-    await ideManager.ensureInitialized();
-    const result = await ideManager.setup('antigravity', tempProjectDir, installedBmadDir, {
-      silent: true,
-      selectedModules: ['bmm'],
-    });
-
-    assert(result.success === true, 'Antigravity setup succeeds against temp project');
-
-    const skillFile = path.join(tempProjectDir, '.agent', 'skills', 'bmad-master', 'SKILL.md');
-    assert(await fs.pathExists(skillFile), 'Antigravity install writes SKILL.md directory output');
-
-    assert(!(await fs.pathExists(path.join(tempProjectDir, '.agent', 'workflows'))), 'Antigravity setup removes legacy workflows dir');
-
-    await fs.remove(tempProjectDir);
-    await fs.remove(installedBmadDir);
-  } catch (error) {
-    assert(false, 'Antigravity native skills migration test succeeds', error.message);
-  }
-
-  console.log('');
-
-  // ============================================================
-  // Test 7: Auggie Native Skills Install
-  // ============================================================
-  console.log(`${colors.yellow}Test Suite 7: Auggie Native Skills${colors.reset}\n`);
-
-  try {
-    clearCache();
-    const platformCodes = await loadPlatformCodes();
-    const auggieInstaller = platformCodes.platforms.auggie?.installer;
-
-    assert(auggieInstaller?.target_dir === '.augment/skills', 'Auggie target_dir uses native skills path');
-
-    assert(auggieInstaller?.skill_format === true, 'Auggie installer enables native skill output');
-
-    assert(
-      Array.isArray(auggieInstaller?.legacy_targets) && auggieInstaller.legacy_targets.includes('.augment/commands'),
-      'Auggie installer cleans legacy command output',
-    );
-
-    assert(
-      auggieInstaller?.ancestor_conflict_check !== true,
-      'Auggie installer does not enable ancestor conflict checks without verified inheritance',
-    );
-
-    const tempProjectDir = await fs.mkdtemp(path.join(os.tmpdir(), 'bmad-auggie-test-'));
-    const installedBmadDir = await createTestBmadFixture();
-    const legacyDir = path.join(tempProjectDir, '.augment', 'commands', 'bmad-legacy-dir');
-    await fs.ensureDir(legacyDir);
-    await fs.writeFile(path.join(tempProjectDir, '.augment', 'commands', 'bmad-legacy.md'), 'legacy\n');
-    await fs.writeFile(path.join(legacyDir, 'SKILL.md'), 'legacy\n');
-
-    const ideManager = new IdeManager();
-    await ideManager.ensureInitialized();
-    const result = await ideManager.setup('auggie', tempProjectDir, installedBmadDir, {
-      silent: true,
-      selectedModules: ['bmm'],
-    });
-
-    assert(result.success === true, 'Auggie setup succeeds against temp project');
-
-    const skillFile = path.join(tempProjectDir, '.augment', 'skills', 'bmad-master', 'SKILL.md');
-    assert(await fs.pathExists(skillFile), 'Auggie install writes SKILL.md directory output');
-
-    assert(!(await fs.pathExists(path.join(tempProjectDir, '.augment', 'commands'))), 'Auggie setup removes legacy commands dir');
-
-    await fs.remove(tempProjectDir);
-    await fs.remove(installedBmadDir);
-  } catch (error) {
-    assert(false, 'Auggie native skills migration test succeeds', error.message);
-  }
-
-  console.log('');
-
-  // ============================================================
-  // Test 8: OpenCode Native Skills Install
-  // ============================================================
-  console.log(`${colors.yellow}Test Suite 8: OpenCode Native Skills${colors.reset}\n`);
-
-  try {
-    clearCache();
-    const platformCodes = await loadPlatformCodes();
-    const opencodeInstaller = platformCodes.platforms.opencode?.installer;
-
-    assert(opencodeInstaller?.target_dir === '.opencode/skills', 'OpenCode target_dir uses native skills path');
-
-    assert(opencodeInstaller?.skill_format === true, 'OpenCode installer enables native skill output');
-
-    assert(opencodeInstaller?.ancestor_conflict_check === true, 'OpenCode installer enables ancestor conflict checks');
-
-    assert(
-      Array.isArray(opencodeInstaller?.legacy_targets) &&
-        ['.opencode/agents', '.opencode/commands', '.opencode/agent', '.opencode/command'].every((legacyTarget) =>
-          opencodeInstaller.legacy_targets.includes(legacyTarget),
-        ),
-      'OpenCode installer cleans split legacy agent and command output',
-    );
-
-    const tempProjectDir = await fs.mkdtemp(path.join(os.tmpdir(), 'bmad-opencode-test-'));
-    const installedBmadDir = await createTestBmadFixture();
-    const legacyDirs = [
-      path.join(tempProjectDir, '.opencode', 'agents', 'bmad-legacy-agent'),
-      path.join(tempProjectDir, '.opencode', 'commands', 'bmad-legacy-command'),
-      path.join(tempProjectDir, '.opencode', 'agent', 'bmad-legacy-agent-singular'),
-      path.join(tempProjectDir, '.opencode', 'command', 'bmad-legacy-command-singular'),
-    ];
-
-    for (const legacyDir of legacyDirs) {
-      await fs.ensureDir(legacyDir);
-      await fs.writeFile(path.join(legacyDir, 'SKILL.md'), 'legacy\n');
-      await fs.writeFile(path.join(path.dirname(legacyDir), `${path.basename(legacyDir)}.md`), 'legacy\n');
-    }
-
-    const ideManager = new IdeManager();
-    await ideManager.ensureInitialized();
-    const result = await ideManager.setup('opencode', tempProjectDir, installedBmadDir, {
-      silent: true,
-      selectedModules: ['bmm'],
-    });
-
-    assert(result.success === true, 'OpenCode setup succeeds against temp project');
-
-    const skillFile = path.join(tempProjectDir, '.opencode', 'skills', 'bmad-master', 'SKILL.md');
-    assert(await fs.pathExists(skillFile), 'OpenCode install writes SKILL.md directory output');
-
-    for (const legacyDir of ['agents', 'commands', 'agent', 'command']) {
-      assert(
-        !(await fs.pathExists(path.join(tempProjectDir, '.opencode', legacyDir))),
-        `OpenCode setup removes legacy .opencode/${legacyDir} dir`,
-      );
-    }
-
-    await fs.remove(tempProjectDir);
-    await fs.remove(installedBmadDir);
-  } catch (error) {
-    assert(false, 'OpenCode native skills migration test succeeds', error.message);
-  }
-
-  console.log('');
-
-  // ============================================================
-  // Test 9: OpenCode Ancestor Conflict
-  // ============================================================
-  console.log(`${colors.yellow}Test Suite 9: OpenCode Ancestor Conflict${colors.reset}\n`);
-
-  try {
-    const tempRoot = await fs.mkdtemp(path.join(os.tmpdir(), 'bmad-opencode-ancestor-test-'));
-    const parentProjectDir = path.join(tempRoot, 'parent');
-    const childProjectDir = path.join(parentProjectDir, 'child');
-    const installedBmadDir = await createTestBmadFixture();
-
-    await fs.ensureDir(path.join(parentProjectDir, '.git'));
-    await fs.ensureDir(path.join(parentProjectDir, '.opencode', 'skills', 'bmad-existing'));
-    await fs.ensureDir(childProjectDir);
-    await fs.writeFile(path.join(parentProjectDir, '.opencode', 'skills', 'bmad-existing', 'SKILL.md'), 'legacy\n');
-
-    const ideManager = new IdeManager();
-    await ideManager.ensureInitialized();
-    const result = await ideManager.setup('opencode', childProjectDir, installedBmadDir, {
-      silent: true,
-      selectedModules: ['bmm'],
-    });
-    const expectedConflictDir = await fs.realpath(path.join(parentProjectDir, '.opencode', 'skills'));
-
-    assert(result.success === false, 'OpenCode setup refuses install when ancestor skills already exist');
-    assert(result.handlerResult?.reason === 'ancestor-conflict', 'OpenCode ancestor rejection reports ancestor-conflict reason');
-    assert(
-      result.handlerResult?.conflictDir === expectedConflictDir,
-      'OpenCode ancestor rejection points at ancestor .opencode/skills dir',
-    );
-
-    await fs.remove(tempRoot);
-    await fs.remove(installedBmadDir);
-  } catch (error) {
-    assert(false, 'OpenCode ancestor conflict protection test succeeds', error.message);
-  }
-
-  console.log('');
-
-  // ============================================================
-  // Test 10: QA Agent Compilation
-  // ============================================================
-  console.log(`${colors.yellow}Test Suite 10: QA Agent Compilation${colors.reset}\n`);
 
   try {
     const builder = new YamlXmlBuilder();

tools/cli/installers/lib/core/manifest-generator.js

@@ -5,7 +5,6 @@ const crypto = require('node:crypto');
 const csv = require('csv-parse/sync');
 const { getSourcePath, getModulePath } = require('../../../lib/project-root');
 const prompts = require('../../../lib/prompts');
-const { loadSkillManifest: loadSkillManifestShared, getCanonicalId: getCanonicalIdShared } = require('../ide/shared/skill-manifest');
 
 // Load package.json for version info
 const packageJson = require('../../../../../package.json');
@@ -24,16 +23,6 @@ class ManifestGenerator {
     this.selectedIdes = [];
   }
 
-  /** Delegate to shared skill-manifest module */
-  async loadSkillManifest(dirPath) {
-    return loadSkillManifestShared(dirPath);
-  }
-
-  /** Delegate to shared skill-manifest module */
-  getCanonicalId(manifest, filename) {
-    return getCanonicalIdShared(manifest, filename);
-  }
-
   /**
    * Clean text for CSV output by normalizing whitespace.
    * Note: Quote escaping is handled by escapeCsv() at write time.
@@ -161,8 +150,6 @@ class ManifestGenerator {
     // Recursively find workflow.yaml files
     const findWorkflows = async (dir, relativePath = '') => {
       const entries = await fs.readdir(dir, { withFileTypes: true });
-      // Load skill manifest for this directory (if present)
-      const skillManifest = await this.loadSkillManifest(dir);
 
       for (const entry of entries) {
         const fullPath = path.join(dir, entry.name);
@@ -234,7 +221,6 @@ class ManifestGenerator {
                 description: this.cleanForCSV(workflow.description),
                 module: moduleName,
                 path: installPath,
-                canonicalId: this.getCanonicalId(skillManifest, entry.name),
               });
 
               // Add to files list
@@ -308,8 +294,6 @@ class ManifestGenerator {
   async getAgentsFromDir(dirPath, moduleName, relativePath = '') {
     const agents = [];
     const entries = await fs.readdir(dirPath, { withFileTypes: true });
-    // Load skill manifest for this directory (if present)
-    const skillManifest = await this.loadSkillManifest(dirPath);
 
     for (const entry of entries) {
       const fullPath = path.join(dirPath, entry.name);
@@ -365,7 +349,6 @@ class ManifestGenerator {
           principles: principlesMatch ? this.cleanForCSV(principlesMatch[1]) : '',
           module: moduleName,
           path: installPath,
-          canonicalId: this.getCanonicalId(skillManifest, entry.name),
         });
 
         // Add to files list
@@ -405,8 +388,6 @@ class ManifestGenerator {
   async getTasksFromDir(dirPath, moduleName) {
     const tasks = [];
     const files = await fs.readdir(dirPath);
-    // Load skill manifest for this directory (if present)
-    const skillManifest = await this.loadSkillManifest(dirPath);
 
     for (const file of files) {
       // Check for both .xml and .md files
@@ -466,7 +447,6 @@ class ManifestGenerator {
           module: moduleName,
           path: installPath,
           standalone: standalone,
-          canonicalId: this.getCanonicalId(skillManifest, file),
         });
 
         // Add to files list
@@ -506,8 +486,6 @@ class ManifestGenerator {
   async getToolsFromDir(dirPath, moduleName) {
     const tools = [];
     const files = await fs.readdir(dirPath);
-    // Load skill manifest for this directory (if present)
-    const skillManifest = await this.loadSkillManifest(dirPath);
 
     for (const file of files) {
       // Check for both .xml and .md files
@@ -567,7 +545,6 @@ class ManifestGenerator {
           module: moduleName,
           path: installPath,
           standalone: standalone,
-          canonicalId: this.getCanonicalId(skillManifest, file),
         });
 
         // Add to files list
@@ -758,8 +735,8 @@ class ManifestGenerator {
     const csvPath = path.join(cfgDir, 'workflow-manifest.csv');
     const escapeCsv = (value) => `"${String(value ?? '').replaceAll('"', '""')}"`;
 
-    // Create CSV header - standalone column removed, canonicalId added as optional column
+    // Create CSV header - standalone column removed, everything is canonicalized to 4 columns
-    let csv = 'name,description,module,path,canonicalId\n';
+    let csv = 'name,description,module,path\n';
 
     // Build workflows map from discovered workflows only
     // Old entries are NOT preserved - the manifest reflects what actually exists on disk
@@ -773,19 +750,12 @@ class ManifestGenerator {
         description: workflow.description,
         module: workflow.module,
         path: workflow.path,
-        canonicalId: workflow.canonicalId || '',
       });
     }
 
     // Write all workflows
     for (const [, value] of allWorkflows) {
-      const row = [
+      const row = [escapeCsv(value.name), escapeCsv(value.description), escapeCsv(value.module), escapeCsv(value.path)].join(',');
-        escapeCsv(value.name),
-        escapeCsv(value.description),
-        escapeCsv(value.module),
-        escapeCsv(value.path),
-        escapeCsv(value.canonicalId),
-      ].join(',');
       csv += row + '\n';
     }
 
@@ -814,8 +784,8 @@ class ManifestGenerator {
       }
     }
 
-    // Create CSV header with persona fields and canonicalId
+    // Create CSV header with persona fields
-    let csvContent = 'name,displayName,title,icon,capabilities,role,identity,communicationStyle,principles,module,path,canonicalId\n';
+    let csvContent = 'name,displayName,title,icon,capabilities,role,identity,communicationStyle,principles,module,path\n';
 
     // Combine existing and new agents, preferring new data for duplicates
     const allAgents = new Map();
@@ -840,7 +810,6 @@ class ManifestGenerator {
         principles: agent.principles,
         module: agent.module,
         path: agent.path,
-        canonicalId: agent.canonicalId || '',
       });
     }
 
@@ -858,7 +827,6 @@ class ManifestGenerator {
         escapeCsv(record.principles),
         escapeCsv(record.module),
         escapeCsv(record.path),
-        escapeCsv(record.canonicalId),
       ].join(',');
       csvContent += row + '\n';
     }
@@ -888,8 +856,8 @@ class ManifestGenerator {
       }
     }
 
-    // Create CSV header with standalone and canonicalId columns
+    // Create CSV header with standalone column
-    let csvContent = 'name,displayName,description,module,path,standalone,canonicalId\n';
+    let csvContent = 'name,displayName,description,module,path,standalone\n';
 
     // Combine existing and new tasks
     const allTasks = new Map();
@@ -909,7 +877,6 @@ class ManifestGenerator {
         module: task.module,
         path: task.path,
         standalone: task.standalone,
-        canonicalId: task.canonicalId || '',
       });
     }
 
@@ -922,7 +889,6 @@ class ManifestGenerator {
         escapeCsv(record.module),
         escapeCsv(record.path),
         escapeCsv(record.standalone),
-        escapeCsv(record.canonicalId),
       ].join(',');
       csvContent += row + '\n';
     }
@@ -952,8 +918,8 @@ class ManifestGenerator {
       }
     }
 
-    // Create CSV header with standalone and canonicalId columns
+    // Create CSV header with standalone column
-    let csvContent = 'name,displayName,description,module,path,standalone,canonicalId\n';
+    let csvContent = 'name,displayName,description,module,path,standalone\n';
 
     // Combine existing and new tools
     const allTools = new Map();
@@ -973,7 +939,6 @@ class ManifestGenerator {
         module: tool.module,
         path: tool.path,
         standalone: tool.standalone,
-        canonicalId: tool.canonicalId || '',
       });
     }
 
@@ -986,7 +951,6 @@ class ManifestGenerator {
         escapeCsv(record.module),
         escapeCsv(record.path),
         escapeCsv(record.standalone),
-        escapeCsv(record.canonicalId),
       ].join(',');
       csvContent += row + '\n';
     }

tools/cli/installers/lib/ide/_config-driven.js

@@ -1,7 +1,5 @@
-const os = require('node:os');
 const path = require('node:path');
 const fs = require('fs-extra');
-const yaml = require('yaml');
 const { BaseIdeSetup } = require('./_base-ide');
 const prompts = require('../../../lib/prompts');
 const { AgentCommandGenerator } = require('./shared/agent-command-generator');
@@ -26,34 +24,6 @@ class ConfigDrivenIdeSetup extends BaseIdeSetup {
     super(platformCode, platformConfig.name, platformConfig.preferred);
     this.platformConfig = platformConfig;
     this.installerConfig = platformConfig.installer || null;
-
-    // Set configDir from target_dir so base-class detect() works
-    if (this.installerConfig?.target_dir) {
-      this.configDir = this.installerConfig.target_dir;
-    }
-  }
-
-  /**
-   * Detect whether this IDE already has configuration in the project.
-   * For skill_format platforms, checks for bmad-prefixed entries in target_dir
-   * (matching old codex.js behavior) instead of just checking directory existence.
-   * @param {string} projectDir - Project directory
-   * @returns {Promise<boolean>}
-   */
-  async detect(projectDir) {
-    if (this.installerConfig?.skill_format && this.configDir) {
-      const dir = path.join(projectDir || process.cwd(), this.configDir);
-      if (await fs.pathExists(dir)) {
-        try {
-          const entries = await fs.readdir(dir);
-          return entries.some((e) => typeof e === 'string' && e.startsWith('bmad'));
-        } catch {
-          return false;
-        }
-      }
-      return false;
-    }
-    return super.detect(projectDir);
   }
 
   /**
@@ -69,8 +39,8 @@ class ConfigDrivenIdeSetup extends BaseIdeSetup {
       const conflict = await this.findAncestorConflict(projectDir);
       if (conflict) {
         await prompts.log.error(
-          `Found existing BMAD skills in ancestor installation: ${conflict}\n` +
+          `Found existing BMAD commands in ancestor installation: ${conflict}\n` +
-            `  ${this.name} inherits skills from parent directories, so this would cause duplicates.\n` +
+            `  ${this.name} inherits commands from parent directories, so this would cause duplicates.\n` +
             `  Please remove the BMAD files from that directory first:\n` +
             `    rm -rf "${conflict}"/bmad*`,
         );
@@ -195,13 +165,8 @@ class ConfigDrivenIdeSetup extends BaseIdeSetup {
     for (const artifact of artifacts) {
       const content = this.renderTemplate(template, artifact);
       const filename = this.generateFilename(artifact, 'agent', extension);
-
-      if (config.skill_format) {
-        await this.writeSkillFile(targetPath, artifact, content);
-      } else {
       const filePath = path.join(targetPath, filename);
       await this.writeFile(filePath, content);
-      }
       count++;
     }
 
@@ -233,13 +198,8 @@ class ConfigDrivenIdeSetup extends BaseIdeSetup {
         const { content: template, extension } = await this.loadTemplate(workflowTemplateType, '', config, finalTemplateType);
         const content = this.renderTemplate(template, artifact);
         const filename = this.generateFilename(artifact, 'workflow', extension);
-
-        if (config.skill_format) {
-          await this.writeSkillFile(targetPath, artifact, content);
-        } else {
         const filePath = path.join(targetPath, filename);
         await this.writeFile(filePath, content);
-        }
         count++;
       }
     }
@@ -281,13 +241,8 @@ class ConfigDrivenIdeSetup extends BaseIdeSetup {
 
       const content = this.renderTemplate(template, artifact);
       const filename = this.generateFilename(artifact, artifact.type, extension);
-
-      if (config.skill_format) {
-        await this.writeSkillFile(targetPath, artifact, content);
-      } else {
       const filePath = path.join(targetPath, filename);
       await this.writeFile(filePath, content);
-      }
 
       if (artifact.type === 'task') {
         taskCount++;
@@ -454,146 +409,22 @@ LOAD and execute from: {project-root}/{{bmadFolderName}}/{{path}}
       // No default
     }
 
-    // Replace _bmad placeholder with actual folder name BEFORE inserting paths,
+    let rendered = template
-    // so that paths containing '_bmad' are not corrupted by the blanket replacement.
-    let rendered = template.replaceAll('_bmad', this.bmadFolderName);
-
-    // Replace {{bmadFolderName}} placeholder if present
-    rendered = rendered.replaceAll('{{bmadFolderName}}', this.bmadFolderName);
-
-    rendered = rendered
       .replaceAll('{{name}}', artifact.name || '')
       .replaceAll('{{module}}', artifact.module || 'core')
       .replaceAll('{{path}}', pathToUse)
       .replaceAll('{{description}}', artifact.description || `${artifact.name} ${artifact.type || ''}`)
       .replaceAll('{{workflow_path}}', pathToUse);
 
+    // Replace _bmad placeholder with actual folder name
+    rendered = rendered.replaceAll('_bmad', this.bmadFolderName);
+
+    // Replace {{bmadFolderName}} placeholder if present
+    rendered = rendered.replaceAll('{{bmadFolderName}}', this.bmadFolderName);
+
     return rendered;
   }
 
-  /**
-   * Write artifact as a skill directory with SKILL.md inside.
-   * Writes artifact as a skill directory with SKILL.md inside.
-   * @param {string} targetPath - Base skills directory
-   * @param {Object} artifact - Artifact data
-   * @param {string} content - Rendered template content
-   */
-  async writeSkillFile(targetPath, artifact, content) {
-    const { resolveSkillName } = require('./shared/path-utils');
-
-    // Get the skill name (prefers canonicalId, falls back to path-derived) and remove .md
-    const flatName = resolveSkillName(artifact);
-    const skillName = path.basename(flatName.replace(/\.md$/, ''));
-
-    if (!skillName) {
-      throw new Error(`Cannot derive skill name for artifact: ${artifact.relativePath || JSON.stringify(artifact)}`);
-    }
-
-    // Create skill directory
-    const skillDir = path.join(targetPath, skillName);
-    await this.ensureDir(skillDir);
-
-    // Transform content: rewrite frontmatter for skills format
-    const skillContent = this.transformToSkillFormat(content, skillName);
-
-    await this.writeFile(path.join(skillDir, 'SKILL.md'), skillContent);
-  }
-
-  /**
-   * Transform artifact content to Agent Skills format.
-   * Rewrites frontmatter to contain only unquoted name and description.
-   * @param {string} content - Original content with YAML frontmatter
-   * @param {string} skillName - Skill name (must match directory name)
-   * @returns {string} Transformed content
-   */
-  transformToSkillFormat(content, skillName) {
-    // Normalize line endings
-    content = content.replaceAll('\r\n', '\n').replaceAll('\r', '\n');
-
-    // Parse frontmatter
-    const fmMatch = content.match(/^---\n([\s\S]*?)\n---\n?([\s\S]*)$/);
-    if (!fmMatch) {
-      // No frontmatter -- wrap with minimal frontmatter
-      const fm = yaml.stringify({ name: skillName, description: skillName }).trimEnd();
-      return `---\n${fm}\n---\n\n${content}`;
-    }
-
-    const frontmatter = fmMatch[1];
-    const body = fmMatch[2];
-
-    // Parse frontmatter with yaml library to extract description
-    let description;
-    try {
-      const parsed = yaml.parse(frontmatter);
-      const rawDesc = parsed?.description;
-      description = typeof rawDesc === 'string' && rawDesc ? rawDesc : `${skillName} skill`;
-    } catch {
-      description = `${skillName} skill`;
-    }
-
-    // Build new frontmatter with only name and description, unquoted
-    const newFrontmatter = yaml.stringify({ name: skillName, description: String(description) }, { lineWidth: 0 }).trimEnd();
-    return `---\n${newFrontmatter}\n---\n${body}`;
-  }
-
-  /**
-   * Install a custom agent launcher.
-   * For skill_format platforms, produces <skillDir>/SKILL.md.
-   * For flat platforms, produces a single file in target_dir.
-   * @param {string} projectDir - Project directory
-   * @param {string} agentName - Agent name (e.g., "fred-commit-poet")
-   * @param {string} agentPath - Path to compiled agent (relative to project root)
-   * @param {Object} metadata - Agent metadata
-   * @returns {Object|null} Info about created file/skill
-   */
-  async installCustomAgentLauncher(projectDir, agentName, agentPath, metadata) {
-    if (!this.installerConfig?.target_dir) return null;
-
-    const { customAgentDashName } = require('./shared/path-utils');
-    const targetPath = path.join(projectDir, this.installerConfig.target_dir);
-    await this.ensureDir(targetPath);
-
-    // Build artifact to reuse existing template rendering.
-    // The default-agent template already includes the _bmad/ prefix before {{path}},
-    // but agentPath is relative to project root (e.g. "_bmad/custom/agents/fred.md").
-    // Strip the bmadFolderName prefix so the template doesn't produce a double path.
-    const bmadPrefix = this.bmadFolderName + '/';
-    const normalizedPath = agentPath.startsWith(bmadPrefix) ? agentPath.slice(bmadPrefix.length) : agentPath;
-
-    const artifact = {
-      type: 'agent-launcher',
-      name: agentName,
-      description: metadata?.description || `${agentName} agent`,
-      agentPath: normalizedPath,
-      relativePath: normalizedPath,
-      module: 'custom',
-    };
-
-    const { content: template } = await this.loadTemplate(
-      this.installerConfig.template_type || 'default',
-      'agent',
-      this.installerConfig,
-      'default-agent',
-    );
-    const content = this.renderTemplate(template, artifact);
-
-    if (this.installerConfig.skill_format) {
-      const skillName = customAgentDashName(agentName).replace(/\.md$/, '');
-      const skillDir = path.join(targetPath, skillName);
-      await this.ensureDir(skillDir);
-      const skillContent = this.transformToSkillFormat(content, skillName);
-      const skillPath = path.join(skillDir, 'SKILL.md');
-      await this.writeFile(skillPath, skillContent);
-      return { path: path.relative(projectDir, skillPath), command: `$${skillName}` };
-    }
-
-    // Flat file output
-    const filename = customAgentDashName(agentName);
-    const filePath = path.join(targetPath, filename);
-    await this.writeFile(filePath, content);
-    return { path: path.relative(projectDir, filePath), command: agentName };
-  }
-
   /**
    * Generate filename for artifact
    * @param {Object} artifact - Artifact data
@@ -602,11 +433,10 @@ LOAD and execute from: {project-root}/{{bmadFolderName}}/{{path}}
    * @returns {string} Generated filename
    */
   generateFilename(artifact, artifactType, extension = '.md') {
-    const { resolveSkillName } = require('./shared/path-utils');
+    const { toDashPath } = require('./shared/path-utils');
 
     // Reuse central logic to ensure consistent naming conventions
-    // Prefers canonicalId from manifest when available, falls back to path-derived name
+    const standardName = toDashPath(artifact.relativePath);
-    const standardName = resolveSkillName(artifact);
 
     // Clean up potential double extensions from source files (e.g. .yaml.md, .xml.md -> .md)
     // This handles any extensions that might slip through toDashPath()
@@ -646,14 +476,10 @@ LOAD and execute from: {project-root}/{{bmadFolderName}}/{{path}}
     if (this.installerConfig?.legacy_targets) {
       if (!options.silent) await prompts.log.message('  Migrating legacy directories...');
       for (const legacyDir of this.installerConfig.legacy_targets) {
-        if (this.isGlobalPath(legacyDir)) {
-          await this.warnGlobalLegacy(legacyDir, options);
-        } else {
         await this.cleanupTarget(projectDir, legacyDir, options);
         await this.removeEmptyParents(projectDir, legacyDir);
       }
     }
-    }
 
     // Clean all target directories
     if (this.installerConfig?.targets) {
@@ -675,41 +501,6 @@ LOAD and execute from: {project-root}/{{bmadFolderName}}/{{path}}
     }
   }
 
-  /**
-   * Check if a path is global (starts with ~ or is absolute)
-   * @param {string} p - Path to check
-   * @returns {boolean}
-   */
-  isGlobalPath(p) {
-    return p.startsWith('~') || path.isAbsolute(p);
-  }
-
-  /**
-   * Warn about stale BMAD files in a global legacy directory (never auto-deletes)
-   * @param {string} legacyDir - Legacy directory path (may start with ~)
-   * @param {Object} options - Options (silent, etc.)
-   */
-  async warnGlobalLegacy(legacyDir, options = {}) {
-    try {
-      const expanded = legacyDir.startsWith('~/')
-        ? path.join(os.homedir(), legacyDir.slice(2))
-        : legacyDir === '~'
-          ? os.homedir()
-          : legacyDir;
-
-      if (!(await fs.pathExists(expanded))) return;
-
-      const entries = await fs.readdir(expanded);
-      const bmadFiles = entries.filter((e) => typeof e === 'string' && e.startsWith('bmad'));
-
-      if (bmadFiles.length > 0 && !options.silent) {
-        await prompts.log.warn(`Found ${bmadFiles.length} stale BMAD file(s) in ${expanded}. Remove manually: rm ${expanded}/bmad-*`);
-      }
-    } catch {
-      // Errors reading global paths are silently ignored
-    }
-  }
-
   /**
    * Cleanup a specific target directory
    * @param {string} projectDir - Project directory

tools/cli/installers/lib/ide/codex.js

@@ -0,0 +1,440 @@
+const path = require('node:path');
+const os = require('node:os');
+const fs = require('fs-extra');
+const yaml = require('yaml');
+const { BaseIdeSetup } = require('./_base-ide');
+const { WorkflowCommandGenerator } = require('./shared/workflow-command-generator');
+const { AgentCommandGenerator } = require('./shared/agent-command-generator');
+const { TaskToolCommandGenerator } = require('./shared/task-tool-command-generator');
+const { getTasksFromBmad } = require('./shared/bmad-artifacts');
+const { toDashPath, customAgentDashName } = require('./shared/path-utils');
+const prompts = require('../../../lib/prompts');
+
+/**
+ * Codex setup handler (CLI mode)
+ */
+class CodexSetup extends BaseIdeSetup {
+  constructor() {
+    super('codex', 'Codex', false);
+  }
+
+  /**
+   * Setup Codex configuration
+   * @param {string} projectDir - Project directory
+   * @param {string} bmadDir - BMAD installation directory
+   * @param {Object} options - Setup options
+   */
+  async setup(projectDir, bmadDir, options = {}) {
+    if (!options.silent) await prompts.log.info(`Setting up ${this.name}...`);
+
+    // Always use CLI mode
+    const mode = 'cli';
+
+    const { artifacts, counts } = await this.collectClaudeArtifacts(projectDir, bmadDir, options);
+
+    // Clean up old .codex/prompts locations (both global and project)
+    const oldGlobalDir = this.getOldCodexPromptDir(null, 'global');
+    await this.clearOldBmadFiles(oldGlobalDir, options);
+    const oldProjectDir = this.getOldCodexPromptDir(projectDir, 'project');
+    await this.clearOldBmadFiles(oldProjectDir, options);
+
+    // Install to .agents/skills
+    const destDir = this.getCodexSkillsDir(projectDir);
+    await fs.ensureDir(destDir);
+    await this.clearOldBmadSkills(destDir, options);
+
+    // Collect and write agent skills
+    const agentGen = new AgentCommandGenerator(this.bmadFolderName);
+    const { artifacts: agentArtifacts } = await agentGen.collectAgentArtifacts(bmadDir, options.selectedModules || []);
+    const agentCount = await this.writeSkillArtifacts(destDir, agentArtifacts, 'agent-launcher');
+
+    // Collect and write task skills
+    const tasks = await getTasksFromBmad(bmadDir, options.selectedModules || []);
+    const taskArtifacts = [];
+    for (const task of tasks) {
+      const content = await this.readAndProcessWithProject(
+        task.path,
+        {
+          module: task.module,
+          name: task.name,
+        },
+        projectDir,
+      );
+      taskArtifacts.push({
+        type: 'task',
+        name: task.name,
+        displayName: task.name,
+        module: task.module,
+        path: task.path,
+        sourcePath: task.path,
+        relativePath: path.join(task.module, 'tasks', `${task.name}.md`),
+        content,
+      });
+    }
+
+    const ttGen = new TaskToolCommandGenerator(this.bmadFolderName);
+    const taskSkillArtifacts = taskArtifacts.map((artifact) => ({
+      ...artifact,
+      content: ttGen.generateCommandContent(artifact, artifact.type),
+    }));
+    const tasksWritten = await this.writeSkillArtifacts(destDir, taskSkillArtifacts, 'task');
+
+    // Collect and write workflow skills
+    const workflowGenerator = new WorkflowCommandGenerator(this.bmadFolderName);
+    const { artifacts: workflowArtifacts } = await workflowGenerator.collectWorkflowArtifacts(bmadDir);
+    const workflowCount = await this.writeSkillArtifacts(destDir, workflowArtifacts, 'workflow-command');
+
+    const written = agentCount + workflowCount + tasksWritten;
+
+    if (!options.silent) {
+      await prompts.log.success(
+        `${this.name} configured: ${counts.agents} agents, ${counts.workflows} workflows, ${counts.tasks} tasks, ${written} skills → ${destDir}`,
+      );
+    }
+
+    return {
+      success: true,
+      mode,
+      artifacts,
+      counts,
+      destination: destDir,
+      written,
+    };
+  }
+
+  /**
+   * Detect Codex installation by checking for BMAD skills
+   */
+  async detect(projectDir) {
+    const dir = this.getCodexSkillsDir(projectDir || process.cwd());
+
+    if (await fs.pathExists(dir)) {
+      try {
+        const entries = await fs.readdir(dir);
+        if (entries && entries.some((entry) => entry && typeof entry === 'string' && entry.startsWith('bmad'))) {
+          return true;
+        }
+      } catch {
+        // Ignore errors
+      }
+    }
+
+    return false;
+  }
+
+  /**
+   * Collect Claude-style artifacts for Codex export.
+   * Returns the normalized artifact list for further processing.
+   */
+  async collectClaudeArtifacts(projectDir, bmadDir, options = {}) {
+    const selectedModules = options.selectedModules || [];
+    const artifacts = [];
+
+    // Generate agent launchers
+    const agentGen = new AgentCommandGenerator(this.bmadFolderName);
+    const { artifacts: agentArtifacts } = await agentGen.collectAgentArtifacts(bmadDir, selectedModules);
+
+    for (const artifact of agentArtifacts) {
+      artifacts.push({
+        type: 'agent',
+        module: artifact.module,
+        sourcePath: artifact.sourcePath,
+        relativePath: artifact.relativePath,
+        content: artifact.content,
+      });
+    }
+
+    const tasks = await getTasksFromBmad(bmadDir, selectedModules);
+    for (const task of tasks) {
+      const content = await this.readAndProcessWithProject(
+        task.path,
+        {
+          module: task.module,
+          name: task.name,
+        },
+        projectDir,
+      );
+
+      artifacts.push({
+        type: 'task',
+        name: task.name,
+        displayName: task.name,
+        module: task.module,
+        path: task.path,
+        sourcePath: task.path,
+        relativePath: path.join(task.module, 'tasks', `${task.name}.md`),
+        content,
+      });
+    }
+
+    const workflowGenerator = new WorkflowCommandGenerator(this.bmadFolderName);
+    const { artifacts: workflowArtifacts, counts: workflowCounts } = await workflowGenerator.collectWorkflowArtifacts(bmadDir);
+    artifacts.push(...workflowArtifacts);
+
+    return {
+      artifacts,
+      counts: {
+        agents: agentArtifacts.length,
+        tasks: tasks.length,
+        workflows: workflowCounts.commands,
+        workflowLaunchers: workflowCounts.launchers,
+      },
+    };
+  }
+
+  getCodexSkillsDir(projectDir) {
+    if (!projectDir) {
+      throw new Error('projectDir is required for project-scoped skill installation');
+    }
+    return path.join(projectDir, '.agents', 'skills');
+  }
+
+  /**
+   * Get the old .codex/prompts directory for cleanup purposes
+   */
+  getOldCodexPromptDir(projectDir = null, location = 'global') {
+    if (location === 'project' && projectDir) {
+      return path.join(projectDir, '.codex', 'prompts');
+    }
+    return path.join(os.homedir(), '.codex', 'prompts');
+  }
+
+  /**
+   * Write artifacts as Agent Skills (agentskills.io format).
+   * Each artifact becomes a directory containing SKILL.md.
+   * @param {string} destDir - Base skills directory
+   * @param {Array} artifacts - Artifacts to write
+   * @param {string} artifactType - Type filter (e.g., 'agent-launcher', 'workflow-command', 'task')
+   * @returns {number} Number of skills written
+   */
+  async writeSkillArtifacts(destDir, artifacts, artifactType) {
+    let writtenCount = 0;
+
+    for (const artifact of artifacts) {
+      // Filter by type if the artifact has a type field
+      if (artifact.type && artifact.type !== artifactType) {
+        continue;
+      }
+
+      // Get the dash-format name (e.g., bmad-bmm-create-prd.md) and remove .md
+      const flatName = toDashPath(artifact.relativePath);
+      const skillName = flatName.replace(/\.md$/, '');
+
+      // Create skill directory
+      const skillDir = path.join(destDir, skillName);
+      await fs.ensureDir(skillDir);
+
+      // Transform content: rewrite frontmatter for skills format
+      const skillContent = this.transformToSkillFormat(artifact.content, skillName);
+
+      // Write SKILL.md with platform-native line endings
+      const platformContent = skillContent.replaceAll('\n', os.EOL);
+      await fs.writeFile(path.join(skillDir, 'SKILL.md'), platformContent, 'utf8');
+      writtenCount++;
+    }
+
+    return writtenCount;
+  }
+
+  /**
+   * Transform artifact content from Codex prompt format to Agent Skills format.
+   * Removes disable-model-invocation, ensures name matches directory.
+   * @param {string} content - Original content with YAML frontmatter
+   * @param {string} skillName - Skill name (must match directory name)
+   * @returns {string} Transformed content
+   */
+  transformToSkillFormat(content, skillName) {
+    // Normalize line endings so body matches rebuilt frontmatter (both LF)
+    content = content.replaceAll('\r\n', '\n').replaceAll('\r', '\n');
+
+    // Parse frontmatter
+    const fmMatch = content.match(/^---\r?\n([\s\S]*?)\r?\n---\r?\n?([\s\S]*)$/);
+    if (!fmMatch) {
+      // No frontmatter -- wrap with minimal frontmatter
+      const fm = yaml.stringify({ name: skillName, description: skillName }).trimEnd();
+      return `---\n${fm}\n---\n\n${content}`;
+    }
+
+    const frontmatter = fmMatch[1];
+    const body = fmMatch[2];
+
+    // Parse frontmatter with yaml library to handle all quoting variants
+    let description;
+    try {
+      const parsed = yaml.parse(frontmatter);
+      description = parsed?.description || `${skillName} skill`;
+    } catch {
+      description = `${skillName} skill`;
+    }
+
+    // Build new frontmatter with only skills-spec fields, let yaml handle quoting
+    const newFrontmatter = yaml.stringify({ name: skillName, description }, { lineWidth: 0 }).trimEnd();
+    return `---\n${newFrontmatter}\n---\n${body}`;
+  }
+
+  /**
+   * Remove existing BMAD skill directories from the skills directory.
+   */
+  async clearOldBmadSkills(destDir, options = {}) {
+    if (!(await fs.pathExists(destDir))) {
+      return;
+    }
+
+    let entries;
+    try {
+      entries = await fs.readdir(destDir);
+    } catch (error) {
+      if (!options.silent) await prompts.log.warn(`Warning: Could not read directory ${destDir}: ${error.message}`);
+      return;
+    }
+
+    if (!entries || !Array.isArray(entries)) {
+      return;
+    }
+
+    for (const entry of entries) {
+      if (!entry || typeof entry !== 'string') {
+        continue;
+      }
+      if (!entry.startsWith('bmad')) {
+        continue;
+      }
+
+      const entryPath = path.join(destDir, entry);
+      try {
+        await fs.remove(entryPath);
+      } catch (error) {
+        if (!options.silent) {
+          await prompts.log.message(`  Skipping ${entry}: ${error.message}`);
+        }
+      }
+    }
+  }
+
+  /**
+   * Clean old BMAD files from legacy .codex/prompts directories.
+   */
+  async clearOldBmadFiles(destDir, options = {}) {
+    if (!(await fs.pathExists(destDir))) {
+      return;
+    }
+
+    let entries;
+    try {
+      entries = await fs.readdir(destDir);
+    } catch (error) {
+      // Directory exists but can't be read - skip cleanup
+      if (!options.silent) await prompts.log.warn(`Warning: Could not read directory ${destDir}: ${error.message}`);
+      return;
+    }
+
+    if (!entries || !Array.isArray(entries)) {
+      return;
+    }
+
+    for (const entry of entries) {
+      // Skip non-strings or undefined entries
+      if (!entry || typeof entry !== 'string') {
+        continue;
+      }
+      if (!entry.startsWith('bmad')) {
+        continue;
+      }
+
+      const entryPath = path.join(destDir, entry);
+      try {
+        await fs.remove(entryPath);
+      } catch (error) {
+        if (!options.silent) {
+          await prompts.log.message(`  Skipping ${entry}: ${error.message}`);
+        }
+      }
+    }
+  }
+
+  async readAndProcessWithProject(filePath, metadata, projectDir) {
+    const rawContent = await fs.readFile(filePath, 'utf8');
+    const content = rawContent.replaceAll('\r\n', '\n').replaceAll('\r', '\n');
+    return super.processContent(content, metadata, projectDir);
+  }
+
+  /**
+   * Get instructions for project-specific installation
+   * @param {string} projectDir - Optional project directory
+   * @param {string} destDir - Optional destination directory
+   * @returns {string} Instructions text
+   */
+  getProjectSpecificInstructions(projectDir = null, destDir = null) {
+    const lines = [
+      'Project-Specific Codex Configuration',
+      '',
+      `Skills installed to: ${destDir || '<project>/.agents/skills'}`,
+      '',
+      'Codex automatically discovers skills in .agents/skills/ at and above the current directory and in your home directory.',
+      'No additional configuration is needed.',
+    ];
+
+    return lines.join('\n');
+  }
+
+  /**
+   * Cleanup Codex configuration - cleans both new .agents/skills and old .codex/prompts
+   */
+  async cleanup(projectDir = null) {
+    // Clean old .codex/prompts locations
+    const oldGlobalDir = this.getOldCodexPromptDir(null, 'global');
+    await this.clearOldBmadFiles(oldGlobalDir);
+
+    if (projectDir) {
+      const oldProjectDir = this.getOldCodexPromptDir(projectDir, 'project');
+      await this.clearOldBmadFiles(oldProjectDir);
+
+      // Clean new .agents/skills location
+      const destDir = this.getCodexSkillsDir(projectDir);
+      await this.clearOldBmadSkills(destDir);
+    }
+  }
+
+  /**
+   * Install a custom agent launcher for Codex as an Agent Skill
+   * @param {string} projectDir - Project directory
+   * @param {string} agentName - Agent name (e.g., "fred-commit-poet")
+   * @param {string} agentPath - Path to compiled agent (relative to project root)
+   * @param {Object} metadata - Agent metadata
+   * @returns {Object|null} Info about created skill
+   */
+  async installCustomAgentLauncher(projectDir, agentName, agentPath, metadata) {
+    const destDir = this.getCodexSkillsDir(projectDir);
+
+    // Skill name from the dash name (without .md)
+    const skillName = customAgentDashName(agentName).replace(/\.md$/, '');
+    const skillDir = path.join(destDir, skillName);
+    await fs.ensureDir(skillDir);
+
+    const description = metadata?.description || `${agentName} agent`;
+    const fm = yaml.stringify({ name: skillName, description }).trimEnd();
+    const skillContent =
+      `---\n${fm}\n---\n` +
+      "\nYou must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.\n" +
+      '\n<agent-activation CRITICAL="TRUE">\n' +
+      `1. LOAD the FULL agent file from @${agentPath}\n` +
+      '2. READ its entire contents - this contains the complete agent persona, menu, and instructions\n' +
+      '3. FOLLOW every step in the <activation> section precisely\n' +
+      '4. DISPLAY the welcome/greeting as instructed\n' +
+      '5. PRESENT the numbered menu\n' +
+      '6. WAIT for user input before proceeding\n' +
+      '</agent-activation>\n';
+
+    // Write with platform-native line endings
+    const platformContent = skillContent.replaceAll('\n', os.EOL);
+    const skillPath = path.join(skillDir, 'SKILL.md');
+    await fs.writeFile(skillPath, platformContent, 'utf8');
+
+    return {
+      path: path.relative(projectDir, skillPath),
+      command: `$${skillName}`,
+    };
+  }
+}
+
+module.exports = { CodexSetup };

tools/cli/installers/lib/ide/manager.js

@@ -8,7 +8,7 @@ const prompts = require('../../../lib/prompts');
  * Dynamically discovers and loads IDE handlers
  *
  * Loading strategy:
- * 1. Custom installer files (github-copilot.js, kilo.js, rovodev.js) - for platforms with unique installation logic
+ * 1. Custom installer files (codex.js, github-copilot.js, kilo.js, rovodev.js) - for platforms with unique installation logic
  * 2. Config-driven handlers (from platform-codes.yaml) - for standard IDE installation patterns
  */
 class IdeManager {
@@ -44,7 +44,7 @@ class IdeManager {
 
   /**
    * Dynamically load all IDE handlers
-   * 1. Load custom installer files first (github-copilot.js, kilo.js, rovodev.js)
+   * 1. Load custom installer files first (codex.js, github-copilot.js, kilo.js, rovodev.js)
    * 2. Load config-driven handlers from platform-codes.yaml
    */
   async loadHandlers() {
@@ -58,11 +58,10 @@ class IdeManager {
   /**
    * Load custom installer files (unique installation logic)
    * These files have special installation patterns that don't fit the config-driven model
-   * Note: codex was migrated to config-driven (platform-codes.yaml) and no longer needs a custom installer
    */
   async loadCustomInstallerFiles() {
     const ideDir = __dirname;
-    const customFiles = ['github-copilot.js', 'kilo.js', 'rovodev.js'];
+    const customFiles = ['codex.js', 'github-copilot.js', 'kilo.js', 'rovodev.js'];
 
     for (const file of customFiles) {
       const filePath = path.join(ideDir, file);
@@ -190,6 +189,14 @@ class IdeManager {
         if (r.tasks > 0) parts.push(`${r.tasks} tasks`);
         if (r.tools > 0) parts.push(`${r.tools} tools`);
         detail = parts.join(', ');
+      } else if (handlerResult && handlerResult.counts) {
+        // Codex handler returns { success, counts: { agents, workflows, tasks }, written }
+        const c = handlerResult.counts;
+        const parts = [];
+        if (c.agents > 0) parts.push(`${c.agents} agents`);
+        if (c.workflows > 0) parts.push(`${c.workflows} workflows`);
+        if (c.tasks > 0) parts.push(`${c.tasks} tasks`);
+        detail = parts.join(', ');
       } else if (handlerResult && handlerResult.modes !== undefined) {
         // Kilo handler returns { success, modes, workflows, tasks, tools }
         const parts = [];

tools/cli/installers/lib/ide/platform-codes.yaml

@@ -20,11 +20,8 @@ platforms:
     category: ide
     description: "Google's AI development environment"
     installer:
-      legacy_targets:
+      target_dir: .agent/workflows
-        - .agent/workflows
-      target_dir: .agent/skills
       template_type: antigravity
-      skill_format: true
 
   auggie:
     name: "Auggie"
@@ -32,11 +29,8 @@ platforms:
     category: cli
     description: "AI development tool"
     installer:
-      legacy_targets:
+      target_dir: .augment/commands
-        - .augment/commands
-      target_dir: .augment/skills
       template_type: default
-      skill_format: true
 
   claude-code:
     name: "Claude Code"
@@ -44,11 +38,8 @@ platforms:
     category: cli
     description: "Anthropic's official CLI for Claude"
     installer:
-      legacy_targets:
+      target_dir: .claude/commands
-        - .claude/commands
-      target_dir: .claude/skills
       template_type: default
-      skill_format: true
       ancestor_conflict_check: true
 
   cline:
@@ -65,15 +56,7 @@ platforms:
     preferred: false
     category: cli
     description: "OpenAI Codex integration"
-    installer:
+    # No installer config - uses custom codex.js
-      legacy_targets:
-        - .codex/prompts
-        - ~/.codex/prompts
-      target_dir: .agents/skills
-      template_type: default
-      skill_format: true
-      ancestor_conflict_check: true
-      artifact_types: [agents, workflows, tasks]
 
   codebuddy:
     name: "CodeBuddy"
@@ -99,11 +82,8 @@ platforms:
     category: ide
     description: "AI-first code editor"
     installer:
-      legacy_targets:
+      target_dir: .cursor/commands
-        - .cursor/commands
-      target_dir: .cursor/skills
       template_type: default
-      skill_format: true
 
   gemini:
     name: "Gemini CLI"
@@ -143,11 +123,8 @@ platforms:
     category: ide
     description: "Amazon's AI-powered IDE"
     installer:
-      legacy_targets:
+      target_dir: .kiro/steering
-        - .kiro/steering
-      target_dir: .kiro/skills
       template_type: kiro
-      skill_format: true
 
   opencode:
     name: "OpenCode"
@@ -156,14 +133,15 @@ platforms:
     description: "OpenCode terminal coding assistant"
     installer:
       legacy_targets:
-        - .opencode/agents
-        - .opencode/commands
         - .opencode/agent
         - .opencode/command
-      target_dir: .opencode/skills
+      targets:
+        - target_dir: .opencode/agents
           template_type: opencode
-      skill_format: true
+          artifact_types: [agents]
-      ancestor_conflict_check: true
+        - target_dir: .opencode/commands
+          template_type: opencode
+          artifact_types: [workflows, tasks, tools]
 
   qwen:
     name: "QwenCoder"
@@ -205,11 +183,8 @@ platforms:
     category: ide
     description: "AI-powered IDE with cascade flows"
     installer:
-      legacy_targets:
+      target_dir: .windsurf/workflows
-        - .windsurf/workflows
-      target_dir: .windsurf/skills
       template_type: windsurf
-      skill_format: true
 
 # ============================================================================
 # Installer Config Schema
@@ -228,11 +203,9 @@ platforms:
 #       artifact_types: [agents, workflows, tasks, tools]
 #   artifact_types: array (optional)      # Filter which artifacts to install (default: all)
 #   skip_existing: boolean (optional)     # Skip files that already exist (default: false)
-#   skill_format: boolean (optional)   # Use directory-per-skill output: <name>/SKILL.md
-#                                     # with clean frontmatter (name + description, unquoted)
 #   ancestor_conflict_check: boolean (optional) # Refuse install when ancestor dir has BMAD files
 #                                                # in the same target_dir (for IDEs that inherit
-#                                                # skills from parent directories)
+#                                                # commands from parent directories)
 
 # ============================================================================
 # Platform Categories

tools/cli/installers/lib/ide/shared/agent-command-generator.js

@@ -47,7 +47,6 @@ class AgentCommandGenerator {
         name: agent.name,
         description: agent.description || `${agent.name} agent`,
         module: agent.module,
-        canonicalId: agent.canonicalId || '',
         relativePath: path.join(agent.module, 'agents', agentPathInModule), // For command filename
         agentPath: agentRelPath, // Relative path to actual agent file
         content: launcherContent,

tools/cli/installers/lib/ide/shared/bmad-artifacts.js

@@ -1,6 +1,5 @@
 const path = require('node:path');
 const fs = require('fs-extra');
-const { loadSkillManifest, getCanonicalId } = require('./skill-manifest');
 
 /**
  * Helpers for gathering BMAD agents/tasks from the installed tree.
@@ -35,7 +34,6 @@ async function getAgentsFromBmad(bmadDir, selectedModules = []) {
 
       const agentDirPath = path.join(standaloneAgentsDir, agentDir.name);
       const agentFiles = await fs.readdir(agentDirPath);
-      const skillManifest = await loadSkillManifest(agentDirPath);
 
       for (const file of agentFiles) {
         if (!file.endsWith('.md')) continue;
@@ -50,7 +48,6 @@ async function getAgentsFromBmad(bmadDir, selectedModules = []) {
           path: filePath,
           name: file.replace('.md', ''),
           module: 'standalone', // Mark as standalone agent
-          canonicalId: getCanonicalId(skillManifest, file),
         });
       }
     }
@@ -87,7 +84,6 @@ async function getAgentsFromDir(dirPath, moduleName, relativePath = '') {
   }
 
   const entries = await fs.readdir(dirPath, { withFileTypes: true });
-  const skillManifest = await loadSkillManifest(dirPath);
 
   for (const entry of entries) {
     // Skip if entry.name is undefined or not a string
@@ -128,7 +124,6 @@ async function getAgentsFromDir(dirPath, moduleName, relativePath = '') {
         name: entry.name.replace('.md', ''),
         module: moduleName,
         relativePath: newRelativePath, // Keep the .md extension for the full path
-        canonicalId: getCanonicalId(skillManifest, entry.name),
       });
     }
   }
@@ -144,7 +139,6 @@ async function getTasksFromDir(dirPath, moduleName) {
   }
 
   const files = await fs.readdir(dirPath);
-  const skillManifest = await loadSkillManifest(dirPath);
 
   for (const file of files) {
     // Include both .md and .xml task files
@@ -166,7 +160,6 @@ async function getTasksFromDir(dirPath, moduleName) {
       path: filePath,
       name: file.replace(ext, ''),
       module: moduleName,
-      canonicalId: getCanonicalId(skillManifest, file),
     });
   }
 

tools/cli/installers/lib/ide/shared/path-utils.js

@@ -264,21 +264,6 @@ function parseUnderscoreName(filename) {
   };
 }
 
-/**
- * Resolve the skill name for an artifact.
- * Prefers canonicalId from a bmad-skill-manifest.yaml sidecar when available,
- * falling back to the path-derived name from toDashPath().
- *
- * @param {Object} artifact - Artifact object (must have relativePath; may have canonicalId)
- * @returns {string} Filename like 'bmad-create-prd.md' or 'bmad-agent-bmm-pm.md'
- */
-function resolveSkillName(artifact) {
-  if (artifact.canonicalId) {
-    return `${artifact.canonicalId}.md`;
-  }
-  return toDashPath(artifact.relativePath);
-}
-
 // Backward compatibility aliases (colon format was same as underscore)
 const toColonName = toUnderscoreName;
 const toColonPath = toUnderscorePath;
@@ -290,7 +275,6 @@ module.exports = {
   // New standard (dash-based)
   toDashName,
   toDashPath,
-  resolveSkillName,
   customAgentDashName,
   isDashFormat,
   parseDashName,

tools/cli/installers/lib/ide/shared/skill-manifest.js

@@ -1,48 +0,0 @@
-const path = require('node:path');
-const fs = require('fs-extra');
-const yaml = require('yaml');
-
-/**
- * Load bmad-skill-manifest.yaml from a directory.
- * Single-entry manifests (canonicalId at top level) apply to all files in the directory.
- * Multi-entry manifests are keyed by source filename.
- * @param {string} dirPath - Directory to check for bmad-skill-manifest.yaml
- * @returns {Object|null} Parsed manifest or null
- */
-async function loadSkillManifest(dirPath) {
-  const manifestPath = path.join(dirPath, 'bmad-skill-manifest.yaml');
-  try {
-    if (!(await fs.pathExists(manifestPath))) return null;
-    const content = await fs.readFile(manifestPath, 'utf8');
-    const parsed = yaml.parse(content);
-    if (!parsed || typeof parsed !== 'object') return null;
-    if (parsed.canonicalId) return { __single: parsed };
-    return parsed;
-  } catch (error) {
-    console.warn(`Warning: Failed to parse bmad-skill-manifest.yaml in ${dirPath}: ${error.message}`);
-    return null;
-  }
-}
-
-/**
- * Get the canonicalId for a specific file from a loaded skill manifest.
- * @param {Object|null} manifest - Loaded manifest (from loadSkillManifest)
- * @param {string} filename - Source filename to look up (e.g., 'pm.md', 'help.md', 'pm.agent.yaml')
- * @returns {string} canonicalId or empty string
- */
-function getCanonicalId(manifest, filename) {
-  if (!manifest) return '';
-  // Single-entry manifest applies to all files in the directory
-  if (manifest.__single) return manifest.__single.canonicalId || '';
-  // Multi-entry: look up by filename directly
-  if (manifest[filename]) return manifest[filename].canonicalId || '';
-  // Fallback: try alternate extensions for compiled files
-  const baseName = filename.replace(/\.(md|xml)$/i, '');
-  const agentKey = `${baseName}.agent.yaml`;
-  if (manifest[agentKey]) return manifest[agentKey].canonicalId || '';
-  const xmlKey = `${baseName}.xml`;
-  if (manifest[xmlKey]) return manifest[xmlKey].canonicalId || '';
-  return '';
-}
-
-module.exports = { loadSkillManifest, getCanonicalId };

tools/cli/installers/lib/ide/shared/task-tool-command-generator.js

@@ -50,7 +50,6 @@ class TaskToolCommandGenerator {
         displayName: task.displayName || task.name,
         description: task.description || `Execute ${task.displayName || task.name}`,
         module: task.module,
-        canonicalId: task.canonicalId || '',
         // Use forward slashes for cross-platform consistency (not path.join which uses backslashes on Windows)
         relativePath: `${task.module}/tasks/${task.name}${taskExt}`,
         path: taskPath,
@@ -76,7 +75,6 @@ class TaskToolCommandGenerator {
         displayName: tool.displayName || tool.name,
         description: tool.description || `Execute ${tool.displayName || tool.name}`,
         module: tool.module,
-        canonicalId: tool.canonicalId || '',
         // Use forward slashes for cross-platform consistency (not path.join which uses backslashes on Windows)
         relativePath: `${tool.module}/tools/${tool.name}${toolExt}`,
         path: toolPath,

tools/cli/installers/lib/ide/shared/workflow-command-generator.js

@@ -93,7 +93,6 @@ class WorkflowCommandGenerator {
         name: workflow.name,
         description: workflow.description || `${workflow.name} workflow`,
         module: workflow.module,
-        canonicalId: workflow.canonicalId || '',
         relativePath: path.join(workflow.module, 'workflows', `${workflow.name}.md`),
         workflowPath: workflowRelPath, // Relative path to actual workflow file
         content: commandContent,

tools/docs/native-skills-migration-checklist.md

@@ -1,215 +0,0 @@
-# Native Skills Migration Checklist
-
-Branch: `refactor/all-is-skills`
-
-Scope: migrate the BMAD-supported platforms that fully support the Agent Skills standard from legacy installer outputs to native skills output.
-
-Current branch status:
-
-- `Claude Code` has already been moved to `.claude/skills`
-- `Codex CLI` has already been moved to `.agents/skills`
-
-This checklist now includes those completed platforms plus the remaining full-support platforms.
-
-## Claude Code
-
-Support assumption: full Agent Skills support. BMAD has already migrated from `.claude/commands` to `.claude/skills`.
-
-- [ ] Confirm current implementation still matches Claude Code skills expectations
-- [ ] Confirm legacy cleanup for `.claude/commands`
-- [ ] Test fresh install
-- [ ] Test reinstall/upgrade from legacy command output
-- [ ] Confirm ancestor conflict protection
-- [ ] Implement/extend automated tests as needed
-- [ ] Commit any follow-up fixes if required
-
-## Codex CLI
-
-Support assumption: full Agent Skills support. BMAD has already migrated from `.codex/prompts` to `.agents/skills`.
-
-- [ ] Confirm current implementation still matches Codex CLI skills expectations
-- [ ] Confirm legacy cleanup for project and global `.codex/prompts`
-- [ ] Test fresh install
-- [ ] Test reinstall/upgrade from legacy prompt output
-- [x] Confirm ancestor conflict protection because Codex inherits parent-directory `.agents/skills`
-- [ ] Implement/extend automated tests as needed
-- [ ] Commit any follow-up fixes if required
-
-## Cursor
-
-Support assumption: full Agent Skills support. BMAD currently installs legacy command files to `.cursor/commands`; target should move to a native skills directory.
-
-- [x] Confirm current Cursor skills path and that BMAD should target `.cursor/skills`
-- [x] Implement installer migration to native skills output
-- [x] Add legacy cleanup for `.cursor/commands`
-- [x] Test fresh install
-- [x] Test reinstall/upgrade from legacy command output
-- [x] Confirm no ancestor conflict protection is needed because a child workspace surfaced child `.cursor/skills` entries but not a parent-only skill during manual verification
-- [ ] Implement/extend automated tests
-- [x] Commit
-
-## Windsurf
-
-Support assumption: full Agent Skills support. Windsurf docs confirm workspace skills at `.windsurf/skills` and global skills at `~/.codeium/windsurf/skills`. BMAD has now migrated from `.windsurf/workflows` to `.windsurf/skills`. Manual verification also confirmed that Windsurf custom skills are triggered via `@skill-name`, not slash commands.
-
-- [x] Confirm Windsurf native skills directory as `.windsurf/skills`
-- [x] Implement installer migration to native skills output
-- [x] Add legacy cleanup for `.windsurf/workflows`
-- [x] Test fresh install
-- [x] Test reinstall/upgrade from legacy workflow output
-- [x] Confirm no ancestor conflict protection is needed because manual Windsurf verification showed child-local `@` skills loaded while a parent-only skill was not inherited
-- [x] Implement/extend automated tests
-- [x] Commit
-
-## Cline
-
-Support assumption: full Agent Skills support. BMAD currently installs workflow files to `.clinerules/workflows`; target should move to the platform's native skills directory.
-
-- [ ] Confirm current Cline skills path and whether `.cline/skills` is the correct BMAD target
-- [ ] Implement installer migration to native skills output
-- [ ] Add legacy cleanup for `.clinerules/workflows`
-- [ ] Test fresh install
-- [ ] Test reinstall/upgrade from legacy workflow output
-- [ ] Confirm ancestor conflict protection where applicable
-- [ ] Implement/extend automated tests
-- [ ] Commit
-
-## Google Antigravity
-
-Support assumption: full Agent Skills support. Antigravity docs confirm workspace skills at `.agent/skills/<skill-folder>/` and global skills at `~/.gemini/antigravity/skills/<skill-folder>/`. BMAD has now migrated from `.agent/workflows` to `.agent/skills`.
-
-- [x] Confirm Antigravity native skills path and project/global precedence
-- [x] Implement installer migration to native skills output
-- [x] Add legacy cleanup for `.agent/workflows`
-- [x] Test fresh install
-- [x] Test reinstall/upgrade from legacy workflow output
-- [x] Confirm no ancestor conflict protection is needed because manual Antigravity verification in `/tmp/antigravity-ancestor-repro/parent/child` showed only the child-local `child-only` skill, with no inherited parent `.agent/skills` entry
-- [x] Implement/extend automated tests
-- [x] Commit
-
-## Auggie
-
-Support assumption: full Agent Skills support. BMAD currently installs commands to `.augment/commands`; target should move to `.augment/skills`.
-
-- [x] Confirm Auggie native skills path and compatibility loading from `.claude/skills` and `.agents/skills` via Augment docs plus local `auggie --print` repros
-- [x] Implement installer migration to native skills output
-- [x] Add legacy cleanup for `.augment/commands`
-- [x] Test fresh install
-- [x] Test reinstall/upgrade from legacy command output
-- [x] Confirm no ancestor conflict protection is needed because local `auggie --workspace-root` repro showed child-local `.augment/skills` loading `child-only` but not parent `parent-only`
-- [x] Implement/extend automated tests
-- [ ] Commit
-
-## CodeBuddy
-
-Support assumption: full Agent Skills support. BMAD currently installs commands to `.codebuddy/commands`; target should move to `.codebuddy/skills`.
-
-- [ ] Confirm CodeBuddy native skills path and any naming/frontmatter requirements
-- [ ] Implement installer migration to native skills output
-- [ ] Add legacy cleanup for `.codebuddy/commands`
-- [ ] Test fresh install
-- [ ] Test reinstall/upgrade from legacy command output
-- [ ] Confirm ancestor conflict protection where applicable
-- [ ] Implement/extend automated tests
-- [ ] Commit
-
-## Crush
-
-Support assumption: full Agent Skills support. BMAD currently installs commands to `.crush/commands`; target should move to the platform's native skills location.
-
-- [ ] Confirm Crush project-local versus global skills path and BMAD's preferred install target
-- [ ] Implement installer migration to native skills output
-- [ ] Add legacy cleanup for `.crush/commands`
-- [ ] Test fresh install
-- [ ] Test reinstall/upgrade from legacy command output
-- [ ] Confirm ancestor conflict protection where applicable
-- [ ] Implement/extend automated tests
-- [ ] Commit
-
-## Kiro
-
-Support assumption: full Agent Skills support. Kiro docs confirm project skills at `.kiro/skills/<skill-name>/SKILL.md` and describe steering as a separate rules mechanism, not a required compatibility layer. BMAD has now migrated from `.kiro/steering` to `.kiro/skills`. Manual app verification also confirmed that Kiro can surface skills in Slash when the relevant UI setting is enabled, and that it does not inherit ancestor `.kiro/skills` directories.
-
-- [x] Confirm Kiro skills path and verify BMAD should stop writing steering artifacts for this migration
-- [x] Implement installer migration to native skills output
-- [x] Add legacy cleanup for `.kiro/steering`
-- [x] Test fresh install
-- [x] Test reinstall/upgrade from legacy steering output
-- [x] Confirm no ancestor conflict protection is needed because manual Kiro verification showed Slash-visible skills from the current workspace only, with no ancestor `.kiro/skills` inheritance
-- [x] Implement/extend automated tests
-- [x] Commit
-
-## OpenCode
-
-Support assumption: full Agent Skills support. BMAD currently splits output between `.opencode/agents` and `.opencode/commands`; target should consolidate to `.opencode/skills`.
-
-- [x] Confirm OpenCode native skills path and compatibility loading from `.claude/skills` and `.agents/skills` in OpenCode docs and with local `opencode run` repros
-- [x] Implement installer migration from multi-target legacy output to single native skills target
-- [x] Add legacy cleanup for `.opencode/agents`, `.opencode/commands`, `.opencode/agent`, and `.opencode/command`
-- [x] Test fresh install
-- [x] Test reinstall/upgrade from split legacy output
-- [x] Confirm ancestor conflict protection is required because local `opencode run` repros loaded both child-local `child-only` and ancestor `parent-only`, matching the docs that project-local skill discovery walks upward to the git worktree
-- [x] Implement/extend automated tests
-- [ ] Commit
-
-## Roo Code
-
-Support assumption: full Agent Skills support. BMAD currently installs commands to `.roo/commands`; target should move to `.roo/skills` or the correct mode-aware skill directories.
-
-- [ ] Confirm Roo native skills path and whether BMAD should use generic or mode-specific skill directories
-- [ ] Implement installer migration to native skills output
-- [ ] Add legacy cleanup for `.roo/commands`
-- [ ] Test fresh install
-- [ ] Test reinstall/upgrade from legacy command output
-- [ ] Confirm ancestor conflict protection where applicable
-- [ ] Implement/extend automated tests
-- [ ] Commit
-
-## Trae
-
-Support assumption: full Agent Skills support. BMAD currently installs rule files to `.trae/rules`; target should move to the platform's native skills directory.
-
-- [ ] Confirm Trae native skills path and whether the current `.trae/rules` path is still required for compatibility
-- [ ] Implement installer migration to native skills output
-- [ ] Add legacy cleanup for `.trae/rules`
-- [ ] Test fresh install
-- [ ] Test reinstall/upgrade from legacy rules output
-- [ ] Confirm ancestor conflict protection where applicable
-- [ ] Implement/extend automated tests
-- [ ] Commit
-
-## GitHub Copilot
-
-Support assumption: full Agent Skills support. BMAD currently uses a custom installer that generates `.github/agents`, `.github/prompts`, and `.github/copilot-instructions.md`; target should move to `.github/skills`.
-
-- [ ] Confirm GitHub Copilot native skills path and whether `.github/agents` remains necessary as a compatibility layer
-- [ ] Design the migration away from the custom prompt/agent installer model
-- [ ] Implement native skills output, ideally with shared config-driven code where practical
-- [ ] Add legacy cleanup for `.github/agents`, `.github/prompts`, and any BMAD-owned Copilot instruction file behavior that should be retired
-- [ ] Test fresh install
-- [ ] Test reinstall/upgrade from legacy custom installer output
-- [ ] Confirm ancestor conflict protection where applicable
-- [ ] Implement/extend automated tests
-- [ ] Commit
-
-## KiloCoder
-
-Support assumption: full Agent Skills support. BMAD currently uses a custom installer that writes `.kilocodemodes` and `.kilocode/workflows`; target should move to native skills output.
-
-- [ ] Confirm KiloCoder native skills path and whether `.kilocodemodes` should be removed entirely or retained temporarily for compatibility
-- [ ] Design the migration away from modes plus workflow markdown
-- [ ] Implement native skills output
-- [ ] Add legacy cleanup for `.kilocode/workflows` and BMAD-owned entries in `.kilocodemodes`
-- [ ] Test fresh install
-- [ ] Test reinstall/upgrade from legacy custom installer output
-- [ ] Confirm ancestor conflict protection where applicable
-- [ ] Implement/extend automated tests
-- [ ] Commit
-
-## Summary Gates
-
-- [ ] All full-support BMAD platforms install `SKILL.md` directory-based output
-- [ ] No full-support platform still emits BMAD command/workflow/rule files as its primary install format
-- [ ] Legacy cleanup paths are defined for every migrated platform
-- [ ] Automated coverage exists for config-driven and custom-installer migrations
-- [ ] Installer docs and migration notes updated after code changes land

website/astro.config.mjs

@@ -36,28 +36,11 @@ export default defineConfig({
   },
 
   integrations: [
-    // Exclude custom 404 pages (all locales) from the sitemap — they are
+    sitemap(),
-    // treated as normal content docs by Starlight even with disable404Route.
-    sitemap({
-      filter: (page) => !/\/404(\/|$)/.test(new URL(page).pathname),
-    }),
     starlight({
       title: 'BMAD Method',
       tagline: 'AI-driven agile development with specialized agents and workflows that scale from bug fixes to enterprise platforms.',
 
-      // i18n: English as root (no URL prefix), Chinese at /zh-cn/
-      defaultLocale: 'root',
-      locales: {
-        root: {
-          label: 'English',
-          lang: 'en',
-        },
-        'zh-cn': {
-          label: '简体中文',
-          lang: 'zh-CN',
-        },
-      },
-
       logo: {
         light: './public/img/bmad-light.png',
         dark: './public/img/bmad-dark.png',
@@ -106,29 +89,25 @@ export default defineConfig({
 
       // Sidebar configuration (Diataxis structure)
       sidebar: [
-        { label: 'Welcome', translations: { 'zh-CN': '欢迎' }, slug: 'index' },
+        { label: 'Welcome', slug: 'index' },
-        { label: 'Roadmap', translations: { 'zh-CN': '路线图' }, slug: 'roadmap' },
+        { label: 'Roadmap', slug: 'roadmap' },
         {
           label: 'Tutorials',
-          translations: { 'zh-CN': '教程' },
           collapsed: false,
           autogenerate: { directory: 'tutorials' },
         },
         {
           label: 'How-To Guides',
-          translations: { 'zh-CN': '操作指南' },
           collapsed: true,
           autogenerate: { directory: 'how-to' },
         },
         {
           label: 'Explanation',
-          translations: { 'zh-CN': '概念说明' },
           collapsed: true,
           autogenerate: { directory: 'explanation' },
         },
         {
           label: 'Reference',
-          translations: { 'zh-CN': '参考' },
           collapsed: true,
           autogenerate: { directory: 'reference' },
         },

website/src/content/config.ts

@@ -1,7 +1,6 @@
 import { defineCollection } from 'astro:content';
-import { docsSchema, i18nSchema } from '@astrojs/starlight/schema';
+import { docsSchema } from '@astrojs/starlight/schema';
 
 export const collections = {
   docs: defineCollection({ schema: docsSchema() }),
-  i18n: defineCollection({ type: 'data', schema: i18nSchema() }),
 };

website/src/content/i18n/zh-CN.json

@@ -1,28 +0,0 @@
-{
-  "skipLink.label": "跳转到内容",
-  "search.label": "搜索",
-  "search.ctrlKey": "Ctrl",
-  "search.cancelLabel": "取消",
-  "themeSelect.accessibleLabel": "选择主题",
-  "themeSelect.dark": "深色",
-  "themeSelect.light": "浅色",
-  "themeSelect.auto": "自动",
-  "languageSelect.accessibleLabel": "选择语言",
-  "menuButton.accessibleLabel": "菜单",
-  "sidebarNav.accessibleLabel": "主导航",
-  "tableOfContents.onThisPage": "本页内容",
-  "tableOfContents.overview": "概述",
-  "i18n.untranslatedContent": "此内容尚未提供中文翻译。",
-  "page.editLink": "编辑页面",
-  "page.lastUpdated": "最后更新：",
-  "page.previousLink": "上一页",
-  "page.nextLink": "下一页",
-  "page.draft": "此内容为草稿，不会包含在正式版本中。",
-  "404.text": "页面未找到。请检查 URL 或尝试使用搜索。",
-  "aside.note": "注意",
-  "aside.tip": "提示",
-  "aside.caution": "警告",
-  "aside.danger": "危险",
-  "fileTree.directory": "目录",
-  "builtWithStarlight.label": "使用 Starlight 构建"
-}