dev-playbooks 1.0.19 → 1.2.1

package/README.md

@@ -27,22 +27,7 @@ AI coding assistants are powerful, but often **unpredictable**:
 - **Evidence-based done**: completion is defined by tests/build/evidence, not AI self-evaluation
 - **Enforced role isolation**: Test Owner and Coder must work in separate conversations
 - **Multiple quality gates**: green evidence checks, task completion, role boundary checks
-- **21 Skills**: proposal, design, debate, review, entropy metrics, federation, and more
-
----
-
-## DevBooks At a Glance (Comparison)
-
-| Dimension | DevBooks | OpenSpec | spec-kit | No spec |
-|------|----------|----------|----------|--------|
-| Spec-driven workflow | Yes | Yes | Yes | No |
-| Artifact traceability | Change package (proposal/design/spec/tasks/verification/evidence) | Mostly folder/file organization | Docs + tasks orchestration | None |
-| Role & responsibility boundaries | **Enforced** (Test Owner / Coder) | Convention-based (not enforced) | Convention-based (not enforced) | None |
-| Definition of Done (DoD) | **Evidence + gates** (tests/build/audit) | Manual definition/checks | Manual definition/checks | Often subjective |
-| Code quality assurance | Gates + metrics (entropy/hotspots) + review roles | External tools / manual review | External tools / manual review | Unstable |
-| Impact analysis | CKB graph capability (falls back to grep) | Text search / manual reasoning | Text search / manual reasoning | Easy to miss |
-| Brownfield onboarding | Baseline specs/glossary/minimal verification anchors | Manual | Limited | - |
-| Automation coverage | 21 Skills (proposal→implementation→archive loop) | 3 core commands | Toolkit (greenfield-leaning) | - |
+- **18 Skills**: proposal, design, review, entropy metrics, and full workflow coverage
 
 ---
 
@@ -175,7 +160,6 @@ Run devbooks-spec-gardener skill for change add-oauth2
 | devbooks-impact-analysis | Cross-module impact analysis |
 | devbooks-proposal-challenger | Challenge a proposal |
 | devbooks-proposal-judge | Adjudicate a proposal |
-| devbooks-proposal-debate-workflow | Triangle debate (Author/Challenger/Judge) |
 | devbooks-design-doc | Create a design doc |
 | devbooks-spec-contract | Define specs & contracts |
 | devbooks-implementation-plan | Create an implementation plan |
@@ -193,6 +177,7 @@ Run devbooks-spec-gardener skill for change add-oauth2
 | Skill | Description |
 |-------|-------------|
 | devbooks-code-review | Code review (readability/consistency) |
+| devbooks-test-reviewer | Test quality and coverage review |
 
 ### Archive stage
 
@@ -206,9 +191,7 @@ Run devbooks-spec-gardener skill for change add-oauth2
 | Skill | Description |
 |-------|-------------|
 | devbooks-entropy-monitor | System entropy metrics |
-| devbooks-federation | Cross-repo federation analysis |
 | devbooks-brownfield-bootstrap | Brownfield project bootstrap |
-| devbooks-index-bootstrap | Generate a SCIP index |
 
 ---
 
@@ -218,52 +201,53 @@ Run devbooks-spec-gardener skill for change add-oauth2
 
 [OpenSpec](https://github.com/Fission-AI/OpenSpec) is a lightweight spec-driven framework with three core commands (proposal/apply/archive), organizing changes by feature folders.
 
-**What DevBooks adds:**
-- **Role isolation**: hard boundary between Test Owner and Coder (separate chats)
-- **Quality gates**: 5+ verification gates to block false completion
-- **21 Skills**: proposal, debate, review, entropy metrics, federation, etc.
-- **Evidence-based done**: tests/build define “done”, not self-evaluation
-
-**Choose OpenSpec**: you want a lightweight spec workflow.
+**OpenSpec's limitations:**
+- No role isolation, AI may self-verify "done"
+- No quality gates, false completion is hard to catch
+- Only 3 commands, insufficient coverage for complex changes
 
-**Choose DevBooks**: you need role separation and verification gates for larger changes.
+**DevBooks solutions:**
+- **Enforced role isolation**: Test Owner and Coder must work in separate conversations, preventing self-verification
+- **5+ quality gates**: Green evidence checks, task completion rate, role boundary checks
+- **18 Skills**: Full coverage from proposal to implementation to archive
 
 ### vs. spec-kit
 
 [GitHub spec-kit](https://github.com/github/spec-kit) is a spec-driven toolkit with a constitution file, multi-step refinement, and structured planning.
 
-**What DevBooks adds:**
-- **Brownfield-first**: generates baseline specs for existing repos
-- **Role isolation**: test authoring and implementation are separated
-- **Quality gates**: runtime verification, not just workflow guidance
-- **Prototype mode**: safe experiments without polluting main `src/`
+**spec-kit's limitations:**
+- Focused on greenfield (0→1) projects, limited brownfield support
+- No enforced role isolation, tests and implementation may get confused
+- Relies on manual checks, no runtime verification
 
-**Choose spec-kit**: greenfield projects with supported AI tools.
-
-**Choose DevBooks**: brownfield repos or when you want enforced gates.
+**DevBooks solutions:**
+- **Brownfield-first**: `devbooks-brownfield-bootstrap` auto-generates baseline specs
+- **Enforced role isolation**: Test authoring and implementation are physically separated
+- **Runtime gates**: Automated verification, not dependent on manual checks
 
 ### vs. Kiro.dev
 
-[Kiro](https://kiro.dev/) is an AWS agentic IDE with a three-phase workflow (EARS requirements, design, tasks), but stores specs separately from implementation artifacts.
-
-**DevBooks differences:**
-- **Change package**: proposal/design/spec/plan/verification/evidence in one place for lifecycle traceability
-- **Role isolation**: Test Owner and Coder are separated
-- **Quality gates**: verified through gates, not just task completion
+[Kiro](https://kiro.dev/) is an AWS agentic IDE with a three-phase workflow (EARS requirements, design, tasks).
 
-**Choose Kiro**: you want an IDE experience and AWS ecosystem integration.
+**Kiro's limitations:**
+- Specs and implementation artifacts stored separately, hard to trace
+- No enforced role isolation
+- Requires a specific IDE environment
 
-**Choose DevBooks**: you want change packages to bundle artifacts and enforce role boundaries.
+**DevBooks solutions:**
+- **Change packages**: proposal/design/spec/plan/verification/evidence centralized, full traceability
+- **Enforced role isolation**: Hard boundary between Test Owner and Coder
+- **Tool-agnostic**: Supports Claude Code, Codex CLI, Cursor, and more
 
 ### vs. no spec
 
-Without specs, the assistant generates code from vague prompts, leading to unpredictable output, scope creep, and “hallucinated completion”.
+Without specs, the assistant generates code from vague prompts, leading to unpredictable output, scope creep, and "hallucinated completion".
 
 **DevBooks brings:**
-- Specs agreed before implementation
-- Quality gates that verify real completion
-- Role isolation to prevent self-verification
-- Evidence chain per change
+- Specs agreed before implementation, clear and controlled scope
+- Quality gates verify real completion
+- Role isolation prevents self-verification
+- Complete evidence chain per change
 
 ---
 
@@ -354,18 +338,6 @@ Generates:
 
 </details>
 
-<details>
-<summary><strong>Cross-repo federation</strong></summary>
-
-For multi-repo analysis:
-
-```
-Run devbooks-federation skill
-```
-
-Analyzes cross-repo contracts and dependencies to support coordinated changes.
-
-</details>
 
 <details>
 <summary><strong>MCP auto-detection</strong></summary>
@@ -391,23 +363,21 @@ DevBooks Skills support graceful MCP (Model Context Protocol) degradation: you c
 - Timeout/failure → silently falls back to basic mode (non-blocking)
 - No manual “basic/enhanced” switch required
 
-To enable enhanced mode: configure CKB per `docs/Recommended-MCP.md` and run `devbooks-index-bootstrap` skill to generate `index.scip`.
+To enable enhanced mode: configure CKB per `docs/Recommended-MCP.md` and manually generate `index.scip`.
 
 </details>
 
 <details>
-<summary><strong>Proposal debate workflow</strong></summary>
+<summary><strong>Proposal review workflow</strong></summary>
 
-For strict proposal review, run the triangle debate:
+For strict proposal review, use separate conversations for Challenger and Judge:
 
-```
-Run devbooks-proposal-debate-workflow skill
-```
+Three roles (must work in separate conversations):
+1. **Author**: creates and defends the proposal (use `devbooks-proposal-author`)
+2. **Challenger**: challenges assumptions, finds gaps, identifies risks (use `devbooks-proposal-challenger`)
+3. **Judge**: makes the final decision and records rationale (use `devbooks-proposal-judge`)
 
-Three roles:
-1. **Author**: creates and defends the proposal
-2. **Challenger**: challenges assumptions, finds gaps, identifies risks
-3. **Judge**: makes the final decision and records rationale
+**Important**: The three roles must work in **separate conversations** to avoid role confusion and self-verification.
 
 Decision: `Approved`, `Revise`, `Rejected`
 

package/bin/devbooks.js

@@ -305,6 +305,160 @@ function getCliVersion() {
   }
 }
 
+// ============================================================================
+// Auto-update .gitignore and .npmignore
+// ============================================================================
+
+const IGNORE_MARKERS = {
+  start: '# DevBooks managed - DO NOT EDIT',
+  end: '# End DevBooks managed'
+};
+
+/**
+ * Get entries to add to .gitignore
+ * @param {string[]} toolIds - Selected AI tool IDs
+ * @returns {string[]} - Entries to ignore
+ */
+function getGitIgnoreEntries(toolIds) {
+  const entries = [
+    '# DevBooks local config (contains user preferences, should not be committed)',
+    '.devbooks/'
+  ];
+
+  // Add corresponding AI tool directories based on selected tools
+  for (const toolId of toolIds) {
+    const tool = AI_TOOLS.find(t => t.id === toolId);
+    if (!tool) continue;
+
+    // Add slash command directory
+    if (tool.slashDir) {
+      const topDir = tool.slashDir.split('/')[0];
+      if (!entries.includes(topDir + '/')) {
+        entries.push(`${topDir}/`);
+      }
+    }
+
+    // Add rules directory
+    if (tool.rulesDir) {
+      const topDir = tool.rulesDir.split('/')[0];
+      if (!entries.includes(topDir + '/')) {
+        entries.push(`${topDir}/`);
+      }
+    }
+
+    // Add agents directory (e.g., .github/instructions)
+    if (tool.instructionsDir) {
+      const topDir = tool.instructionsDir.split('/')[0];
+      if (topDir !== '.github') { // .github directory usually needs to be kept
+        if (!entries.includes(topDir + '/')) {
+          entries.push(`${topDir}/`);
+        }
+      }
+    }
+  }
+
+  return entries;
+}
+
+/**
+ * Get entries to add to .npmignore
+ * @returns {string[]} - Entries to ignore
+ */
+function getNpmIgnoreEntries() {
+  return [
+    '# DevBooks development docs (not needed at runtime)',
+    'dev-playbooks/',
+    '.devbooks/',
+    '',
+    '# AI tool config directories',
+    '.claude/',
+    '.cursor/',
+    '.windsurf/',
+    '.gemini/',
+    '.agent/',
+    '.opencode/',
+    '.continue/',
+    '.qoder/',
+    '.github/instructions/',
+    '.github/copilot-instructions.md',
+    '',
+    '# DevBooks instruction files',
+    'CLAUDE.md',
+    'AGENTS.md',
+    'GEMINI.md'
+  ];
+}
+
+/**
+ * Update ignore file, preserving user-defined content
+ * @param {string} filePath - ignore file path
+ * @param {string[]} entries - Entries to add
+ * @returns {object} - { updated: boolean, action: 'created' | 'updated' | 'unchanged' }
+ */
+function updateIgnoreFile(filePath, entries) {
+  const managedBlock = [
+    IGNORE_MARKERS.start,
+    ...entries,
+    IGNORE_MARKERS.end
+  ].join('\n');
+
+  if (!fs.existsSync(filePath)) {
+    // File doesn't exist, create new file
+    fs.writeFileSync(filePath, managedBlock + '\n');
+    return { updated: true, action: 'created' };
+  }
+
+  const content = fs.readFileSync(filePath, 'utf-8');
+  const startIdx = content.indexOf(IGNORE_MARKERS.start);
+  const endIdx = content.indexOf(IGNORE_MARKERS.end);
+
+  if (startIdx !== -1 && endIdx !== -1 && startIdx < endIdx) {
+    // Managed block exists, update it
+    const before = content.slice(0, startIdx);
+    const after = content.slice(endIdx + IGNORE_MARKERS.end.length);
+    const newContent = before + managedBlock + after;
+
+    if (newContent !== content) {
+      fs.writeFileSync(filePath, newContent);
+      return { updated: true, action: 'updated' };
+    }
+    return { updated: false, action: 'unchanged' };
+  }
+
+  // No managed block, append to end of file
+  const newContent = content.trimEnd() + '\n\n' + managedBlock + '\n';
+  fs.writeFileSync(filePath, newContent);
+  return { updated: true, action: 'updated' };
+}
+
+/**
+ * Setup project's ignore files
+ * @param {string[]} toolIds - Selected AI tool IDs
+ * @param {string} projectDir - Project directory
+ * @returns {object[]} - Results array
+ */
+function setupIgnoreFiles(toolIds, projectDir) {
+  const results = [];
+
+  // Update .gitignore
+  const gitIgnorePath = path.join(projectDir, '.gitignore');
+  const gitIgnoreEntries = getGitIgnoreEntries(toolIds);
+  const gitResult = updateIgnoreFile(gitIgnorePath, gitIgnoreEntries);
+  if (gitResult.updated) {
+    results.push({ file: '.gitignore', action: gitResult.action });
+  }
+
+  // Update .npmignore
+  const npmIgnorePath = path.join(projectDir, '.npmignore');
+  const npmIgnoreEntries = getNpmIgnoreEntries();
+  const npmResult = updateIgnoreFile(npmIgnorePath, npmIgnoreEntries);
+  if (npmResult.updated) {
+    results.push({ file: '.npmignore', action: npmResult.action });
+  }
+
+  return results;
+}
+
 function showVersion() {
   console.log(`${CLI_COMMAND} v${getCliVersion()}`);
 }
@@ -459,7 +613,53 @@ function installSkills(toolIds, update = false) {
 }
 
 // ============================================================================
-// 安装 Rules（Cursor, Windsurf, Gemini, Antigravity, OpenCode, Continue）
+// Install Claude Code Custom Subagents (solves built-in subagents cannot access Skills)
+// ============================================================================
+
+function installClaudeAgents(toolIds, projectDir, update = false) {
+  const results = [];
+
+  // Only Claude Code needs custom subagents
+  if (!toolIds.includes('claude')) return results;
+
+  const agentsSrcDir = path.join(__dirname, '..', 'templates', 'claude-agents');
+  const agentsDestDir = path.join(projectDir, '.claude', 'agents');
+
+  if (!fs.existsSync(agentsSrcDir)) return results;
+
+  const agentFiles = fs.readdirSync(agentsSrcDir)
+    .filter(name => name.endsWith('.md'));
+
+  if (agentFiles.length === 0) return results;
+
+  fs.mkdirSync(agentsDestDir, { recursive: true });
+
+  let installedCount = 0;
+  for (const agentFile of agentFiles) {
+    const srcPath = path.join(agentsSrcDir, agentFile);
+    const destPath = path.join(agentsDestDir, agentFile);
+
+    if (fs.existsSync(destPath) && !update) continue;
+
+    fs.copyFileSync(srcPath, destPath);
+    installedCount++;
+  }
+
+  if (installedCount > 0) {
+    results.push({
+      tool: 'Claude Code',
+      type: 'agents',
+      count: installedCount,
+      total: agentFiles.length,
+      path: agentsDestDir
+    });
+  }
+
+  return results;
+}
+
+// ============================================================================
+// Install Rules (Cursor, Windsurf, Gemini, Antigravity, OpenCode, Continue)
 // ============================================================================
 
 function installRules(toolIds, projectDir, update = false) {
@@ -838,17 +1038,25 @@ async function initCommand(projectDir, options) {
   });
 
   if (fullSupportTools.length > 0) {
-    const skillsSpinner = ora('安装 Skills...').start();
+    const skillsSpinner = ora('Installing Skills...').start();
     const skillsResults = installSkills(fullSupportTools);
-    skillsSpinner.succeed('Skills 安装完成');
+    skillsSpinner.succeed('Skills installed');
 
     for (const result of skillsResults) {
       if (result.count > 0) {
-        console.log(chalk.gray(`  └ ${result.tool}: ${result.count}/${result.total} 个 ${result.type}`));
+        console.log(chalk.gray(`  └ ${result.tool}: ${result.count}/${result.total} ${result.type}`));
       } else if (result.note) {
         console.log(chalk.gray(`  └ ${result.tool}: ${result.note}`));
       }
     }
+
+    // Install Claude Code custom subagents (solves built-in subagents cannot access Skills)
+    const agentsResults = installClaudeAgents(fullSupportTools, projectDir);
+    for (const result of agentsResults) {
+      if (result.count > 0) {
+        console.log(chalk.gray(`  └ ${result.tool}: ${result.count} custom subagents → ${result.path}`));
+      }
+    }
   }
 
   // 安装 Rules（Rules 类似系统的工具）
@@ -867,16 +1075,28 @@ async function initCommand(projectDir, options) {
     }
   }
 
-  // 安装指令文件
-  const instructionSpinner = ora('创建指令文件...').start();
+  // Install instruction files
+  const instructionSpinner = ora('Creating instruction files...').start();
   const instructionResults = installInstructionFiles(selectedTools, projectDir);
-  instructionSpinner.succeed(`创建了 ${instructionResults.length} 个指令文件`);
+  instructionSpinner.succeed(`Created ${instructionResults.length} instruction files`);
 
   for (const result of instructionResults) {
     console.log(chalk.gray(`  └ ${result.tool}: ${path.relative(projectDir, result.path)}`));
   }
 
-  // 完成
+  // Setup ignore files
+  const ignoreSpinner = ora('Configuring ignore files...').start();
+  const ignoreResults = setupIgnoreFiles(selectedTools, projectDir);
+  if (ignoreResults.length > 0) {
+    ignoreSpinner.succeed('Ignore files configured');
+    for (const result of ignoreResults) {
+      console.log(chalk.gray(`  └ ${result.file}: ${result.action}`));
+    }
+  } else {
+    ignoreSpinner.succeed('Ignore files already up to date');
+  }
+
+  // Done
   console.log();
   console.log(chalk.green('══════════════════════════════════════'));
   console.log(chalk.green('✓') + chalk.bold(' DevBooks 初始化完成！'));
@@ -942,6 +1162,14 @@ async function updateCommand(projectDir) {
     }
   }
 
+  // Update Claude Code custom subagents (project directory)
+  const agentsResults = installClaudeAgents(configuredTools, projectDir, true);
+  for (const result of agentsResults) {
+    if (result.count > 0) {
+      console.log(chalk.green('✓') + ` ${result.tool}: updated ${result.count} custom subagents`);
+    }
+  }
+
   // Update Rules (project directory)
   const rulesTools = configuredTools.filter(id => {
     const tool = AI_TOOLS.find(t => t.id === id);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "dev-playbooks",
-  "version": "1.0.19",
+  "version": "1.2.1",
   "description": "AI-powered spec-driven development workflow",
   "keywords": [
     "devbooks",

package/skills/Skills-Usage-Guide.md

@@ -115,26 +115,6 @@ If you are not using DevBooks, replace `dev-playbooks/specs` / `dev-playbooks/ch
 
 ---
 
-## `devbooks-proposal-debate-workflow` (Proposal Debate Workflow)
-
-- Purpose: run “proposal → challenge → judgment” as a 3-role triangular debate (Author/Challenger/Judge isolation), and ensure the Decision Log is explicit.
-- When to use:
-  - You want enforced 3-role contention to raise proposal quality
-  - Your team often “starts coding before risks are stated”
-- Copy-paste prompt:
-  ```text
-  You are Proposal Debate Orchestrator. Explicitly use `devbooks-proposal-debate-workflow`.
-  First read: `dev-playbooks/project.md`
-  Constraint: Author/Challenger/Judge must be separate conversations/instances; if I cannot provide that, stop and explain why.
-  Goal: `dev-playbooks/changes/<change-id>/proposal.md` Decision Log must end in Approved/Revise/Rejected (no Pending).
-  Tell me, step by step, what instruction I should copy-paste into each separate conversation, and what outputs I should paste back here.
-
-  My request:
-  <one-sentence request + background + constraints>
-  ```
-
----
-
 ## `devbooks-design-doc` (Design Owner / Design Doc)
 
 - Purpose: write `design.md` with What/Constraints + AC-xxx only (no implementation steps). This is the golden truth for tests and planning.
@@ -364,62 +344,23 @@ If you are not using DevBooks, replace `dev-playbooks/specs` / `dev-playbooks/ch
 
 ---
 
-## `devbooks-index-bootstrap` (Index Bootstrapper) [New]
+## Generating SCIP Index (Manual)
 
-- Purpose: detect project language stack and generate a SCIP index to unlock graph-based code understanding (call graph, impact analysis, symbol references, etc.).
-- Triggers:
-  - User asks for “index initialization / code graph / graph analysis”
-  - `mcp__ckb__getStatus` reports `healthy: false` for SCIP backend
-  - New project and `index.scip` does not exist
-- When to use:
-  - You want graph-mode in `devbooks-impact-analysis`
-  - You want hotspot awareness in `devbooks-coder` / `devbooks-code-review`
-  - CKB MCP tools report “SCIP backend unavailable”
-- Copy-paste prompt:
-  ```text
-  Explicitly use `devbooks-index-bootstrap`.
-  Goal: detect project stack, generate SCIP index, enable graph-based understanding.
-  Project root: $(pwd)
-  ```
-- Manual indexing (no Skill required):
-  ```bash
-  # TypeScript/JavaScript
-  npm install -g @anthropic-ai/scip-typescript
-  scip-typescript index --output index.scip
-
-  # Python
-  pip install scip-python
-  scip-python index . --output index.scip
-
-  # Go
-  go install github.com/sourcegraph/scip-go@latest
-  scip-go --output index.scip
-  ```
+If you need graph-based code understanding (call graph, impact analysis, symbol references), you can generate a SCIP index manually:
 
----
+```bash
+# TypeScript/JavaScript
+npm install -g @anthropic-ai/scip-typescript
+scip-typescript index --output index.scip
 
-## `devbooks-federation` (Federation Analyst) [New]
+# Python
+pip install scip-python
+scip-python index . --output index.scip
 
-- Purpose: cross-repo federation analysis and contract synchronization: detect contract changes, analyze cross-repo impact, notify downstream consumers.
-- Triggers:
-  - User asks for “cross-repo impact / federation analysis / contract sync / upstream-downstream dependencies”
-  - The change touches contract files defined in `federation.yaml`
-- When to use:
-  - Multi-repo projects where you need downstream impact analysis
-  - External API/contract changes requiring consumer notification
-  - You want cross-repo traceability
-- Prerequisite:
-  - `.devbooks/federation.yaml` exists at project root (copy from `skills/devbooks-federation/templates/federation.yaml`)
-- Copy-paste prompt:
-  ```text
-  Explicitly use `devbooks-federation`.
-  Goal: analyze cross-repo impact for this change, detect contract changes, generate an impact report.
-  Project root: $(pwd)
-  Changed files: <list of changed files>
-  ```
-- Script usage:
-  ```bash
-  # Check federation contract changes
-  bash ~/.claude/skills/devbooks-federation/scripts/federation-check.sh --project-root "$(pwd)"
-  ```
+# Go
+go install github.com/sourcegraph/scip-go@latest
+scip-go --output index.scip
+```
+
+See `docs/Recommended-MCP.md` for more details on configuring CKB.
 

package/skills/_shared/mcp-enhancement-template.md

@@ -48,7 +48,7 @@ When MCP is unavailable, output:
 
 ```
 ⚠️ CKB unavailable (timeout or not configured), running in basic mode.
-To enable enhanced features, run devbooks-index-bootstrap skill to build the index.
+To enable enhanced features, manually generate SCIP index.
 ```
 ```
 
@@ -65,7 +65,6 @@ The following Skills do not depend on MCP and do not need an MCP Enhancement sec
 - devbooks-proposal-author (document-only)
 - devbooks-proposal-challenger (review-only)
 - devbooks-proposal-judge (verdict-only)
-- devbooks-proposal-debate-workflow (workflow orchestration)
 - devbooks-design-backport (document backport)
 - devbooks-spec-gardener (file pruning)
 - devbooks-test-reviewer (test review)
@@ -88,8 +87,6 @@ The following Skills depend on MCP and require the full MCP Enhancement section:
 | devbooks-code-review | mcp__ckb__getHotspots | Hotspot highlighting |
 | devbooks-impact-analysis | mcp__ckb__analyzeImpact, findReferences | Precise impact analysis |
 | devbooks-brownfield-bootstrap | mcp__ckb__* | COD model generation |
-| devbooks-index-bootstrap | mcp__ckb__getStatus | Index status detection |
-| devbooks-federation | mcp__ckb__*, mcp__github__* | Cross-repo analysis |
 | devbooks-router | mcp__ckb__getStatus | Index availability detection |
 | devbooks-spec-contract | mcp__ckb__findReferences | Reference detection |
 | devbooks-entropy-monitor | mcp__ckb__getHotspots | Hotspot trend analysis |