feat: enhance spec loading capabilities and add new categories

- Added support for loading specs from new categories: debug, test, review, and validation.
- Updated various agents and skills to include instructions for loading project context from the new spec categories.
- Introduced new spec documents for test conventions, review standards, and validation rules to improve project guidelines.
- Enhanced the frontend to support new watcher settings and display auto-watch status.
- Improved the spec index builder to accommodate new categories and ensure proper loading of specifications.

.claude/agents/cli-planning-agent.md

@@ -31,6 +31,9 @@ If the prompt contains a `<files_to_read>` block, you MUST use the `Read` tool
 to load every file listed there before performing any other actions. This is your
 primary context.
 
+**Load Project Context** (from spec system):
+- Run: `ccw spec load --category test` for test framework context, coverage targets, and conventions
+
 **Core responsibilities:**
 - **FIRST: Execute CLI analysis** with appropriate templates and context
 - Parse structured results (fix strategies, root causes, modification points)

.claude/agents/debug-explore-agent.md

@@ -36,6 +36,7 @@ Phase 5: Fix & Verification
 ## Phase 1: Bug Analysis
 
 **Load Project Context** (from spec system):
+- Load debug specs using: `ccw spec load --category debug` for known issues, workarounds, and root-cause notes
 - Load exploration specs using: `ccw spec load --category exploration` for tech stack context and coding constraints
 
 **Session Setup**:

.claude/agents/tdd-developer.md

@@ -383,6 +383,7 @@ Bash(
 ### Context Loading (Inherited from code-developer)
 
 **Standard Context Sources**:
+- Test specs: Run `ccw spec load --category test` for test framework context, conventions, and coverage targets
 - Task JSON: `description`, `convergence.criteria`, `focus_paths`
 - Context Package: `context_package_path` → brainstorm artifacts, exploration results
 - Tech Stack: `meta.shared_context.tech_stack` (skip auto-detection if present)

.claude/agents/test-action-planning-agent.md

@@ -52,6 +52,9 @@ Read("d:\Claude_dms3\.claude\agents\action-planning-agent.md")
 ```
 <!-- TODO: verify mandatory read path -->
 
+**Load Project Context** (from spec system):
+- Run: `ccw spec load --category test` for test framework, coverage targets, and conventions
+
 </role>
 
 <test_specification_reference>

.claude/agents/test-context-search-agent.md

@@ -25,6 +25,7 @@ You are a test context discovery specialist focused on gathering test coverage i
 **Mandatory Initial Read:**
 - Project `CLAUDE.md` for coding standards and conventions
 - Test session metadata (`workflow-session.json`) for session context
+- Run: `ccw spec load --category test` for test framework, coverage targets, and conventions
 
 **Core Responsibilities:**
 - Coverage-first analysis of existing tests

.claude/agents/test-fix-agent.md

@@ -34,6 +34,9 @@ If the prompt contains a `<files_to_read>` block, you MUST use the `Read` tool
 to load every file listed there before performing any other actions. This is your
 primary context.
 
+**Load Project Context** (from spec system):
+- Run: `ccw spec load --category test` for test framework, coverage targets, and conventions
+
 ## Core Philosophy
 
 **"Tests Are the Review"** - When all tests pass across all layers, the code is approved and ready. No separate review process is needed.

.claude/skills/review-code/SKILL.md

@@ -40,6 +40,8 @@ Multi-dimensional code review skill that analyzes code across 6 key dimensions a
 └─────────────────────────────────────────────────────────────────┘
 ```
 
+**Project Context**: Run `ccw spec load --category review` for review standards, checklists, and approval gates.
+
 ## Key Design Principles
 
 1. **多维度审查**: 覆盖正确性、可读性、性能、安全性、测试覆盖、架构一致性六大维度

.claude/skills/review-cycle/SKILL.md

@@ -98,6 +98,10 @@ Skill(skill="review-cycle", args="-y src/auth/**")
 | module | [phases/review-module.md](phases/review-module.md) | review-module-cycle.md | Module-based review: path patterns → 7-dimension parallel analysis → aggregation → deep-dive → completion |
 | fix | [phases/review-fix.md](phases/review-fix.md) | review-cycle-fix.md | Automated fix: export file → intelligent batching → parallel planning → execution → completion |
 
+## Project Context
+
+Run `ccw spec load --category review` for review standards, checklists, and approval gates.
+
 ## Core Rules
 
 1. **Mode Detection First**: Parse input to determine session/module/fix mode before anything else

.claude/skills/skill-simplify/phases/02-optimize.md

@@ -9,6 +9,10 @@ Apply simplification rules from analysisResult to produce optimized content. Wri
 - Fix pseudo-code format issues
 - Write optimized content back to target file
 
+## Pre-Step: Load Context
+
+Run `ccw spec load --category validation` for verification rules and acceptance criteria to validate optimization preserves functional integrity.
+
 ## Execution
 
 ### Step 2.1: Apply Operations in Order

.claude/skills/spec-generator/phases/05-epics-stories.md

@@ -19,6 +19,10 @@ Decompose the specification into executable Epics and Stories with dependency ma
 
 ## Execution Steps
 
+### Step 0: Load Validation Context
+
+Run `ccw spec load --category validation` for verification rules and acceptance criteria to validate epic decomposition.
+
 ### Step 1: Load Phase 2-4 Context
 
 ```javascript

.claude/skills/team-frontend-debug/roles/analyzer/role.md

@@ -31,8 +31,9 @@ Root cause analysis from debug evidence.
 
 ## Phase 2: Load Evidence
 
-1. Read upstream artifacts via team_msg(operation="get_state", role="reproducer")
+1. Load debug specs: Run `ccw spec load --category debug` for known issues, workarounds, and root-cause notes
-2. Extract evidence paths from reproducer's state_update ref
+2. Read upstream artifacts via team_msg(operation="get_state", role="reproducer")
+3. Extract evidence paths from reproducer's state_update ref
 3. Load evidence-summary.json from session evidence/
 4. Load all evidence files:
    - Read screenshot files (visual inspection)

.claude/skills/team-quality-assurance/roles/executor/role.md

@@ -26,7 +26,8 @@ Run test suites, collect coverage data, and perform automatic fix cycles when te
 | Target layer | task description `layer: L1/L2/L3` | Yes |
 
 1. Extract session path and target layer from task description
-2. Read .msg/meta.json for strategy and generated test file list
+2. Load validation specs: Run `ccw spec load --category validation` for verification rules and acceptance criteria
+3. Read .msg/meta.json for strategy and generated test file list
 3. Detect test command by framework:
 
 | Framework | Command |

.claude/skills/team-review/roles/reviewer/role.md

@@ -21,7 +21,8 @@ Deep analysis on scan findings: triage, root cause / impact / optimization enric
 | .msg/meta.json | <session>/.msg/meta.json | No |
 
 1. Extract session path, input path, dimensions from task description
-2. Load scan results. If missing or empty -> report clean, complete immediately
+2. Load review specs: Run `ccw spec load --category review` for review standards, checklists, and approval gates
+3. Load scan results. If missing or empty -> report clean, complete immediately
 3. Load wisdom files from `<session>/wisdom/`
 4. Triage findings into two buckets:
 

.claude/skills/team-tech-debt/roles/scanner/role.md

@@ -18,7 +18,8 @@ Multi-dimension tech debt scanner. Scan codebase across 5 dimensions (code, arch
 | .msg/meta.json | <session>/.msg/meta.json | Yes |
 
 1. Extract session path and scan scope from task description
-2. Read .msg/meta.json for team context
+2. Load debug specs: Run `ccw spec load --category debug` for known issues, workarounds, and root-cause notes
+3. Read .msg/meta.json for team context
 3. Detect project type and framework:
 
 | Signal File | Project Type |

.claude/skills/team-testing/roles/executor/role.md

@@ -24,7 +24,8 @@ Execute tests, collect coverage, attempt auto-fix for failures. Acts as the Crit
 | .msg/meta.json | <session>/wisdom/.msg/meta.json | No |
 
 1. Extract session path and test directory from task description
-2. Extract coverage target (default: 80%)
+2. Load test specs: Run `ccw spec load --category test` for test framework conventions and coverage targets
+3. Extract coverage target (default: 80%)
 3. Read .msg/meta.json for framework info (from strategist namespace)
 4. Determine test framework:
 

.claude/skills/team-testing/roles/generator/role.md

@@ -22,7 +22,8 @@ Generate test code by layer (L1 unit / L2 integration / L3 E2E). Acts as the Gen
 | .msg/meta.json | <session>/wisdom/.msg/meta.json | No |
 
 1. Extract session path and layer from task description
-2. Read test strategy:
+2. Load test specs: Run `ccw spec load --category test` for test framework conventions and coverage targets
+3. Read test strategy:
 
 ```
 Read("<session>/strategy/test-strategy.md")

.claude/skills/team-ultra-analyze/roles/explorer/role.md

@@ -18,7 +18,8 @@ Explore codebase structure through cli-explore-agent, collecting structured cont
 | Task description | From task subject/description | Yes |
 | Session path | Extracted from task description | Yes |
 
-1. Extract session path, topic, perspective, dimensions from task description:
+1. Load debug specs: Run `ccw spec load --category debug` for known issues and root-cause notes
+2. Extract session path, topic, perspective, dimensions from task description:
 
 | Field | Pattern | Default |
 |-------|---------|---------|

.claude/skills/workflow-execute/phases/06-review.md

@@ -93,7 +93,7 @@ rg "password|token|secret|auth" -g "*.{ts,js,py}"
 rg "eval|exec|innerHTML|dangerouslySetInnerHTML" -g "*.{ts,js,tsx}"
 
 # Gemini security analysis
-ccw spec load --category execution
+ccw spec load --category review
 ccw cli -p "
 PURPOSE: Security audit of completed implementation
 TASK: Review code for security vulnerabilities, insecure patterns, auth/authz issues
@@ -105,7 +105,7 @@ RULES: Focus on OWASP Top 10, authentication, authorization, data validation, in
 
 **Architecture Review** (`architecture`):
 ```bash
-ccw spec load --category execution
+ccw spec load --category review
 ccw cli -p "
 PURPOSE: Architecture compliance review
 TASK: Evaluate adherence to architectural patterns, identify technical debt, review design decisions
@@ -117,7 +117,7 @@ RULES: Check for patterns, separation of concerns, modularity, scalability
 
 **Quality Review** (`quality`):
 ```bash
-ccw spec load --category execution
+ccw spec load --category review
 ccw cli -p "
 PURPOSE: Code quality and best practices review
 TASK: Assess code readability, maintainability, adherence to best practices
@@ -139,7 +139,7 @@ for task_file in ${sessionPath}/.task/*.json; do
 done
 
 # Cross-check implementation against requirements
-ccw spec load --category execution
+ccw spec load --category review
 ccw cli -p "
 PURPOSE: Verify all requirements and acceptance criteria are met
 TASK: Cross-check implementation summaries against original requirements

.claude/skills/workflow-lite-test-review/SKILL.md

@@ -8,6 +8,8 @@ allowed-tools: Skill, Agent, AskUserQuestion, TodoWrite, Read, Write, Edit, Bash
 
 Test review and fix engine for lite-execute chain or standalone invocation.
 
+**Project Context**: Run `ccw spec load --category test` for test framework conventions, coverage targets, and fixtures.
+
 ---
 
 ## Usage

.claude/skills/workflow-plan/phases/05-plan-verify.md

@@ -34,6 +34,10 @@ You **MUST** consider the user input before proceeding (if not empty).
 
 ## Execution
 
+### Step 5.0: Load Validation Context
+
+Run `ccw spec load --category validation` for verification rules and acceptance criteria.
+
 ### Step 5.1: Initialize Analysis Context
 
 ```bash

.claude/skills/workflow-tdd-plan/phases/02-context-gathering.md

@@ -222,6 +222,7 @@ Execute complete context-search-agent workflow for TDD implementation planning:
 ### Phase 1: Initialization & Pre-Analysis
 1. **Project State Loading**:
    - Run: \`ccw spec load --category execution\` to load project context, tech stack, and guidelines.
+   - Run: \`ccw spec load --category test\` to load test framework conventions, coverage targets, and fixtures.
    - If files don't exist, proceed with fresh analysis.
 2. **Detection**: Check for existing context-package (early exit if valid)
 3. **Foundation**: Initialize CodexLens, get project structure, load docs

.claude/skills/workflow-tdd-plan/phases/05-tdd-task-generation.md

@@ -237,13 +237,14 @@ MCP Capabilities: {exa_code, exa_web, code_index}
 These files provide project-level constraints that apply to ALL tasks:
 
 1. **ccw spec load --category execution** (project specs and tech analysis)
+2. **ccw spec load --category test** (test framework, coverage targets, conventions)
    - Contains: tech_stack, architecture_type, key_components, build_system, test_framework, coding_conventions, naming_rules, forbidden_patterns, quality_gates, custom_constraints
    - Usage: Populate plan.json shared_context, align task tech choices, set correct test commands
    - Apply as HARD CONSTRAINTS on all generated tasks — task implementation steps,
      acceptance criteria, and convergence.verification MUST respect these guidelines
    - If empty/missing: No additional constraints (proceed normally)
 
-Loading order: \`ccw spec load --category execution\` → planning-notes.md → context-package.json
+Loading order: \`ccw spec load --category execution\` → \`ccw spec load --category test\` → planning-notes.md → context-package.json
 
 ## USER CONFIGURATION (from Phase 0)
 Execution Method: ${userConfig.executionMethod}  // agent|hybrid|cli

.claude/skills/workflow-test-fix/phases/02-test-context-gather.md

@@ -346,6 +346,7 @@ Execute complete context-search-agent workflow for implementation planning:
 ### Phase 1: Initialization & Pre-Analysis
 1. **Project State Loading**:
    - Run: \`ccw spec load --category execution\` to load project context, tech stack, and guidelines.
+   - Run: \`ccw spec load --category test\` to load test framework conventions, coverage targets, and fixtures.
    - If files don't exist, proceed with fresh analysis.
 2. **Detection**: Check for existing context-package (early exit if valid)
 3. **Foundation**: Initialize CodexLens, get project structure, load docs

.claude/skills/workflow-test-fix/phases/05-test-cycle-execute.md

@@ -249,7 +249,8 @@ Task(
     ${selectedStrategy} - ${strategyDescription}
 
     ## PROJECT CONTEXT (MANDATORY)
-    1. Run: \`ccw spec load --category execution\` (tech stack, test framework, build system, constraints)
+    1. Run: \`ccw spec load --category execution\` (tech stack, build system, constraints)
+    2. Run: \`ccw spec load --category test\` (test framework, coverage targets, conventions)
 
     ## MANDATORY FIRST STEPS
     1. Read test results: ${session.test_results_path}

.claude/skills/workflow-tune/phases/01-setup.md

@@ -377,6 +377,99 @@ if (invalidSteps.length > 0) {
 }
 ```
 
+### Step 1.2b: Generate Test Requirements (Acceptance Criteria)
+
+> 调优的前提：为每一步生成跟任务匹配的验收标准。没有预期基准，就无法判断命令执行是否达标。
+
+用 Gemini 根据 step command + workflow context + 上下游关系，自动推断每步的验收标准。
+
+```javascript
+// Build step chain description for context
+const stepChainDesc = steps.map((s, i) =>
+  `Step ${i + 1}: ${s.name} (${s.type}) — ${s.command}`
+).join('\n');
+
+const reqGenPrompt = `PURPOSE: Generate concrete acceptance criteria (test requirements) for each step in a workflow pipeline. These criteria will be used to objectively judge whether each step's execution succeeded or failed.
+
+WORKFLOW:
+Name: ${workflowName}
+Goal: ${workflowContext}
+
+STEP CHAIN:
+${stepChainDesc}
+
+TASK:
+For each step, generate:
+1. **expected_outputs** — what files/artifacts should be produced (specific filenames or patterns)
+2. **content_signals** — what content patterns indicate success (keywords, structures, data shapes)
+3. **quality_thresholds** — minimum quality bar (e.g., "no empty files", "JSON must be parseable", "must contain at least N items")
+4. **pass_criteria** — 1-2 sentence description of what "pass" looks like for this step
+5. **fail_signals** — what patterns indicate failure (error messages, empty output, wrong format)
+6. **handoff_contract** — what this step must provide for the next step to work (data format, required fields)
+
+CONTEXT RULES:
+- Infer from the command what the step is supposed to do
+- Consider workflow goal when judging what "good enough" means
+- Each step's handoff_contract should match what the next step needs as input
+- Be specific: "report.md with ## Summary section" not "a report file"
+
+EXPECTED OUTPUT (strict JSON, no markdown):
+{
+  "step_requirements": [
+    {
+      "step_index": 0,
+      "step_name": "<name>",
+      "expected_outputs": ["<file or pattern>"],
+      "content_signals": ["<keyword or pattern that indicates success>"],
+      "quality_thresholds": ["<minimum bar>"],
+      "pass_criteria": "<what pass looks like>",
+      "fail_signals": ["<pattern that indicates failure>"],
+      "handoff_contract": "<what next step needs from this step>"
+    }
+  ]
+}
+
+CONSTRAINTS: Be specific to each command, output ONLY JSON`;
+
+Bash({
+  command: `ccw cli -p "${escapeForShell(reqGenPrompt)}" --tool gemini --mode analysis --rule universal-rigorous-style`,
+  run_in_background: true,
+  timeout: 300000
+});
+
+// STOP — wait for hook callback
+// After callback: parse JSON, attach requirements to each step
+
+const reqOutput = /* CLI output from callback */;
+const reqJsonMatch = reqOutput.match(/\{[\s\S]*\}/);
+
+if (reqJsonMatch) {
+  try {
+    const reqData = JSON.parse(reqJsonMatch[0]);
+    (reqData.step_requirements || []).forEach(req => {
+      const idx = req.step_index;
+      if (idx >= 0 && idx < steps.length) {
+        steps[idx].test_requirements = {
+          expected_outputs: req.expected_outputs || [],
+          content_signals: req.content_signals || [],
+          quality_thresholds: req.quality_thresholds || [],
+          pass_criteria: req.pass_criteria || '',
+          fail_signals: req.fail_signals || [],
+          handoff_contract: req.handoff_contract || ''
+        };
+      }
+    });
+  } catch (e) {
+    // Fallback: proceed without generated requirements
+    // Steps will use any manually provided success_criteria
+  }
+}
+
+// Capture session ID for resume chain start
+const reqSessionMatch = reqOutput.match(/\[CCW_EXEC_ID=([^\]]+)\]/);
+const reqSessionId = reqSessionMatch ? reqSessionMatch[1] : null;
+```
+
 ### Step 1.3: Create Workspace
 
 ```javascript
@@ -414,9 +507,10 @@ const initialState = {
     index: i,
     status: 'pending',
     execution: null,
-    analysis: null
+    analysis: null,
+    test_requirements: s.test_requirements || null  // from Step 1.2b
   })),
-  analysis_session_id: null,  // ccw cli resume chain
+  analysis_session_id: reqSessionId || null,  // resume chain starts from requirements generation
   process_log_entries: [],
   synthesis: null,
   errors: [],

.codex/skills/analyze-with-file/SKILL.md

@@ -96,6 +96,7 @@ Step 1: Topic Understanding
 Step 2: Exploration (Inline, No Agents)
    ├─ Detect codebase → search relevant modules, patterns
    │   ├─ Run `ccw spec load --category exploration` (if spec system available)
+   │   ├─ Run `ccw spec load --category debug` (known issues and root-cause notes)
    │   └─ Use Grep, Glob, Read, mcp__ace-tool__search_context
    ├─ Multi-perspective analysis (if selected, serial)
    │   ├─ Single: Comprehensive analysis
@@ -320,6 +321,7 @@ const hasCodebase = Bash(`
 if (hasCodebase !== 'none') {
   // 1. Read project metadata (if exists)
   //    - Run `ccw spec load --category exploration` (load project specs)
+  //    - Run `ccw spec load --category debug` (known issues and root-cause notes)
   //    - .workflow/specs/*.md (project conventions)
 
   // 2. Search codebase for relevant content

.codex/skills/debug-with-file/SKILL.md

@@ -22,6 +22,10 @@ Enhanced evidence-based debugging with **documented exploration process**. Recor
 
 **$BUG**
 
+## Project Context
+
+Run `ccw spec load --category debug` for known issues, workarounds, and root-cause notes.
+
 ## Execution Process
 
 ```

.codex/skills/issue-discover/SKILL.md

@@ -232,6 +232,7 @@ const agentId = spawn_agent({
 ### MANDATORY FIRST STEPS (Agent Execute)
 1. **Read role definition**: ~/.codex/agents/{agent-type}.md (MUST read first)
 2. Execute: ccw spec load --category exploration
+3. Execute: ccw spec load --category debug (known issues cross-reference)
 
 ## TASK CONTEXT
 ${taskContext}

.codex/skills/review-cycle/phases/02-parallel-review.md

@@ -95,6 +95,7 @@ dimensions.forEach(dimension => {
 4. Validate file access: bash(ls -la ${targetFiles.join(' ')})
 5. Execute: cat ~/.ccw/workflows/cli-templates/schemas/review-dimension-results-schema.json (get output schema reference)
 6. Execute: ccw spec load --category "exploration execution" (technology stack and constraints)
+7. Execute: ccw spec load --category review (review standards and checklists)
 
 ---
 
@@ -217,6 +218,7 @@ dimensions.forEach(dimension => {
 5. Read review state: ${reviewStateJsonPath}
 6. Execute: cat ~/.ccw/workflows/cli-templates/schemas/review-dimension-results-schema.json (get output schema reference)
 7. Execute: ccw spec load --category "exploration execution" (technology stack and constraints)
+8. Execute: ccw spec load --category review (review standards and checklists)
 
 ---
 
@@ -335,6 +337,7 @@ const deepDiveAgentId = spawn_agent({
 5. Read test files: bash(find ${projectDir}/tests -name "*${basename(file, '.ts')}*" -type f)
 6. Execute: cat ~/.ccw/workflows/cli-templates/schemas/review-deep-dive-results-schema.json (get output schema reference)
 7. Execute: ccw spec load --category "exploration execution" (technology stack and constraints for remediation)
+8. Execute: ccw spec load --category review (review standards and checklists)
 
 ---
 

.codex/skills/workflow-test-fix-cycle/phases/01-test-fix-gen.md

@@ -76,6 +76,7 @@ const contextAgentId = spawn_agent({
 ### MANDATORY FIRST STEPS (Agent Execute)
 1. **Read role definition**: ~/.codex/agents/test-context-search-agent.md (MUST read first)
 2. Run: `ccw spec load --category planning`
+3. Run: `ccw spec load --category test` (test framework, coverage targets, conventions)
 
 ---
 
@@ -102,6 +103,7 @@ const contextAgentId = spawn_agent({
 ### MANDATORY FIRST STEPS (Agent Execute)
 1. **Read role definition**: ~/.codex/agents/context-search-agent.md (MUST read first)
 2. Run: `ccw spec load --category planning`
+3. Run: `ccw spec load --category test` (test framework, coverage targets, conventions)
 
 ---
 
@@ -175,6 +177,7 @@ const analysisAgentId = spawn_agent({
 ### MANDATORY FIRST STEPS (Agent Execute)
 1. **Read role definition**: ~/.codex/agents/cli-execution-agent.md (MUST read first)
 2. Run: `ccw spec load --category planning`
+3. Run: `ccw spec load --category test` (test framework, coverage targets, conventions)
 
 ---
 
@@ -243,6 +246,7 @@ const taskGenAgentId = spawn_agent({
 ### MANDATORY FIRST STEPS (Agent Execute)
 1. **Read role definition**: ~/.codex/agents/action-planning-agent.md (MUST read first)
 2. Run: `ccw spec load --category planning`
+3. Run: `ccw spec load --category test` (test framework, coverage targets, conventions)
 
 ---
 

.codex/skills/workflow-test-fix-cycle/phases/02-test-cycle-execute.md

@@ -91,6 +91,7 @@ const analysisAgentId = spawn_agent({
 ### MANDATORY FIRST STEPS (Agent Execute)
 1. **Read role definition**: ~/.codex/agents/cli-planning-agent.md (MUST read first)
 2. Run: `ccw spec load --category planning`
+3. Run: `ccw spec load --category test` (test framework, coverage targets, conventions)
 
 ---
 
@@ -157,6 +158,7 @@ const fixAgentId = spawn_agent({
 ### MANDATORY FIRST STEPS (Agent Execute)
 1. **Read role definition**: ~/.codex/agents/test-fix-agent.md (MUST read first)
 2. Run: `ccw spec load --category execution`
+3. Run: `ccw spec load --category test` (test framework, coverage targets, conventions)
 
 ---
 

ccw/frontend/src/components/codexlens/EnvSettingsTab.tsx

@@ -66,11 +66,19 @@ const ENV_GROUPS: EnvGroup[] = [
       { key: 'CODEXLENS_DB_PATH', label: 'DB Path' },
       { key: 'CODEXLENS_INDEX_WORKERS', label: 'Index Workers' },
       { key: 'CODEXLENS_CODE_AWARE_CHUNKING', label: 'Code Aware Chunking' },
+      { key: 'CODEXLENS_AST_CHUNKING', label: 'AST Chunking' },
       { key: 'CODEXLENS_MAX_FILE_SIZE', label: 'Max File Size' },
       { key: 'CODEXLENS_HNSW_EF', label: 'HNSW EF' },
       { key: 'CODEXLENS_HNSW_M', label: 'HNSW M' },
     ],
   },
+  {
+    title: 'watcher',
+    fields: [
+      { key: 'CODEXLENS_AUTO_WATCH', label: 'Auto Watch' },
+      { key: 'CODEXLENS_WATCHER_DEBOUNCE_MS', label: 'Watch Debounce (ms)' },
+    ],
+  },
 ];
 
 // Fields that are only relevant in API mode
@@ -95,6 +103,9 @@ const FIELD_DEFAULTS: Record<string, string> = {
   CODEXLENS_RERANKER_BATCH_SIZE: '32',
   CODEXLENS_INDEX_WORKERS: '2',
   CODEXLENS_CODE_AWARE_CHUNKING: 'true',
+  CODEXLENS_AST_CHUNKING: 'true',
+  CODEXLENS_AUTO_WATCH: 'false',
+  CODEXLENS_WATCHER_DEBOUNCE_MS: '1000',
   CODEXLENS_MAX_FILE_SIZE: '1000000',
   CODEXLENS_HNSW_EF: '150',
   CODEXLENS_HNSW_M: '32',

ccw/frontend/src/components/codexlens/IndexManagerTab.tsx

@@ -10,7 +10,7 @@ import { useQueryClient } from '@tanstack/react-query';
 import { Card, CardHeader, CardTitle, CardContent } from '@/components/ui/Card';
 import { Button } from '@/components/ui/Button';
 import { Input } from '@/components/ui/Input';
-import { useIndexStatus, useSyncIndex, useRebuildIndex, codexLensKeys, type IndexStatusData } from '@/hooks/useCodexLens';
+import { useIndexStatus, useSyncIndex, useRebuildIndex, useWatcherStatus, codexLensKeys, type IndexStatusData } from '@/hooks/useCodexLens';
 import { useWorkflowStore, selectProjectPath } from '@/stores/workflowStore';
 
 interface ProjectStatusCardProps {
@@ -131,8 +131,17 @@ export function IndexManagerTab() {
     }
   };
 
+  const { autoWatch } = useWatcherStatus();
+
   return (
     <div className="space-y-4">
+      {/* Global watcher status */}
+      <div className="flex items-center gap-2">
+        <span className={`text-xs px-2 py-0.5 rounded-full ${autoWatch ? 'bg-green-100 text-green-700' : 'bg-gray-100 text-gray-500'}`}>
+          {autoWatch ? 'Auto-watch ON' : 'Auto-watch OFF'}
+        </span>
+      </div>
+
       {/* Add project path */}
       <div className="flex gap-2">
         <Input

ccw/frontend/src/hooks/useCodexLens.ts

@@ -204,3 +204,18 @@ export function useCodexLensMcpConfig() {
     staleTime: 30_000,
   });
 }
+
+// ========================================
+// Watcher Status Hook
+// ========================================
+
+export function useWatcherStatus() {
+  const { data: envData } = useCodexLensEnv();
+  const autoWatch = envData?.values?.CODEXLENS_AUTO_WATCH === 'true';
+  const debounceMs = envData?.values?.CODEXLENS_WATCHER_DEBOUNCE_MS || '1000';
+
+  return {
+    autoWatch,
+    debounceMs,
+  };
+}

ccw/src/commands/spec.ts

@@ -97,7 +97,7 @@ async function loadAction(options: SpecOptions): Promise<void> {
     const result = await loadSpecs({
       projectPath,
       dimension: dimension as 'specs' | 'personal' | undefined,
-      category: category as 'general' | 'exploration' | 'planning' | 'execution' | undefined,
+      category: category as 'general' | 'exploration' | 'planning' | 'execution' | 'debug' | 'test' | 'review' | 'validation' | undefined,
       keywords,
       outputFormat: stdin ? 'hook' : 'cli',
       stdinData,
@@ -367,11 +367,16 @@ ${chalk.bold('OPTIONS')}
   --stdin             Read input from stdin (Hook mode)
   --json              Output as JSON
 
-${chalk.bold('KEYWORD CATEGORIES')}
+${chalk.bold('CATEGORIES')}
-  Use these predefined keywords to load specs for specific workflow stages:
+  Use --category to load specs for specific workflow stages:
-  ${chalk.cyan('exploration')}  - Code exploration, analysis, debugging context
+  ${chalk.cyan('general')}      - Applies to all stages (always included)
+  ${chalk.cyan('exploration')}  - Code exploration, analysis, codebase understanding
   ${chalk.cyan('planning')}     - Task planning, requirements context
-  ${chalk.cyan('execution')}    - Implementation, testing, deployment context
+  ${chalk.cyan('execution')}    - Implementation, coding, deployment context
+  ${chalk.cyan('debug')}        - Debugging, known issues, workarounds
+  ${chalk.cyan('test')}         - Test conventions, frameworks, coverage
+  ${chalk.cyan('review')}       - Code review standards, checklists, gates
+  ${chalk.cyan('validation')}   - Verification rules, acceptance criteria
 
 ${chalk.bold('EXAMPLES')}
   ${chalk.gray('# Initialize spec system:')}

ccw/src/core/routes/codexlens-routes.ts

@@ -101,6 +101,8 @@ const CODEXLENS_ENV_DEFAULTS: Record<string, string> = {
   CODEXLENS_CODE_AWARE_CHUNKING: 'true',
   CODEXLENS_AST_CHUNKING: 'true',
   CODEXLENS_MAX_FILE_SIZE: '1000000',
+  CODEXLENS_AUTO_WATCH: 'false',
+  CODEXLENS_WATCHER_DEBOUNCE_MS: '1000',
   CODEXLENS_HNSW_EF: '150',
   CODEXLENS_HNSW_M: '32',
 };
@@ -147,7 +149,7 @@ function buildMcpServerConfig(savedEnv: Record<string, string>): Record<string,
 
   return {
     command: 'uvx',
-    args: ['--from', 'codexlens-search[mcp,ast]', 'codexlens-mcp'],
+    args: ['--from', 'codexlens-search[mcp,ast,watcher]', 'codexlens-mcp'],
     ...(Object.keys(filteredEnv).length > 0 ? { env: filteredEnv } : {}),
   };
 }

ccw/src/tools/spec-index-builder.ts

@@ -28,17 +28,21 @@ import { homedir } from 'os';
 
 /**
  * Spec categories for workflow stage-based loading.
- * - general: Applies to all stages (e.g. coding conventions)
+ * - general: Applies to all stages (e.g. coding conventions) — always included
- * - exploration: Code exploration, analysis, debugging context
+ * - exploration: Code exploration, analysis, codebase understanding
  * - planning: Task planning, roadmap, requirements context
- * - execution: Implementation, testing, deployment context
+ * - execution: Implementation, coding, deployment context
+ * - debug: Debugging, known issues, workarounds, root-cause notes
+ * - test: Test conventions, frameworks, coverage, fixtures
+ * - review: Code review standards, checklists, approval gates
+ * - validation: Verification rules, acceptance criteria, quality checks
  *
  * Usage: Set category field in spec frontmatter:
  *   category: exploration
  *
  * System-level loading by stage: ccw spec load --category exploration
  */
-export const SPEC_CATEGORIES = ['general', 'exploration', 'planning', 'execution'] as const;
+export const SPEC_CATEGORIES = ['general', 'exploration', 'planning', 'execution', 'debug', 'test', 'review', 'validation'] as const;
 
 export type SpecCategory = typeof SPEC_CATEGORIES[number];
 

ccw/src/tools/spec-init.ts

@@ -18,7 +18,7 @@ import { join } from 'path';
 export interface SpecFrontmatter {
   title: string;
   dimension: string;
-  category?: 'general' | 'exploration' | 'planning' | 'execution';
+  category?: 'general' | 'exploration' | 'planning' | 'execution' | 'debug' | 'test' | 'review' | 'validation';
   keywords: string[];
   readMode: 'required' | 'optional';
   priority: 'high' | 'medium' | 'low';
@@ -117,6 +117,133 @@ export const SEED_DOCS: Map<string, SeedDoc[]> = new Map([
 - External dependencies require justification
 - Prefer standard library when available
 - Pin dependency versions for reproducibility
+`,
+      },
+      {
+        filename: 'debug-notes.md',
+        frontmatter: {
+          title: 'Debug Notes',
+          dimension: 'specs',
+          category: 'debug',
+          keywords: ['debug', 'issue', 'workaround', 'root-cause', 'gotcha'],
+          readMode: 'optional',
+          priority: 'medium',
+        },
+        body: `# Debug Notes
+
+## Known Issues
+
+- Document known bugs and their workarounds here
+- Include root-cause analysis for resolved issues
+
+## Common Gotchas
+
+- List environment-specific pitfalls
+- Note platform differences that cause unexpected behavior
+
+## Debugging Tips
+
+- Preferred debugging workflows for this project
+- Key log locations and diagnostic commands
+`,
+      },
+      {
+        filename: 'test-conventions.md',
+        frontmatter: {
+          title: 'Test Conventions',
+          dimension: 'specs',
+          category: 'test',
+          keywords: ['test', 'coverage', 'mock', 'fixture', 'assertion', 'framework'],
+          readMode: 'required',
+          priority: 'high',
+        },
+        body: `# Test Conventions
+
+## Framework
+
+- Test runner and assertion library used in this project
+- Configuration file locations
+
+## Structure
+
+- Test file naming conventions (e.g., *.test.ts, *.spec.ts)
+- Test directory organization
+- Fixture and mock patterns
+
+## Coverage
+
+- Minimum coverage thresholds
+- Coverage report configuration
+- Files excluded from coverage
+
+## Best Practices
+
+- Prefer unit tests for business logic
+- Use integration tests for API boundaries
+- Mock external dependencies, not internal modules
+`,
+      },
+      {
+        filename: 'review-standards.md',
+        frontmatter: {
+          title: 'Review Standards',
+          dimension: 'specs',
+          category: 'review',
+          keywords: ['review', 'checklist', 'gate', 'approval', 'standard'],
+          readMode: 'required',
+          priority: 'medium',
+        },
+        body: `# Review Standards
+
+## Code Review Checklist
+
+- Correctness: Does it do what it claims?
+- Clarity: Is the intent obvious without comments?
+- Tests: Are changes covered by tests?
+- Security: No new vulnerabilities introduced?
+- Performance: No unnecessary allocations or O(n²) loops?
+
+## Approval Gates
+
+- All CI checks must pass
+- At least one approving review required
+- No unresolved conversations
+
+## Style
+
+- Follow existing project conventions
+- Keep PRs focused and reviewable (< 400 lines preferred)
+`,
+      },
+      {
+        filename: 'validation-rules.md',
+        frontmatter: {
+          title: 'Validation Rules',
+          dimension: 'specs',
+          category: 'validation',
+          keywords: ['validation', 'verification', 'acceptance', 'criteria', 'check'],
+          readMode: 'required',
+          priority: 'high',
+        },
+        body: `# Validation Rules
+
+## Acceptance Criteria
+
+- Define clear pass/fail conditions for each feature
+- Include edge cases in acceptance criteria
+- Specify performance thresholds where applicable
+
+## Verification Steps
+
+- Build must succeed without warnings
+- All existing tests must continue to pass
+- New features must include corresponding tests
+
+## Quality Checks
+
+- No TypeScript strict mode errors
+- No linter warnings in changed files
+- Bundle size regression checks (if applicable)
 `,
       },
     ],

ccw/src/tools/spec-loader.ts

@@ -255,7 +255,8 @@ export function filterSpecs(
 
   for (const entry of index.entries) {
     // Category filter: skip if category specified and doesn't match
-    if (category && entry.category !== category) {
+    // 'general' category always passes through (applies to all stages)
+    if (category && entry.category !== category && entry.category !== 'general') {
       continue;
     }