agileflow 3.4.3 → 4.0.0-alpha.2

package/src/core/commands/ci.md

@@ -1,330 +0,0 @@
----
-description: Bootstrap CI/CD workflow with testing and quality checks
-phase: implementation
-argument-hint: "(no arguments)"
-compact_context:
-  priority: high
-  preserve_rules:
-    - "CI setup creates .github/workflows/ci.yml with lint/typecheck/test jobs"
-    - "MUST parse OWNERS input (comma-separated GitHub handles or team names)"
-    - "MUST create CODEOWNERS file with owner mappings for src/ and docs/03-decisions/"
-    - "{{RULES:file_preview}}"
-    - "Concurrency control and minimal permissions are required for security"
-  state_fields:
-    - owners_input
-    - workflow_created
-    - codeowners_created
----
-
-# ci-setup
-
-STEP 0: ACTIVATE COMPACT SUMMARY MODE
-Before reading the full command, execute this script to display the compact summary:
-```bash
-sed -n '/<!-- COMPACT_SUMMARY_START -->/,/<!-- COMPACT_SUMMARY_END -->/p' "$(dirname "$0")/ci.md" | grep -v "COMPACT_SUMMARY"
-```
-If the user confirms they want the full details, continue. Otherwise, stop here.
-
-Bootstrap minimal CI workflow and CODEOWNERS.
-
-<!-- COMPACT_SUMMARY_START -->
-
-## ⚠️ COMPACT SUMMARY - /agileflow:ci-setup IS ACTIVE
-
-**CRITICAL**: You are bootstrapping CI/CD workflow. All steps must complete to create production-ready CI.
-
-**ROLE**: CI Bootstrapper - Create GitHub Actions workflow with quality gates (lint/typecheck/test) and code ownership rules
-
----
-
-### 🚨 RULE #1: ALWAYS USE TaskCreate/TaskUpdate FOR TRACKING
-
-Track all 5 steps explicitly:
-```xml
-<invoke name="TaskCreate/TaskUpdate">
-<parameter name="content">
-1. Parse OWNERS input (required, comma-separated)
-2. Generate .github/workflows/ci.yml with 3 jobs
-3. Generate CODEOWNERS file with mappings
-4. Show diff preview (both files side-by-side)
-5. Create files after YES/NO confirmation
-</parameter>
-<parameter name="status">in-progress</parameter>
-</invoke>
-```
-
-Mark each step complete as you finish. This ensures nothing is forgotten.
-
----
-
-### 🚨 RULE #2: REQUIRED PARAMETERS
-
-`OWNERS` is required (no default):
-- Format: `@username` or `@org/team-name`
-- Multiple: Comma-separated, no spaces
-- Example: `OWNERS=@alice,@dev-team,@bob`
-
-If missing:
-```
-❌ Missing OWNERS parameter
-
-Usage: /agileflow:ci-setup OWNERS=@username,@team
-
-Examples:
-  /agileflow:ci-setup OWNERS=@alice
-  /agileflow:ci-setup OWNERS=@alice,@bob,@dev-team
-```
-
----
-
-### 🚨 RULE #3: DIFF-FIRST PATTERN
-
-ALWAYS show preview of BOTH files before creating:
-
-```
-Preview of files to create:
-
-========== .github/workflows/ci.yml ==========
-name: CI
-on: [push, pull_request]
-... [full YAML preview]
-
-========== CODEOWNERS ==========
-/src/ @alice @dev-team
-/docs/03-decisions/ @alice @dev-team
-```
-
-Then ask: "Create these files? (YES/NO)"
-
----
-
-### 🚨 RULE #4: JOBS REQUIRED
-
-Always generate these 3 jobs (generic placeholders OK):
-1. **lint**: `npm run lint` (or project equivalent)
-2. **typecheck**: `npm run typecheck` (or project equivalent)
-3. **test**: `npm test` (or project equivalent)
-
-Each job:
-- `runs-on: ubuntu-latest`
-- `permissions: { contents: read }` (minimal security)
-- `concurrency: { group: ... cancel-in-progress: true }` (cost control)
-
----
-
-### 🚨 RULE #5: CODEOWNERS MAPPINGS
-
-Required mappings:
-```
-/src/ @owners  # All source code
-/docs/03-decisions/ @owners  # ADRs require owner review
-```
-
-Both paths MUST include the parsed OWNERS.
-
----
-
-### ANTI-PATTERNS (DON'T DO THESE)
-
-❌ Skip diff preview - go directly to file creation
-❌ Hardcode owners instead of parsing input
-❌ Create workflow without concurrency control
-❌ Forget to validate OWNERS parameter format
-❌ Create CODEOWNERS without /src/ and /docs/03-decisions/ mappings
-❌ Use overly permissive permissions (contents: write)
-
-### DO THESE INSTEAD
-
-✅ ALWAYS show diff preview first
-✅ Parse OWNERS parameter, validate format
-✅ Include concurrency with cancel-in-progress
-✅ Use minimal permissions (contents: read)
-✅ Include both required path mappings
-✅ Track with TaskCreate/TaskUpdate for safety
-
----
-
-### WORKFLOW PHASES
-
-**Phase 1: Validate Input (Step 1)**
-- Parse OWNERS parameter
-- Validate format (looks like @username or @org/team)
-- If invalid: show error and ask for correction
-
-**Phase 2: Generate Files (Steps 2-3)**
-- Create workflow YAML with 3 jobs
-- Create CODEOWNERS with owner mappings
-
-**Phase 3: Preview & Confirm (Step 4)**
-- Display both files in unified diff
-- Ask: "Create these files? (YES/NO)"
-
-**Phase 4: Complete (Step 5)**
-- Write .github/workflows/ci.yml
-- Write CODEOWNERS
-- Display next steps note
-
----
-
-### NEXT STEPS TO DISPLAY
-
-```
-✅ CI setup complete!
-
-Next steps:
-1. Customize job commands for your project:
-   - Update lint command (currently: npm run lint)
-   - Update typecheck command
-   - Update test command
-
-2. Enable branch protection in GitHub:
-   - Settings → Branches → Branch protection rules
-   - Require "ci" status check
-   - Require branches to be up-to-date
-
-3. Optional: Configure merge queue
-   - Settings → Branches → Branch protection
-   - Enable merge queue for faster merges
-
-4. Optional: Add required checks
-   - Each job can be marked as required
-```
-
----
-
-### KEY FILES TO REMEMBER
-
-| File | Purpose |
-|------|---------|
-| `.github/workflows/ci.yml` | GitHub Actions workflow with 3 jobs |
-| `CODEOWNERS` | Code ownership rules for PR reviews |
-| Parsed `OWNERS` | Critical - determines who gets PRs routed |
-
----
-
-### REMEMBER AFTER COMPACTION
-
-- `/agileflow:ci-setup` IS ACTIVE - create CI workflow
-- OWNERS parameter is required (validate format)
-- ALWAYS show diff-first before creating files
-- Include lint, typecheck, test jobs
-- Map both /src/ and /docs/03-decisions/ in CODEOWNERS
-- Use TaskCreate/TaskUpdate to track 5 steps
-- Display next steps for GitHub configuration
-
-<!-- COMPACT_SUMMARY_END -->
-
-## Prompt
-
-ROLE: CI Bootstrapper
-
-TODO LIST TRACKING
-**CRITICAL**: Immediately create a todo list using TaskCreate/TaskUpdate tool to track CI setup:
-```
-1. Parse input (OWNERS)
-2. Create .github/workflows/ci.yml with lint/typecheck/test jobs
-3. Create CODEOWNERS file with owner mappings
-4. Show preview and wait for YES/NO confirmation
-5. Print notes for enabling required checks
-```
-
-Mark each step complete as you finish it. This ensures nothing is forgotten.
-
-INPUT
-OWNERS=<@handles>
-
-ACTIONS
-1) Create .github/workflows/ci.yml with jobs for lint, typecheck, tests (generic placeholders), minimal permissions, concurrency.
-2) Create CODEOWNERS with:
-   /src/  <OWNERS>
-   /docs/03-decisions/  <OWNERS>
-3) Print notes for enabling required checks.
-
-Diff-first; YES/NO.
-
----
-
-## Expected Output
-
-### Success - CI Workflow Created
-
-```
-🔧 CI/CD Setup
-══════════════════════════════════════════════════════════════
-
-Creating workflow configuration...
-
-✓ Created .github/workflows/ci.yml
-  - lint: ESLint + Prettier check
-  - typecheck: TypeScript compilation
-  - test: Jest with coverage
-  - Concurrency: cancel-in-progress enabled
-
-✓ Created CODEOWNERS
-  /src/  @team-lead @senior-dev
-  /docs/03-decisions/  @tech-lead
-
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
-✅ CI/CD Setup Complete
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
-
-Next steps:
-1. Push workflow: git add . && git push
-2. Enable branch protection in GitHub settings
-3. Set required checks: lint, typecheck, test
-
-View workflow: .github/workflows/ci.yml
-```
-
-### Success - Workflow Updated
-
-```
-🔧 CI/CD Update
-══════════════════════════════════════════════════════════════
-
-Existing workflow detected. Updating...
-
-Changes:
-+ Added code coverage threshold (80%)
-+ Added security audit job
-~ Updated Node.js version to 20
-
-✓ Updated .github/workflows/ci.yml
-
-Review changes before committing:
-  git diff .github/workflows/ci.yml
-```
-
-### Error - Missing OWNERS
-
-```
-❌ Error: OWNERS parameter required
-
-Specify code owners for CODEOWNERS file:
-
-/agileflow:ci OWNERS="@username1, @username2"
-
-These users will be required reviewers for PR changes.
-```
-
-### Error - Invalid Workflow
-
-```
-❌ Error: Invalid workflow configuration
-
-.github/workflows/ci.yml has syntax errors:
-  Line 15: Invalid job name 'test!'
-  Line 23: Missing 'runs-on' field
-
-Fix errors or run with FORCE=true to overwrite.
-```
-
----
-
-## Related Commands
-
-- `/agileflow:configure` - Manage AgileFlow features and hooks
-- `/agileflow:deploy` - Set up deployment pipeline
-- `/agileflow:tests` - Set up testing infrastructure
-- `/agileflow:verify` - Run tests and verify stories
-- `/agileflow:pr` - Generate pull request from story

package/src/core/commands/code/accessibility.md

@@ -1,363 +0,0 @@
----
-description: Multi-agent WCAG accessibility analysis with consensus voting for finding a11y barriers across semantic structure, ARIA, visual, keyboard, and forms
-argument-hint: "[file|directory] [DEPTH=quick|deep|ultradeep|extreme] [FOCUS=semantic|aria|visual|keyboard|forms|all] [MODEL=haiku|sonnet|opus]"
-compact_context:
-  priority: high
-  preserve_rules:
-    - "ACTIVE COMMAND: /agileflow:code:accessibility - Multi-agent WCAG accessibility analysis"
-    - "CRITICAL: Deploy analyzers IN PARALLEL in ONE message with multiple Task calls"
-    - "CRITICAL: Wait for all results before running consensus (use TaskOutput with block=true)"
-    - "CRITICAL: Severity scale: BLOCKER | MAJOR | MINOR | ENHANCEMENT"
-    - "MUST parse arguments: TARGET (file/dir), DEPTH (quick/deep/ultradeep), FOCUS (semantic|aria|visual|keyboard|forms|all)"
-    - "Pass consensus all analyzer outputs, let it synthesize the final report"
-    - "DEPTH GATE: ultradeep/extreme MUST spawn tmux sessions via spawn-audit-sessions.js — NEVER deploy in-process"
-    - "Use check-sessions.js to monitor spawned tmux sessions — NEVER write custom polling scripts"
-  state_fields:
-    - target_path
-    - depth
-    - focus_areas
-    - analyzers_deployed
-    - findings_collected
----
-
-# /agileflow:code:accessibility
-
-Deploy multiple specialized WCAG accessibility analyzers in parallel to find a11y barriers, then synthesize results through consensus voting into a prioritized Accessibility Audit Report.
-
----
-
-## Quick Reference
-
-```
-/agileflow:code:accessibility app/                               # Analyze app directory (quick, all 5 analyzers)
-/agileflow:code:accessibility . DEPTH=deep                       # Deep analysis - comprehensive findings
-/agileflow:code:accessibility src/ FOCUS=keyboard,aria            # Focus on specific areas
-/agileflow:code:accessibility . DEPTH=deep FOCUS=all              # Comprehensive full audit
-/agileflow:code:accessibility . DEPTH=ultradeep                   # Each analyzer in its own tmux session
-/agileflow:code:accessibility components/ FOCUS=forms             # Check forms accessibility
-```
-
----
-
-## How It Works
-
-```
-┌─────────────────────────────────────────────────────────────┐
-│                /agileflow:code:accessibility                 │
-│                                                              │
-│  1. Parse arguments (target, depth, focus)                   │
-│  2. Deploy analyzers IN PARALLEL                             │
-│  3. Collect all findings                                     │
-│  4. Run consensus coordinator to validate & prioritize       │
-│  5. Generate actionable Accessibility Audit Report           │
-└─────────────────────────────────────────────────────────────┘
-
-   ┌──────────┐ ┌──────┐ ┌────────┐ ┌──────────┐ ┌───────┐
-   │ Semantic │ │ ARIA │ │ Visual │ │ Keyboard │ │ Forms │
-   └────┬─────┘ └──┬───┘ └───┬────┘ └────┬─────┘ └───┬───┘
-        │          │         │           │            │
-        └──────────┴─────────┼───────────┴────────────┘
-                             ▼
-              ┌──────────────────────┐
-              │  Consensus Coordinator│
-              │  (validates, votes,  │
-              │   maps to WCAG 2.2)  │
-              └──────────────────────┘
-```
-
----
-
-## Arguments
-
-| Argument | Values | Default | Description |
-|----------|--------|---------|-------------|
-| TARGET | file/directory | `.` | What to analyze |
-| DEPTH | quick, deep, ultradeep, extreme | quick | quick = focus on BLOCKER/MAJOR, deep = all severities, ultradeep = separate tmux, extreme = partitioned tmux |
-| FOCUS | semantic,aria,visual,keyboard,forms,all | all | Which analyzers to deploy |
-| MODEL | haiku, sonnet, opus | haiku | Model for analyzer subagents |
-
----
-
-## Step-by-Step Process
-
-### STEP 1: Parse Arguments
-
-```
-TARGET = first argument or current directory
-DEPTH = quick (default) or deep or ultradeep
-FOCUS = all (default) or comma-separated list
-```
-
-**Analyzer Selection**:
-
-| Condition | Analyzers Deployed |
-|-----------|-------------------|
-| `FOCUS=all` | All 5: semantic, aria, visual, keyboard, forms |
-| `FOCUS=semantic` | a11y-analyzer-semantic only |
-| `FOCUS=aria` | a11y-analyzer-aria only |
-| `FOCUS=visual` | a11y-analyzer-visual only |
-| `FOCUS=keyboard` | a11y-analyzer-keyboard only |
-| `FOCUS=forms` | a11y-analyzer-forms only |
-| `FOCUS=keyboard,forms` | Deploy specified analyzers |
-
-**DEPTH behavior**:
-- `quick` (default): Focus on BLOCKER and MAJOR issues only.
-- `deep`: Include MINOR and ENHANCEMENT findings.
-- `ultradeep`: Spawn each analyzer as a separate Claude Code session in tmux.
-
-**ULTRADEEP mode** (DEPTH=ultradeep):
-1. Show cost estimate:
-   ```bash
-   node .agileflow/scripts/spawn-audit-sessions.js --audit=accessibility --target=TARGET --focus=FOCUS --model=MODEL --dry-run
-   ```
-2. Confirm with user before launching
-3. Spawn sessions (use `--json` to capture trace ID):
-   ```bash
-   node .agileflow/scripts/spawn-audit-sessions.js --audit=accessibility --target=TARGET --focus=FOCUS --model=MODEL --json
-   ```
-   Parse the JSON output to get `traceId`. Example: `{"ok":true,"traceId":"abc123ef",...}`
-4. Wait for all analyzers to complete:
-   ```bash
-   node .agileflow/scripts/check-sessions.js wait TRACE_ID --timeout=1800
-   ```
-   - Exit 0 = all complete (JSON results on stdout)
-   - Exit 1 = timeout (partial results on stdout, `missing` array shows what's left)
-   - To check progress without blocking: `node .agileflow/scripts/check-sessions.js status TRACE_ID`
-   - To retry stalled analyzers: `node .agileflow/scripts/check-sessions.js retry TRACE_ID`
-5. Parse `results` array from the JSON output. Pass all findings to consensus coordinator (same as deep mode).
-6. If tmux unavailable (spawn exits code 2), fall back to `DEPTH=deep` with warning
-
-**EXTREME mode** (DEPTH=extreme):
-Partition-based multi-agent audit. Instead of 1 analyzer per tmux window, the codebase is split into partitions and each partition runs ALL analyzers.
-1. Scan the target directory to understand the codebase structure:
-   - Use Glob to find top-level source directories
-   - Group related directories into 3-7 logical partitions (coherent domains: auth, api, ui, etc.)
-   - If user provided PARTITIONS=N (a number), split into exactly N partitions
-   - If user provided PARTITIONS=dir1,dir2,dir3, use those exact directories
-2. Show the partition plan and agent count to the user, confirm before launching:
-   Example: "5 partitions x 5 analyzers = 25 agents. Estimated cost: $X. Proceed?"
-3. Spawn sessions with partitions:
-   ```bash
-   node .agileflow/scripts/spawn-audit-sessions.js --audit=accessibility --target=TARGET --depth=extreme --partitions=dir1,dir2,dir3 --model=MODEL --json
-   ```
-4. Wait and collect results (same as ultradeep - use check-sessions.js)
-5. Run consensus on combined results from all partitions
-
-**PARTITIONS argument** (only used with DEPTH=extreme):
-| Value | Behavior |
-|-------|----------|
-| Not set | AI decides partitions (3-7 based on codebase size) |
-| `PARTITIONS=5` | AI creates exactly 5 partitions |
-| `PARTITIONS=src/auth,src/api,lib` | Use these exact directories |
-
----
-
-### DEPTH ROUTING GATE
-
-| DEPTH | Route |
-|-------|-------|
-| `quick` or `deep` | Continue to STEP 2 below |
-| `ultradeep` | STOP. Follow ULTRADEEP instructions above. Do NOT proceed to STEP 2. |
-| `extreme` | STOP. Follow EXTREME instructions above. Do NOT proceed to STEP 2. |
-
-**CRITICAL**: STEP 2 is for `quick`/`deep` ONLY. For `ultradeep`/`extreme`, the analyzers run in separate tmux sessions — NOT in-process via Task calls. If you deploy Task calls for ultradeep/extreme, you are doing it wrong. Follow the spawn-audit-sessions.js workflow above, then skip to the consensus step with the collected results.
-
----
-
-### STEP 2: Deploy Analyzers in Parallel (quick/deep ONLY)
-
-**CRITICAL**: Deploy ALL selected analyzers in a SINGLE message with multiple Task calls.
-
-**Prompt template for each analyzer**:
-
-```
-TASK: Analyze the following code for {A11Y_DOMAIN} accessibility issues.
-
-TARGET: {file_path or directory}
-DEPTH: {quick|deep}
-
-{For quick depth}: Focus on BLOCKER and MAJOR severity issues only. Skip enhancements.
-{For deep depth}: Be comprehensive. Include MINOR and ENHANCEMENT findings.
-
-Read the target files and apply your analysis methodology.
-
-OUTPUT your findings in your standard format (FINDING-N with location, severity, confidence, WCAG SC, code, explanation, remediation).
-
-If no issues found, output: "No {A11Y_DOMAIN} accessibility issues found in {TARGET}"
-```
-
-**Deploy all 5 analyzers** using these subagent types:
-- `a11y-analyzer-semantic` - Heading hierarchy, landmarks, document structure
-- `a11y-analyzer-aria` - ARIA roles, states, properties, live regions
-- `a11y-analyzer-visual` - Color contrast, motion, color-only info
-- `a11y-analyzer-keyboard` - Focus management, tab order, keyboard access
-- `a11y-analyzer-forms` - Labels, errors, autocomplete, validation
-
-### STEP 3: Collect Results
-
-Wait for all analyzers to complete using TaskOutput with `block=true`.
-
-### STEP 4: Run Consensus Coordinator
-
-Pass all analyzer outputs to the consensus coordinator:
-
-```xml
-<invoke name="Task">
-<parameter name="description">Accessibility audit consensus</parameter>
-<parameter name="prompt">You are the Accessibility Consensus Coordinator.
-
-TARGET: {target_path}
-DEPTH: {depth}
-
-## Analyzer Outputs
-
-### Semantic Analyzer Results:
-{semantic_output}
-
-### ARIA Analyzer Results:
-{aria_output}
-
-### Visual Analyzer Results:
-{visual_output}
-
-### Keyboard Analyzer Results:
-{keyboard_output}
-
-### Forms Analyzer Results:
-{forms_output}
-
----
-
-Follow your consensus process:
-1. Detect framework and component libraries
-2. Parse all findings into normalized structure
-3. Group related findings by component/area
-4. Vote on confidence (CONFIRMED if 2+ agree, LIKELY if 1 with evidence)
-5. Filter by framework (Radix, Headless UI, etc.)
-6. Map findings to WCAG 2.2 success criteria
-7. Generate the final Accessibility Audit Report
-8. Save report to docs/08-project/a11y-audits/a11y-audit-{YYYYMMDD}.md
-</parameter>
-<parameter name="subagent_type">a11y-consensus</parameter>
-</invoke>
-```
-
-### STEP 5: Present Results
-
-After consensus completes, show the report summary and offer next steps:
-
-```xml
-<invoke name="AskUserQuestion">
-<parameter name="questions">[{
-  "question": "Accessibility audit complete: [N] findings ([blockers] Blockers, [major] Major). [files_count] files analyzed. WCAG Level A: [pass/fail].",
-  "header": "Next steps",
-  "multiSelect": false,
-  "options": [
-    {"label": "Fix [blockers] Blocker issues now (Recommended)", "description": "[top_issue_summary] - [WCAG SC]"},
-    {"label": "Create stories for all findings", "description": "Track [blockers] blocker + [major] major priority items in backlog"},
-    {"label": "Re-run with DEPTH=deep", "description": "Current was quick - deep includes MINOR and ENHANCEMENT findings"},
-    {"label": "Save report and done", "description": "Report saved to docs/08-project/a11y-audits/"}
-  ]
-}]</parameter>
-</invoke>
-```
-
----
-
-## Example Output
-
-```
-♿ Accessibility Audit: app/
-══════════════════════════════════════════════════════════════
-
-Deploying 5 accessibility analyzers (quick mode)...
-✓ Semantic Analyzer
-✓ ARIA Analyzer
-✓ Visual Analyzer
-✓ Keyboard Analyzer
-✓ Forms Analyzer
-
-Running consensus...
-✓ Consensus complete
-✓ Framework detected: Next.js + shadcn/ui (Radix-based)
-
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
-ACCESSIBILITY SUMMARY
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
-
-| Severity | Count | WCAG Level |
-|----------|-------|------------|
-| Blocker  | 2     | A          |
-| Major    | 4     | A/AA       |
-| Minor    | 3     | AA         |
-
-Total: 9 findings (3 false positives excluded - Radix handles ARIA)
-WCAG 2.2 Level A: FAIL (2 blockers)
-WCAG 2.2 Level AA: FAIL
-
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
-FIX IMMEDIATELY
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
-
-1. Modal missing focus trap [CONFIRMED by Keyboard, ARIA]
-   Location: components/Modal.tsx:28
-   SC 2.1.2 | Level A
-   Fix: Add FocusTrap component or use Dialog from Radix
-
-2. Form inputs without labels [CONFIRMED by Forms, Semantic]
-   Location: app/settings/page.tsx:45
-   SC 1.3.1, 4.1.2 | Level A
-   Fix: Add Label components with htmlFor associations
-
-[Full report saved to docs/08-project/a11y-audits/a11y-audit-20260301.md]
-```
-
----
-
-<!-- COMPACT_SUMMARY_START -->
-## Compact Summary
-
-**Command**: `/agileflow:code:accessibility` - Multi-agent WCAG accessibility analysis with consensus
-
-**Quick Usage**:
-```
-/agileflow:code:accessibility app/                        # Quick scan (all 5 analyzers)
-/agileflow:code:accessibility . DEPTH=deep                # Comprehensive analysis
-/agileflow:code:accessibility components/ FOCUS=keyboard   # Specific area
-```
-
-**What It Does**: Deploy a11y analyzers in parallel -> Each checks different WCAG areas -> Consensus validates, filters by framework, maps to WCAG 2.2 -> Actionable Accessibility Audit Report
-
-**Analyzers (all 5)**:
-- `a11y-analyzer-semantic` - Headings, landmarks, semantic elements
-- `a11y-analyzer-aria` - ARIA roles, states, live regions, widget patterns
-- `a11y-analyzer-visual` - Contrast, motion, color-only info, focus indicators
-- `a11y-analyzer-keyboard` - Focus management, tab order, keyboard-only access
-- `a11y-analyzer-forms` - Labels, errors, autocomplete, validation
-
-**Severity Levels** (impact-oriented):
-- BLOCKER: No access at all (missing keyboard support, no labels)
-- MAJOR: Significant barrier (skipped headings, missing landmarks)
-- MINOR: Degraded experience (redundant ARIA, missing autocomplete)
-- ENHANCEMENT: Best practice improvement
-
-**Output**: `docs/08-project/a11y-audits/a11y-audit-{YYYYMMDD}.md`
-<!-- COMPACT_SUMMARY_END -->
-
----
-
-## Boundary Rules (No Overlap)
-
-- **vs code:security**: No XSS, injection, auth issues - those are security domain
-- **vs code:performance**: No bundle size, rendering perf - those are performance domain
-- **vs code:test**: No test coverage, test quality - those are test domain
-- **Focus on WCAG conformance and assistive technology access**
-
----
-
-## Related Commands
-
-- `/agileflow:code:security` - Security vulnerability analysis
-- `/agileflow:code:logic` - Logic bug analysis
-- `/agileflow:code:performance` - Performance bottleneck analysis
-- `/agileflow:review` - Code review (includes basic a11y checks)