claude-code-workflow 7.2.27 → 7.2.28

package/.claude/skills/team-visual-a11y/roles/coordinator/commands/dispatch.md

@@ -0,0 +1,250 @@
+# Command: Dispatch
+
+Create the visual accessibility task chain with correct dependencies and structured task descriptions. Supports audit-only and full pipeline modes.
+
+## Phase 2: Context Loading
+
+| Input | Source | Required |
+|-------|--------|----------|
+| User requirement | From coordinator Phase 1 | Yes |
+| Session folder | From coordinator Phase 2 | Yes |
+| Pipeline mode | From session meta.json `pipeline` | Yes |
+| Target info | From session meta.json `target` | Yes |
+
+1. Load user requirement and scope from meta.json
+2. Load pipeline stage definitions from specs/pipelines.md
+3. Read `pipeline` and `target` from meta.json
+
+## Phase 3: Task Chain Creation (Mode-Branched)
+
+### Task Description Template
+
+Every task description uses structured format:
+
+```
+TaskCreate({
+  subject: "<TASK-ID>",
+  description: "PURPOSE: <what this task achieves> | Success: <measurable completion criteria>
+TASK:
+  - <step 1: specific action>
+  - <step 2: specific action>
+  - <step 3: specific action>
+CONTEXT:
+  - Session: <session-folder>
+  - Target: <URL or file path>
+  - WCAG Level: <AA|AAA>
+  - Upstream artifacts: <artifact-1>, <artifact-2>
+  - Shared memory: <session>/.msg/meta.json
+EXPECTED: <deliverable path> + <quality criteria>
+CONSTRAINTS: <scope limits, focus areas>"
+})
+TaskUpdate({ taskId: "<TASK-ID>", addBlockedBy: [<dependency-list>], owner: "<role>" })
+```
+
+### Mode Router
+
+| Mode | Action |
+|------|--------|
+| `audit-only` | Create 4 tasks: [COLOR-001 + TYPO-001 + FOCUS-001] parallel -> REMED-001 |
+| `full` | Create 7 tasks: [COLOR-001 + TYPO-001 + FOCUS-001] -> REMED-001 -> FIX-001 -> [COLOR-002 + FOCUS-002] |
+
+---
+
+### Audit-Only Pipeline Task Chain
+
+**COLOR-001** (color-auditor):
+```
+TaskCreate({
+  subject: "COLOR-001",
+  description: "PURPOSE: OKLCH color contrast audit for all color combinations | Success: Complete color audit with WCAG 2.1 + APCA contrast ratios and color blindness assessment
+TASK:
+  - Extract all color values (OKLCH, HSL, RGB, hex) from stylesheets
+  - Calculate WCAG 2.1 contrast ratios for all text/background combinations
+  - Calculate APCA Lc values for body and large text
+  - Assess OKLCH lightness ranges for text and backgrounds
+  - Simulate color blindness (protanopia, deuteranopia, tritanopia)
+  - Check dark mode color parity if applicable
+CONTEXT:
+  - Session: <session-folder>
+  - Target: <target>
+  - WCAG Level: <level>
+  - Shared memory: <session>/.msg/meta.json
+EXPECTED: <session>/audits/color/color-audit-001.md | Pass/fail per color combination
+CONSTRAINTS: Read-only analysis | Use Chrome DevTools for computed styles when available"
+})
+TaskUpdate({ taskId: "COLOR-001", owner: "color-auditor" })
+```
+
+**TYPO-001** (typo-auditor):
+```
+TaskCreate({
+  subject: "TYPO-001",
+  description: "PURPOSE: Typography readability audit across all viewports | Success: Complete typography audit with size, line-height, reading width at each breakpoint
+TASK:
+  - Audit font sizes at each breakpoint (320px, 768px, 1024px, 1400px)
+  - Validate minimum body text >= 16px on mobile
+  - Check line-height ratios (body 1.5-1.75, headings 1.1-1.3)
+  - Validate clamp() functions for responsive scaling
+  - Measure reading width (45-75 characters per line)
+  - Assess font loading strategy (font-display values)
+CONTEXT:
+  - Session: <session-folder>
+  - Target: <target>
+  - WCAG Level: <level>
+  - Shared memory: <session>/.msg/meta.json
+EXPECTED: <session>/audits/typography/typo-audit-001.md | Breakpoint-by-breakpoint report
+CONSTRAINTS: Read-only analysis | Screenshot at multiple viewports if Chrome DevTools available"
+})
+TaskUpdate({ taskId: "TYPO-001", owner: "typo-auditor" })
+```
+
+**FOCUS-001** (focus-auditor):
+```
+TaskCreate({
+  subject: "FOCUS-001",
+  description: "PURPOSE: Focus management and keyboard accessibility audit | Success: Complete focus audit with tab order, indicator visibility, ARIA coverage
+TASK:
+  - Audit tab order for logical sequence and no tab traps
+  - Check focus indicator visibility (outline >= 2px, contrast >= 3:1)
+  - Verify :focus-visible usage for keyboard vs mouse distinction
+  - Check skip link presence and functionality
+  - Audit focus traps in modals/dialogs (Tab cycles, Escape dismisses)
+  - Verify ARIA live regions for dynamic content
+  - Check ARIA roles and states on interactive elements
+  - Validate keyboard operability (Enter/Space, Arrow keys)
+CONTEXT:
+  - Session: <session-folder>
+  - Target: <target>
+  - WCAG Level: <level>
+  - Shared memory: <session>/.msg/meta.json
+EXPECTED: <session>/audits/focus/focus-audit-001.md | Element-by-element focus report
+CONSTRAINTS: Read-only analysis | Tab through elements if Chrome DevTools available"
+})
+TaskUpdate({ taskId: "FOCUS-001", owner: "focus-auditor" })
+```
+
+**CRITICAL**: COLOR-001, TYPO-001, FOCUS-001 have NO blockedBy -- they run in PARALLEL.
+
+**REMED-001** (remediation-planner):
+```
+TaskCreate({
+  subject: "REMED-001",
+  description: "PURPOSE: Synthesize all 3 audit findings into prioritized remediation plan | Success: Complete remediation plan with severity ranking, code-level fix guidance, WCAG criterion mapping
+TASK:
+  - Read color, typography, and focus audit reports
+  - Merge and deduplicate findings
+  - Prioritize by severity (Critical > High > Medium > Low)
+  - Group by file/component for efficient fixing
+  - Provide code-level fix guidance (specific CSS/HTML changes)
+  - Map each fix to WCAG success criterion
+  - Estimate effort per fix
+CONTEXT:
+  - Session: <session-folder>
+  - Target: <target>
+  - WCAG Level: <level>
+  - Upstream artifacts: audits/color/color-audit-001.md, audits/typography/typo-audit-001.md, audits/focus/focus-audit-001.md
+  - Shared memory: <session>/.msg/meta.json
+EXPECTED: <session>/remediation/remediation-plan.md | All critical/high issues addressed
+CONSTRAINTS: Read-only synthesis | No code modifications"
+})
+TaskUpdate({ taskId: "REMED-001", addBlockedBy: ["COLOR-001", "TYPO-001", "FOCUS-001"], owner: "remediation-planner" })
+```
+
+---
+
+### Full Pipeline Task Chain
+
+Same as audit-only (COLOR-001, TYPO-001, FOCUS-001, REMED-001), plus:
+
+**FIX-001** (fix-implementer):
+```
+TaskCreate({
+  subject: "FIX-001",
+  description: "PURPOSE: Implement accessibility fixes from remediation plan | Success: All critical and high severity issues fixed with passing contrast ratios and ARIA validation
+TASK:
+  - Read remediation plan for prioritized fix list
+  - Apply OKLCH color corrections for contrast compliance
+  - Add/fix focus styles (outline, outline-offset, :focus-visible)
+  - Add missing ARIA attributes (role, aria-label, aria-live, aria-expanded)
+  - Add reduced-motion media queries where needed
+  - Fix typography (clamp(), line-height, max-width for reading)
+  - Add skip link if missing
+  - Apply fixes in priority order (critical first)
+CONTEXT:
+  - Session: <session-folder>
+  - Target: <target>
+  - WCAG Level: <level>
+  - Upstream artifacts: remediation/remediation-plan.md
+  - Shared memory: <session>/.msg/meta.json
+EXPECTED: Modified source files + <session>/fixes/fix-summary-001.md | All critical/high fixes applied
+CONSTRAINTS: Modify only files identified in remediation plan | Preserve existing functionality"
+})
+TaskUpdate({ taskId: "FIX-001", addBlockedBy: ["REMED-001"], owner: "fix-implementer" })
+```
+
+**COLOR-002** (color-auditor):
+```
+TaskCreate({
+  subject: "COLOR-002",
+  description: "PURPOSE: Re-audit color contrast after fixes applied | Success: All color combinations pass WCAG target level
+TASK:
+  - Re-extract all color values from modified stylesheets
+  - Re-calculate WCAG 2.1 contrast ratios
+  - Re-calculate APCA Lc values
+  - Compare before/after for each fixed combination
+  - Verify no regressions in unfixed combinations
+CONTEXT:
+  - Session: <session-folder>
+  - Target: <target>
+  - WCAG Level: <level>
+  - Upstream artifacts: fixes/fix-summary-001.md, audits/color/color-audit-001.md
+  - Shared memory: <session>/.msg/meta.json
+EXPECTED: <session>/re-audit/color-audit-002.md | Before/after comparison with pass/fail
+CONSTRAINTS: Read-only verification | Focus on fixed items + regression check"
+})
+TaskUpdate({ taskId: "COLOR-002", addBlockedBy: ["FIX-001"], owner: "color-auditor" })
+```
+
+**FOCUS-002** (focus-auditor):
+```
+TaskCreate({
+  subject: "FOCUS-002",
+  description: "PURPOSE: Re-audit focus management after fixes applied | Success: All focus indicators visible with correct ARIA attributes
+TASK:
+  - Re-audit tab order after DOM changes
+  - Verify focus indicator fixes (outline, contrast)
+  - Check new ARIA attributes are valid
+  - Verify skip link implementation
+  - Test keyboard operability of fixed elements
+  - Compare before/after for each fixed element
+CONTEXT:
+  - Session: <session-folder>
+  - Target: <target>
+  - WCAG Level: <level>
+  - Upstream artifacts: fixes/fix-summary-001.md, audits/focus/focus-audit-001.md
+  - Shared memory: <session>/.msg/meta.json
+EXPECTED: <session>/re-audit/focus-audit-002.md | Before/after comparison with pass/fail
+CONSTRAINTS: Read-only verification | Focus on fixed items + regression check"
+})
+TaskUpdate({ taskId: "FOCUS-002", addBlockedBy: ["FIX-001"], owner: "focus-auditor" })
+```
+
+**CRITICAL**: COLOR-002 and FOCUS-002 both blocked only by FIX-001 -- they run in PARALLEL after fixes.
+
+---
+
+## Phase 4: Validation
+
+Verify task chain integrity:
+
+| Check | Method | Expected |
+|-------|--------|----------|
+| Task count correct | TaskList count | audit-only: 4, full: 7 |
+| Dependencies correct | Trace dependency graph | Acyclic, correct blockedBy |
+| No circular dependencies | Trace dependency graph | Acyclic |
+| 3 audit tasks have NO blockedBy | Pattern check | COLOR-001, TYPO-001, FOCUS-001 are parallel |
+| REMED-001 blocked by all 3 | Check blockedBy | [COLOR-001, TYPO-001, FOCUS-001] |
+| Task IDs use correct prefixes | Pattern check | COLOR/TYPO/FOCUS/REMED/FIX |
+| Structured descriptions complete | Each has PURPOSE/TASK/CONTEXT/EXPECTED/CONSTRAINTS | All present |
+
+If validation fails, fix the specific task and re-validate.

package/.claude/skills/team-visual-a11y/roles/coordinator/commands/monitor.md

@@ -0,0 +1,204 @@
+# Monitor Pipeline
+
+Event-driven pipeline coordination. Beat model: coordinator wake -> process -> spawn -> STOP.
+
+## Constants
+
+- SPAWN_MODE: background
+- ONE_STEP_PER_INVOCATION: true
+- FAST_ADVANCE_AWARE: true
+- WORKER_AGENT: team-worker
+- MAX_GC_ROUNDS: 2
+
+## Handler Router
+
+| Source | Handler |
+|--------|---------|
+| Message contains [color-auditor], [typo-auditor], [focus-auditor], [remediation-planner], [fix-implementer] | handleCallback |
+| "capability_gap" | handleAdapt |
+| "check" or "status" | handleCheck |
+| "resume" or "continue" | handleResume |
+| All tasks completed | handleComplete |
+| Default | handleSpawnNext |
+
+## handleCallback
+
+Worker completed. Process and advance.
+
+1. Parse message to identify role and task ID:
+
+| Message Pattern | Role |
+|----------------|------|
+| `[color-auditor]` or `COLOR-*` | color-auditor |
+| `[typo-auditor]` or `TYPO-*` | typo-auditor |
+| `[focus-auditor]` or `FOCUS-*` | focus-auditor |
+| `[remediation-planner]` or `REMED-*` | remediation-planner |
+| `[fix-implementer]` or `FIX-*` | fix-implementer |
+
+2. Mark task completed: `TaskUpdate({ taskId: "<task-id>", status: "completed" })`
+3. Record completion in session state
+
+4. Check checkpoint for completed task:
+
+| Completed Task | Checkpoint | Action |
+|---------------|------------|--------|
+| COLOR-001 | Parallel fan-in | Check if all 3 audits complete -> unblock REMED-001 |
+| TYPO-001 | Parallel fan-in | Check if all 3 audits complete -> unblock REMED-001 |
+| FOCUS-001 | Parallel fan-in | Check if all 3 audits complete -> unblock REMED-001 |
+| REMED-001 | -- | Unblock FIX-001 (full mode only) |
+| FIX-001 | GC check | Spawn COLOR-002 + FOCUS-002 in parallel (full mode) |
+| COLOR-002 | Re-audit fan-in | Check if both re-audits complete -> handleComplete |
+| FOCUS-002 | Re-audit fan-in | Check if both re-audits complete -> handleComplete |
+
+5. **Parallel fan-in handling** (audit task completed):
+
+   **CRITICAL**: REMED-001 must wait for ALL 3 auditors (COLOR-001 + TYPO-001 + FOCUS-001) to complete.
+
+   Check completion state:
+   ```
+   completed_audits = count of completed tasks in [COLOR-001, TYPO-001, FOCUS-001]
+   if completed_audits < 3:
+     -> Log "[coordinator] Audit fan-in: {completed_audits}/3 complete, waiting for remaining"
+     -> STOP (do NOT advance)
+   if completed_audits === 3:
+     -> Log "[coordinator] All 3 audits complete, advancing to REMED-001"
+     -> handleSpawnNext (will pick up REMED-001)
+   ```
+
+6. **GC loop handling** (full mode, after FIX-001 completes):
+
+   Read re-audit results when COLOR-002 and FOCUS-002 both complete:
+
+   | Signal | Condition | Action |
+   |--------|-----------|--------|
+   | All pass | No critical/high issues remaining | GC converged -> handleComplete |
+   | Issues remain | Critical/high issues found | gc_rounds < max -> create FIX-002 + re-audit tasks |
+   | Any | gc_rounds >= max | Escalate to user |
+
+   **GC Fix Task Creation** (when re-audit finds issues):
+   ```
+   TaskCreate({ subject: "FIX-002",
+     description: "PURPOSE: Address remaining issues from re-audit | Success: All critical/high issues resolved
+   TASK:
+     - Parse re-audit reports for remaining issues
+     - Apply targeted fixes for color and focus issues
+   CONTEXT:
+     - Session: <session-folder>
+     - Upstream artifacts: re-audit/color-audit-002.md, re-audit/focus-audit-002.md" })
+   TaskUpdate({ taskId: "FIX-002", addBlockedBy: ["COLOR-002", "FOCUS-002"], owner: "fix-implementer" })
+   ```
+   Then create new re-audit tasks blocked by FIX-002. Increment gc_state.round.
+
+   **GC Escalation Options** (when max rounds exceeded):
+   1. Accept current state - acknowledge remaining issues
+   2. Try one more round
+   3. Terminate
+
+7. -> handleSpawnNext
+
+## handleCheck
+
+Read-only status report, then STOP.
+
+```
+Pipeline Status (<pipeline-mode>):
+  [DONE]  COLOR-001 (color-auditor)        -> audits/color/color-audit-001.md
+  [DONE]  TYPO-001  (typo-auditor)         -> audits/typography/typo-audit-001.md
+  [RUN]   FOCUS-001 (focus-auditor)        -> auditing focus...
+  [WAIT]  REMED-001 (remediation-planner)  -> blocked by COLOR-001, TYPO-001, FOCUS-001
+  [WAIT]  FIX-001   (fix-implementer)      -> blocked by REMED-001
+  [WAIT]  COLOR-002 (color-auditor)        -> blocked by FIX-001
+  [WAIT]  FOCUS-002 (focus-auditor)        -> blocked by FIX-001
+
+Fan-in: 2/3 audits complete
+GC Rounds: 0/2
+Session: <session-id>
+Commands: 'resume' to advance | 'check' to refresh
+```
+
+Output status -- do NOT advance pipeline.
+
+## handleResume
+
+1. Audit task list for inconsistencies:
+   - Tasks stuck in "in_progress" -> reset to "pending"
+   - Tasks with completed blockers but still "pending" -> include in spawn list
+2. -> handleSpawnNext
+
+## handleSpawnNext
+
+Find ready tasks, spawn workers, STOP.
+
+1. Collect: completedSubjects, inProgressSubjects, readySubjects (pending + all blockedBy completed)
+2. No ready + work in progress -> report waiting, STOP
+3. No ready + nothing in progress -> handleComplete
+4. Has ready -> for each:
+   a. Check inner loop role with active worker -> skip (worker picks up)
+   b. TaskUpdate -> in_progress
+   c. team_msg log -> task_unblocked
+   d. Spawn team-worker:
+
+```
+Agent({
+  subagent_type: "team-worker",
+  description: "Spawn <role> worker for <task-id>",
+  team_name: "visual-a11y",
+  name: "<role>",
+  run_in_background: true,
+  prompt: `## Role Assignment
+role: <role>
+role_spec: <skill_root>/roles/<role>/role.md
+session: <session-folder>
+session_id: <session-id>
+team_name: visual-a11y
+requirement: <task-description>
+inner_loop: <true|false>
+
+Read role_spec file to load Phase 2-4 domain instructions.
+Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).`
+})
+```
+
+**Parallel spawn rules by mode**:
+
+| Mode | Scenario | Spawn Behavior |
+|------|----------|---------------|
+| audit-only | Initial | Spawn COLOR-001 + TYPO-001 + FOCUS-001 in parallel |
+| audit-only | After 3 audits complete | Spawn REMED-001 |
+| full | Initial | Spawn COLOR-001 + TYPO-001 + FOCUS-001 in parallel |
+| full | After 3 audits complete | Spawn REMED-001 |
+| full | After REMED-001 | Spawn FIX-001 |
+| full | After FIX-001 | Spawn COLOR-002 + FOCUS-002 in parallel |
+
+5. Add to active_workers, update session, output summary, STOP
+
+## handleComplete
+
+Pipeline done. Generate report and completion action.
+
+**Completion check by mode**:
+
+| Mode | Completion Condition |
+|------|---------------------|
+| audit-only | All 4 tasks (+ any fix tasks) completed |
+| full | All 7 tasks (+ any GC fix tasks) completed |
+
+1. If any tasks not completed -> handleSpawnNext
+2. If all completed -> transition to coordinator Phase 5
+
+## handleAdapt
+
+Capability gap reported mid-pipeline.
+
+1. Parse gap description
+2. Check if existing role covers it -> redirect
+3. Role count < 6 -> generate dynamic role spec
+4. Create new task, spawn worker
+5. Role count >= 6 -> merge or pause
+
+## Fast-Advance Reconciliation
+
+On every coordinator wake:
+1. Read team_msg entries with type="fast_advance"
+2. Sync active_workers with spawned successors
+3. No duplicate spawns

package/.claude/skills/team-visual-a11y/roles/coordinator/role.md

@@ -0,0 +1,169 @@
+# Coordinator Role
+
+Visual Accessibility Team coordinator. Orchestrate pipeline: analyze -> dispatch -> spawn -> monitor -> report. Manages parallel fan-in (3 auditors), remediation synthesis, fix implementation, and optional re-audit GC loop.
+
+## Identity
+- **Name**: coordinator | **Tag**: [coordinator]
+- **Responsibility**: Analyze scope -> Create team -> Dispatch tasks -> Monitor progress -> Report results
+
+## Boundaries
+
+### MUST
+- All output (SendMessage, team_msg, logs) must carry `[coordinator]` identifier
+- Use `team-worker` agent type for all worker spawns (NOT `general-purpose`)
+- Dispatch tasks with proper dependency chains and blockedBy
+- Spawn COLOR-001, TYPO-001, FOCUS-001 in PARALLEL (no blockedBy between them)
+- Monitor worker progress via message bus and route messages
+- Handle Generator-Critic loops with max 2 iterations
+- Maintain session state persistence
+
+### MUST NOT
+- Implement domain logic (auditing, planning, fixing) -- workers handle this
+- Spawn workers without creating tasks first
+- Skip sync points when configured
+- Force-advance pipeline past failed audit
+- Modify source code or design artifacts directly -- delegate to workers
+- Omit `[coordinator]` identifier in any output
+
+## Command Execution Protocol
+
+When coordinator needs to execute a command (analyze, dispatch, monitor):
+
+1. Read `commands/<command>.md`
+2. Follow the workflow defined in the command
+3. Commands are inline execution guides, NOT separate agents
+4. Execute synchronously, complete before proceeding
+
+## Entry Router
+
+| Detection | Condition | Handler |
+|-----------|-----------|---------|
+| Worker callback | Message contains [color-auditor], [typo-auditor], [focus-auditor], [remediation-planner], [fix-implementer] | -> handleCallback (monitor.md) |
+| Status check | Args contain "check" or "status" | -> handleCheck (monitor.md) |
+| Manual resume | Args contain "resume" or "continue" | -> handleResume (monitor.md) |
+| Capability gap | Message contains "capability_gap" | -> handleAdapt (monitor.md) |
+| Pipeline complete | All tasks have status "completed" | -> handleComplete (monitor.md) |
+| Interrupted session | Active/paused session exists in .workflow/.team/VA-* | -> Phase 0 |
+| New session | None of above | -> Phase 1 |
+
+For callback/check/resume/adapt/complete: load `@commands/monitor.md`, execute matched handler, STOP.
+
+## Phase 0: Session Resume Check
+
+1. Scan `.workflow/.team/VA-*/.msg/meta.json` for active/paused sessions
+2. No sessions -> Phase 1
+3. Single session -> reconcile (audit TaskList, reset in_progress->pending, rebuild team, kick first ready task)
+4. Multiple -> AskUserQuestion for selection
+
+## Phase 1: Requirement Clarification
+
+TEXT-LEVEL ONLY. No source code reading.
+
+1. Parse task description from arguments
+2. Detect audit scope:
+
+| Signal | Pipeline Mode |
+|--------|---------------|
+| "audit only", "no fixes", "assessment" | audit-only |
+| "full audit", "fix", "remediate", "full cycle" | full |
+| Unclear | ask user |
+
+3. Ask for missing parameters if scope unclear:
+   ```
+   AskUserQuestion({
+     questions: [
+       { question: "Accessibility audit scope?", header: "Scope", options: [
+         { label: "Audit only", description: "Color + typography + focus audit with remediation plan" },
+         { label: "Full cycle", description: "Audit + fix + re-audit verification" }
+       ]},
+       { question: "Target?", header: "Target", options: [
+         { label: "URL (rendered page)" },
+         { label: "Component path (source)" },
+         { label: "Full site" }
+       ]}
+     ]
+   })
+   ```
+4. Delegate to `@commands/analyze.md` -> output scope context
+5. Record: pipeline_mode, target, wcag_level
+
+## Phase 2: Create Team + Initialize Session
+
+1. Resolve workspace paths (MUST do first):
+   - `project_root` = result of `Bash({ command: "pwd" })`
+   - `skill_root` = `<project_root>/.claude/skills/team-visual-a11y`
+2. Generate session ID: `VA-<slug>-<YYYY-MM-DD>`
+3. Create session folder structure:
+   ```
+   .workflow/.team/VA-<slug>-<date>/audits/color/
+   .workflow/.team/VA-<slug>-<date>/audits/typography/
+   .workflow/.team/VA-<slug>-<date>/audits/focus/
+   .workflow/.team/VA-<slug>-<date>/remediation/
+   .workflow/.team/VA-<slug>-<date>/fixes/
+   .workflow/.team/VA-<slug>-<date>/re-audit/
+   .workflow/.team/VA-<slug>-<date>/evidence/
+   .workflow/.team/VA-<slug>-<date>/.msg/
+   ```
+4. Initialize `.msg/meta.json` via team_msg state_update with pipeline metadata
+5. TeamCreate(team_name="visual-a11y")
+6. Do NOT spawn workers yet - deferred to Phase 4
+
+## Phase 3: Create Task Chain
+
+Delegate to `@commands/dispatch.md`. Task chains by mode:
+
+| Mode | Task Chain |
+|------|------------|
+| audit-only | [COLOR-001 + TYPO-001 + FOCUS-001 parallel] -> REMED-001 |
+| full | [COLOR-001 + TYPO-001 + FOCUS-001 parallel] -> REMED-001 -> FIX-001 -> [COLOR-002 + FOCUS-002 parallel] |
+
+## Phase 4: Spawn-and-Stop
+
+**CRITICAL**: Spawn COLOR-001, TYPO-001, FOCUS-001 in PARALLEL (all 3 have NO blockedBy).
+
+Delegate to `@commands/monitor.md#handleSpawnNext`:
+1. Find ready tasks (pending + blockedBy resolved)
+2. Spawn team-worker agents (see SKILL.md Spawn Template)
+3. Output status summary
+4. STOP
+
+## Phase 5: Report + Completion Action
+
+1. Read session state -> collect all results
+2. List deliverables:
+
+| Deliverable | Path |
+|-------------|------|
+| Color Audit | <session>/audits/color/color-audit-001.md |
+| Typography Audit | <session>/audits/typography/typo-audit-001.md |
+| Focus Audit | <session>/audits/focus/focus-audit-001.md |
+| Remediation Plan | <session>/remediation/remediation-plan.md |
+| Fix Summary | <session>/fixes/fix-summary-001.md (full mode) |
+| Re-audit Color | <session>/re-audit/color-audit-002.md (full mode) |
+| Re-audit Focus | <session>/re-audit/focus-audit-002.md (full mode) |
+| Evidence | <session>/evidence/*.png (if Chrome DevTools used) |
+
+3. Calculate: completed_tasks, gc_rounds, issues_found, issues_fixed, wcag_compliance_level
+4. Output pipeline summary with [coordinator] prefix
+5. Execute completion action:
+   ```
+   AskUserQuestion({
+     questions: [{ question: "Pipeline complete. What next?", header: "Completion", options: [
+       { label: "Archive & Clean", description: "Archive session and clean up team resources" },
+       { label: "Keep Active", description: "Keep session for follow-up work" },
+       { label: "Export Results", description: "Export deliverables to specified location" }
+     ]}]
+   })
+   ```
+
+## Error Handling
+
+| Error | Resolution |
+|-------|------------|
+| Task timeout | Log, mark failed, ask user to retry or skip |
+| Worker crash | Reset task to pending, respawn worker |
+| Dependency cycle | Detect, report to user, halt |
+| Invalid scope | Reject with error, ask to clarify |
+| Session corruption | Attempt recovery, fallback to manual reconciliation |
+| GC loop stuck > 2 rounds | Escalate to user: accept / try one more / terminate |
+| Chrome DevTools unavailable | Mark in meta.json, auditors degrade to static analysis |