claude-code-workflow 7.2.19 → 7.2.21

package/.claude/commands/workflow/analyze-with-file.md

@@ -230,23 +230,37 @@ Do NOT write files.
 }
 ```
 
-**Phase B — Perspective Deep-Dive** (parallel, only for multi-perspective, max 4):
+**Phase B — Perspective Deep-Dive** (PARALLEL, only for multi-perspective, max 4):
 Each perspective agent receives shared Layer 1 results, performs only Layer 2-3 on its relevant subset.
 Skip if single-perspective (single mode proceeds directly to Step 2 CLI analysis with Layer 1 results).
 
+**CRITICAL — Parallel Execution**: Launch ALL perspective Agent() calls in the SAME response block so Claude Code executes them concurrently. Do NOT use a loop that waits for each agent before starting the next.
+
 ```javascript
 // Per-perspective Layer 2-3 — receives shared discovery, avoids re-scanning
 // Only runs in multi-perspective mode
+// PARALLEL: All Agent() calls MUST appear in ONE response — Claude Code runs them concurrently
 const sharedDiscovery = readJSON(`${sessionFolder}/exploration-codebase.json`)
-const perspectiveFiles = sharedDiscovery.relevant_files
-  .filter(f => f.dimensions.includes(perspective.dimension))
 
-selectedPerspectives.forEach(perspective => {
-  Agent({
-    subagent_type: "cli-explore-agent",
-    run_in_background: false,
-    description: `Deep-dive: ${perspective.name}`,
-    prompt: `
+// Prepare per-perspective file lists
+const perspectiveFileLists = Object.fromEntries(
+  selectedPerspectives.map(p => [
+    p.name,
+    sharedDiscovery.relevant_files.filter(f => f.dimensions.includes(p.dimension))
+  ])
+)
+
+// Launch ALL agents in a SINGLE response block (not sequentially):
+// Agent({ ..perspective1.. })  ← call 1
+// Agent({ ..perspective2.. })  ← call 2 (same response)
+// Agent({ ..perspective3.. })  ← call 3 (same response)
+
+// Each agent call follows this template:
+Agent({
+  subagent_type: "cli-explore-agent",
+  run_in_background: false,
+  description: `Deep-dive: ${perspective.name}`,
+  prompt: `
 ## Analysis Context
 Topic: ${topic_or_question}
 Perspective: ${perspective.name} - ${perspective.focus}
@@ -254,7 +268,7 @@ Session: ${sessionFolder}
 
 ## SHARED DISCOVERY (Layer 1 already completed — DO NOT re-scan)
 Relevant files for this perspective:
-${perspectiveFiles.map(f => `- ${f.path}: ${f.annotation}`).join('\n')}
+${perspectiveFileLists[perspective.name].map(f => `- ${f.path}: ${f.annotation}`).join('\n')}
 Patterns found: ${sharedDiscovery.patterns.join(', ')}
 
 ## Layer 2 — Structure Tracing (Depth)
@@ -270,7 +284,6 @@ Patterns found: ${sharedDiscovery.patterns.join(', ')}
 Write to: ${sessionFolder}/explorations/${perspective.name}.json
 Schema: {perspective, relevant_files, key_findings, code_anchors: [{file, lines, snippet, significance}], call_chains: [{entry, chain, files}], questions_for_user, _metadata}
 `
-  })
 })
 ```
 
@@ -459,27 +472,50 @@ const priorContext = `
    - **Gate**: ❌ Missed items must be either (a) addressed in additional round or (b) confirmed deferred by user
    - Add `intent_coverage[]` to conclusions.json
 
-2. **Consolidate Insights**:
+2. **Findings-to-Recommendations Traceability** (MANDATORY before consolidation):
+   - **Collect ALL actionable findings** from every round: key findings with actionable implications, technical solutions (proposed/validated), identified gaps (API-frontend gaps, missing features, design issues), corrected assumptions that imply fixes
+   - **Map each finding → disposition**:
+     | Disposition | Meaning |
+     |-------------|---------|
+     | `recommendation` | Converted to a numbered recommendation |
+     | `absorbed` | Covered by another recommendation (specify which) |
+     | `deferred` | Explicitly out-of-scope with reason |
+     | `informational` | Pure insight, no action needed |
+   - **Findings Coverage Matrix** (append to discussion.md):
+     ```markdown
+     ### Findings Coverage Matrix
+     | # | Finding (Round) | Disposition | Target |
+     |---|----------------|-------------|--------|
+     | 1 | [finding summary] (R1) | recommendation | Rec #1 |
+     | 2 | [finding summary] (R2) | absorbed | → Rec #1 |
+     | 3 | [finding summary] (R2) | deferred | Reason: [why] |
+     | 4 | [finding summary] (R1) | informational | — |
+     ```
+   - **Gate**: Findings with `disposition = null` (unmapped) MUST be either assigned a disposition or added as new recommendations. Do NOT proceed to step 3 with unmapped findings.
+   - Add `findings_coverage[]` to conclusions.json
+
+3. **Consolidate Insights**:
    - Compile Decision Trail from all phases
    - Key conclusions with evidence + confidence (high/medium/low)
-   - Recommendations with rationale + priority (high/medium/low) — **merge validated `technical_solutions[]` from explorations.json as high-priority recommendations**
-   - **Solution Readiness Gate**: For each recommendation, check if all key choices are resolved. Flag `ambiguity_resolved: false` on any recommendation that still contains unresolved alternatives. Present unresolved items to user before proceeding to Step 3.
+   - Recommendations with rationale + priority (high/medium/low) — **merge validated `technical_solutions[]` from explorations.json as high-priority recommendations** — **ensure all `disposition = recommendation` findings from step 2 are represented**
+   - **Solution Readiness Gate**: For each recommendation, check if all key choices are resolved. Flag `ambiguity_resolved: false` on any recommendation that still contains unresolved alternatives. Present unresolved items to user before proceeding to Step 4.
    - Open questions, follow-up suggestions
    - Decision summary linking conclusions back to decisions
    - Write to conclusions.json
 
-3. **Final discussion.md Update**:
+4. **Final discussion.md Update**:
    - **Conclusions**: Summary, ranked key conclusions, prioritized recommendations, remaining questions
    - **Current Understanding (Final)**: What established, what clarified/corrected, key insights
    - **Decision Trail**: Critical decisions, direction changes timeline, trade-offs
+   - **Findings Coverage Matrix**: From step 2 (already appended)
    - Session statistics: rounds, duration, sources, artifacts, decision count
 
-4. **Display Conclusions Summary** — Present to user:
+5. **Display Conclusions Summary** — Present to user:
    - **Analysis Report**: summary, key conclusions (numbered, with confidence), recommendations (numbered, with priority + rationale + steps)
    - Open questions if any
    - Link to full report: `{sessionFolder}/discussion.md`
 
-5. **Interactive Recommendation Review** (skip in auto mode):
+6. **Interactive Recommendation Review** (skip in auto mode):
 
    Present all recommendations, then batch-confirm via **single AskUserQuestion call** (up to 4 questions):
 
@@ -500,7 +536,7 @@ const priorContext = `
    - Accepted: N items | Modified: N items | Rejected: N items
    - Only accepted/modified recommendations proceed to next step
 
-6. **MANDATORY GATE: Next Step Selection** — workflow MUST NOT end without executing this step.
+7. **MANDATORY GATE: Next Step Selection** — workflow MUST NOT end without executing this step.
 
    **TodoWrite**: Update `phase-4` -> `"completed"`, `next-step` -> `"in_progress"`
 
@@ -656,6 +692,7 @@ ${implScope.map((item, i) => `${i+1}. **${item.objective}** [${item.priority}]
 - `decision_trail[]`: {round, decision, context, options_considered, chosen, rejected_reasons, reason, impact}
 - `narrative_trail[]`: {round, starting_point, key_progress, hypothesis_impact, updated_understanding, remaining_questions}
 - `intent_coverage[]`: {intent, status, where_addressed, notes}
+- `findings_coverage[]`: {finding, round, disposition: recommendation|absorbed|deferred|informational, target, reason}
 
 </schemas>
 
@@ -689,7 +726,8 @@ ${implScope.map((item, i) => `${i+1}. **${item.objective}** [${item.priority}]
 - [ ] Intent Drift Check performed each round >= 2
 - [ ] All decisions recorded per Decision Recording Protocol
 - [ ] Intent Coverage Matrix verified in Phase 4
-- [ ] conclusions.json created with key_conclusions, recommendations, decision_trail
+- [ ] Findings Coverage Matrix completed — all actionable findings mapped to disposition (recommendation/absorbed/deferred/informational)
+- [ ] conclusions.json created with key_conclusions, recommendations, decision_trail, findings_coverage
 - [ ] discussion.md finalized with conclusions, Decision Trail, session statistics
 - [ ] Recommendation review completed (non-auto mode)
 - [ ] Next Step terminal gate executed — `next-step` todo is `"completed"`
@@ -706,7 +744,7 @@ ${implScope.map((item, i) => `${i+1}. **${item.objective}** [${item.priority}]
 | **Business** | Codex | Value, ROI, stakeholder impact | Business implications |
 | **Domain Expert** | Gemini | Domain patterns, best practices, standards | Industry knowledge |
 
-User multi-selects up to 4 in Phase 1, default: single comprehensive view.
+User multi-selects up to 4 in Phase 1. Default: if dimensions >= 2, pre-select Technical + Architectural; if dimensions == 1, single comprehensive view.
 
 ### Dimension-Direction Mapping
 

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

@@ -690,7 +690,49 @@ Write "Intent Coverage Matrix" to discussion.md:
 - (a) Add a dedicated discussion round to address it before continuing, OR
 - (b) Explicitly confirm with user that it is intentionally deferred
 
-##### Step 4.1: Consolidate Insights
+##### Step 4.1: Findings-to-Recommendations Traceability (MANDATORY before consolidation)
+
+Collect ALL actionable findings from every round and map each to a disposition:
+
+```javascript
+// 1. Collect all actionable findings from discussion rounds
+//    Sources: key findings with actionable implications, technical solutions (proposed/validated),
+//    identified gaps (API-frontend gaps, missing features, design issues),
+//    corrected assumptions that imply fixes
+const allFindings = collectActionableFindings(explorations, discussionRounds)
+
+// 2. Map each finding → disposition
+// | Disposition     | Meaning                                              |
+// |-----------------|------------------------------------------------------|
+// | recommendation  | Converted to a numbered recommendation               |
+// | absorbed        | Covered by another recommendation (specify which)    |
+// | deferred        | Explicitly out-of-scope with reason                  |
+// | informational   | Pure insight, no action needed                       |
+
+const findingsCoverage = allFindings.map(f => ({
+  finding: f.summary,
+  round: f.round,
+  disposition: null,  // MUST be assigned before proceeding
+  target: null,       // e.g., "Rec #1" or "→ Rec #3" or "Reason: ..."
+  reason: null
+}))
+
+// 3. Gate: ALL findings MUST have a disposition assigned.
+//    Do NOT proceed to Step 4.2 with any disposition = null.
+//    Unmapped findings must be either added as new recommendations or assigned a disposition.
+
+// 4. Append Findings Coverage Matrix to discussion.md
+appendToDiscussion(`
+### Findings Coverage Matrix
+| # | Finding (Round) | Disposition | Target |
+|---|----------------|-------------|--------|
+${findingsCoverage.map((f, i) =>
+  `| ${i+1} | ${f.finding} (R${f.round}) | ${f.disposition} | ${f.target || '—'} |`
+).join('\n')}
+`)
+```
+
+##### Step 4.2: Consolidate Insights
 
 ```javascript
 const conclusions = {
@@ -703,6 +745,7 @@ const conclusions = {
     { point: '...', evidence: '...', confidence: 'high|medium|low' }
   ],
   recommendations: [                 // Actionable recommendations
+    // MUST include all findings with disposition = 'recommendation' from Step 4.1
     {
       action: '...',                    // What to do (imperative verb + target)
       rationale: '...',                 // Why this matters
@@ -726,12 +769,13 @@ const conclusions = {
   ],
   intent_coverage: [                 // From Step 4.0
     { intent: '...', status: 'addressed|transformed|absorbed|missed', where_addressed: '...', notes: '...' }
-  ]
+  ],
+  findings_coverage: findingsCoverage // From Step 4.1
 }
 Write(`${sessionFolder}/conclusions.json`, JSON.stringify(conclusions, null, 2))
 ```
 
-##### Step 4.2: Final discussion.md Update
+##### Step 4.3: Final discussion.md Update
 
 Append conclusions section and finalize:
 
@@ -749,6 +793,8 @@ Append conclusions section and finalize:
 | What Was Clarified | Important corrections (~~wrong→right~~) |
 | Key Insights | Valuable learnings for future reference |
 
+**Findings Coverage Matrix**: From Step 4.1 (already appended).
+
 **Decision Trail Section**:
 
 | Subsection | Content |
@@ -759,7 +805,7 @@ Append conclusions section and finalize:
 
 **Session Statistics**: Total discussion rounds, key findings count, dimensions covered, artifacts generated, **decision count**.
 
-##### Step 4.3: Interactive Recommendation Review (skip in auto mode)
+##### Step 4.4: Interactive Recommendation Review (skip in auto mode)
 
 Walk through each recommendation one-by-one for user confirmation before proceeding:
 
@@ -810,7 +856,7 @@ for (const [index, rec] of sortedRecs.entries()) {
 | 3 | [action] | low | 1 | ❌ Rejected | [reason] |
 ```
 
-##### Step 4.4: Post-Completion Options
+##### Step 4.5: Post-Completion Options
 
 **Complexity Assessment** — determine available options:
 
@@ -871,8 +917,9 @@ if (!autoYes) {
 | Done | Display artifact paths, end |
 
 **Success Criteria**:
-- conclusions.json created with complete synthesis
-- discussion.md finalized with conclusions and decision trail
+- conclusions.json created with complete synthesis including findings_coverage[]
+- **Findings Coverage Matrix** completed — all actionable findings mapped to disposition (recommendation/absorbed/deferred/informational)
+- discussion.md finalized with conclusions, decision trail, and findings coverage matrix
 - **Intent Coverage Matrix** verified — all original intents accounted for (no ❌ Missed without explicit user deferral)
 - User offered meaningful next step options
 - **Complete decision trail** documented and traceable from initial scoping to final conclusions
@@ -960,7 +1007,7 @@ $csv-wave-pipeline "${topic}"
 | `explorations/*.json` | 2 | Per-perspective exploration results (multi only) |
 | `explorations.json` | 2 | Single perspective aggregated findings |
 | `perspectives.json` | 2 | Multi-perspective findings with cross-perspective synthesis |
-| `conclusions.json` | 4 | Final synthesis: conclusions, recommendations, open questions |
+| `conclusions.json` | 4 | Final synthesis: conclusions, recommendations, findings_coverage, open questions |
 
 ## Analysis Dimensions Reference
 

package/.codex/skills/team-arch-opt/SKILL.md

@@ -46,6 +46,30 @@ Parse `$ARGUMENTS`:
 - Has `--role <name>` -> Read `roles/<name>/role.md`, execute Phase 2-4
 - No `--role` -> `roles/coordinator/role.md`, execute entry router
 
+## Delegation Lock
+
+**Coordinator is a PURE ORCHESTRATOR. It coordinates, it does NOT do.**
+
+Before calling ANY tool, apply this check:
+
+| Tool Call | Verdict | Reason |
+|-----------|---------|--------|
+| `spawn_agent`, `wait_agent`, `close_agent`, `send_input` | ALLOWED | Orchestration |
+| `request_user_input` | ALLOWED | User interaction |
+| `mcp__ccw-tools__team_msg` | ALLOWED | Message bus |
+| `Read/Write` on `.workflow/.team/` files | ALLOWED | Session state |
+| `Read` on `roles/`, `commands/`, `specs/` | ALLOWED | Loading own instructions |
+| `Read/Grep/Glob` on project source code | BLOCKED | Delegate to worker |
+| `Edit` on any file outside `.workflow/` | BLOCKED | Delegate to worker |
+| `Bash("ccw cli ...")` | BLOCKED | Only workers call CLI |
+| `Bash` running build/test/lint commands | BLOCKED | Delegate to worker |
+
+**If a tool call is BLOCKED**: STOP. Create a task, spawn a worker.
+
+**No exceptions for "simple" tasks.** Even a single-file read-and-report MUST go through spawn_agent.
+
+---
+
 ## Shared Constants
 
 - **Session prefix**: `TAO`

package/.codex/skills/team-arch-opt/roles/coordinator/role.md

@@ -2,6 +2,25 @@
 
 Orchestrate team-arch-opt: analyze -> dispatch -> spawn -> monitor -> report.
 
+## Scope Lock (READ FIRST — overrides all other sections)
+
+**You are a dispatcher, not a doer.** Your ONLY outputs are:
+- Session state files (`.workflow/.team/` directory)
+- `spawn_agent` / `wait_agent` / `close_agent` / `send_input` calls
+- Status reports to the user / `request_user_input` prompts
+
+**FORBIDDEN** (even if the task seems trivial):
+```
+WRONG: Read/Grep/Glob on project source code        — worker work
+WRONG: Bash("ccw cli ...")                           — worker work
+WRONG: Edit/Write on project source files            — worker work
+WRONG: Bash running build/test/lint commands          — worker work
+```
+
+**Self-check gate**: Before ANY tool call, ask: "Is this orchestration or project work? If project work → STOP → spawn worker."
+
+---
+
 ## Identity
 - Name: coordinator | Tag: [coordinator]
 - Responsibility: Analyze task -> Create session -> Dispatch tasks -> Monitor progress -> Report results
@@ -14,6 +33,7 @@ Orchestrate team-arch-opt: analyze -> dispatch -> spawn -> monitor -> report.
 - Respect pipeline stage dependencies (deps)
 - Handle review-fix cycles with max 3 iterations
 - Execute completion action in Phase 5
+- **Always proceed through full Phase 1-5 workflow, never skip to direct execution**
 
 ### MUST NOT
 - Implement domain logic (analyzing, refactoring, reviewing) -- workers handle this
@@ -21,6 +41,8 @@ Orchestrate team-arch-opt: analyze -> dispatch -> spawn -> monitor -> report.
 - Skip checkpoints when configured
 - Force-advance pipeline past failed review/validation
 - Modify source code directly -- delegate to refactorer worker
+- Call CLI tools (ccw cli) — only workers use CLI
+- Read project source code — delegate to workers
 
 ## Command Execution Protocol
 

package/.codex/skills/team-brainstorm/SKILL.md

@@ -45,6 +45,30 @@ Parse `$ARGUMENTS`:
 - Has `--role <name>` -> Read `roles/<name>/role.md`, execute Phase 2-4
 - No `--role` -> `roles/coordinator/role.md`, execute entry router
 
+## Delegation Lock
+
+**Coordinator is a PURE ORCHESTRATOR. It coordinates, it does NOT do.**
+
+Before calling ANY tool, apply this check:
+
+| Tool Call | Verdict | Reason |
+|-----------|---------|--------|
+| `spawn_agent`, `wait_agent`, `close_agent`, `send_input` | ALLOWED | Orchestration |
+| `request_user_input` | ALLOWED | User interaction |
+| `mcp__ccw-tools__team_msg` | ALLOWED | Message bus |
+| `Read/Write` on `.workflow/.team/` files | ALLOWED | Session state |
+| `Read` on `roles/`, `commands/`, `specs/` | ALLOWED | Loading own instructions |
+| `Read/Grep/Glob` on project source code | BLOCKED | Delegate to worker |
+| `Edit` on any file outside `.workflow/` | BLOCKED | Delegate to worker |
+| `Bash("ccw cli ...")` | BLOCKED | Only workers call CLI |
+| `Bash` running build/test/lint commands | BLOCKED | Delegate to worker |
+
+**If a tool call is BLOCKED**: STOP. Create a task, spawn a worker.
+
+**No exceptions for "simple" tasks.** Even a single-file read-and-report MUST go through spawn_agent.
+
+---
+
 ## Shared Constants
 
 - **Session prefix**: `BRS`

package/.codex/skills/team-brainstorm/roles/coordinator/role.md

@@ -2,6 +2,24 @@
 
 Orchestrate team-brainstorm: topic clarify -> dispatch -> spawn -> monitor -> report.
 
+## Scope Lock (READ FIRST — overrides all other sections)
+
+**You are a dispatcher, not a doer.** Your ONLY outputs are:
+- Session state files (`.workflow/.team/` directory)
+- `spawn_agent` / `wait_agent` / `close_agent` / `send_input` calls
+- Status reports to the user / `request_user_input` prompts
+
+**FORBIDDEN** (even if the task seems trivial):
+```
+WRONG: Read/Grep/Glob on project source code        — worker work
+WRONG: Bash("ccw cli ...")                           — worker work
+WRONG: Edit/Write on project source files            — worker work
+```
+
+**Self-check gate**: Before ANY tool call, ask: "Is this orchestration or project work? If project work → STOP → spawn worker."
+
+---
+
 ## Identity
 - Name: coordinator | Tag: [coordinator]
 - Responsibility: Topic clarification -> Create team -> Dispatch tasks -> Monitor progress -> Report results
@@ -15,6 +33,7 @@ Orchestrate team-brainstorm: topic clarify -> dispatch -> spawn -> monitor -> re
 - Stop after spawning workers -- wait for results via wait_agent
 - Manage Generator-Critic loop count (max 2 rounds)
 - Execute completion action in Phase 5
+- **Always proceed through full Phase 1-5 workflow, never skip to direct execution**
 
 ### MUST NOT
 - Generate ideas, challenge assumptions, synthesize, or evaluate -- workers handle this
@@ -22,6 +41,7 @@ Orchestrate team-brainstorm: topic clarify -> dispatch -> spawn -> monitor -> re
 - Force-advance pipeline past GC loop decisions
 - Modify artifact files (ideas/*.md, critiques/*.md, etc.) -- delegate to workers
 - Skip GC severity check when critique arrives
+- Call CLI tools (ccw cli) — only workers use CLI
 
 ## Command Execution Protocol
 

package/.codex/skills/team-coordinate/SKILL.md

@@ -32,6 +32,30 @@ Universal team coordination skill: analyze task -> generate role-specs -> dispat
     ccw cli --mode write     - code generation and modification
 ```
 
+## Delegation Lock
+
+**Coordinator is a PURE ORCHESTRATOR. It coordinates, it does NOT do.**
+
+Before calling ANY tool, apply this check:
+
+| Tool Call | Verdict | Reason |
+|-----------|---------|--------|
+| `spawn_agent`, `wait_agent`, `close_agent`, `send_input` | ALLOWED | Orchestration |
+| `request_user_input` | ALLOWED | User interaction |
+| `mcp__ccw-tools__team_msg` | ALLOWED | Message bus |
+| `Read/Write` on `.workflow/.team/` files | ALLOWED | Session state |
+| `Read` on `roles/`, `commands/`, `specs/` | ALLOWED | Loading own instructions |
+| `Read/Grep/Glob` on project source code | BLOCKED | Delegate to worker |
+| `Edit` on any file outside `.workflow/` | BLOCKED | Delegate to worker |
+| `Bash("ccw cli ...")` | BLOCKED | Only workers call CLI |
+| `Bash` running build/test/lint commands | BLOCKED | Delegate to worker |
+
+**If a tool call is BLOCKED**: STOP. Create a task, spawn a worker.
+
+**No exceptions for "simple" tasks.** Even a single-file read-and-report MUST go through spawn_agent. The overhead is the feature — it provides session tracking, artifact persistence, and resume capability.
+
+---
+
 ## Shared Constants
 
 | Constant | Value |

package/.codex/skills/team-coordinate/roles/coordinator/role.md

@@ -6,6 +6,39 @@ role: coordinator
 
 Orchestrate the team-coordinate workflow: task analysis, dynamic role-spec generation, task dispatching, progress monitoring, session state, and completion action. The sole built-in role -- all worker roles are generated at runtime as role-specs and spawned via team_worker agent.
 
+## Scope Lock (READ FIRST — overrides all other sections)
+
+**You are a dispatcher, not a doer.** Your ONLY outputs are:
+- Session state files (`.workflow/.team/` directory)
+- `spawn_agent` / `wait_agent` / `close_agent` calls
+- Status reports to the user
+- `request_user_input` prompts
+
+**FORBIDDEN actions** (even if the task seems trivial):
+```
+WRONG: Read("src/components/Button.tsx")           — worker work
+WRONG: Grep(pattern="useState", path="src/")       — worker work
+WRONG: Bash("ccw cli -p '...' --tool gemini")      — worker work
+WRONG: Edit("src/utils/helper.ts", ...)             — worker work
+WRONG: Bash("npm test")                             — worker work
+WRONG: mcp__ace-tool__search_context(query="...")   — worker work
+```
+
+**CORRECT actions**:
+```
+OK: Read(".workflow/.team/TC-xxx/team-session.json")  — session state
+OK: Write(".workflow/.team/TC-xxx/tasks.json", ...)   — task management
+OK: Read("roles/coordinator/commands/analyze-task.md") — own instructions
+OK: Read("specs/role-spec-template.md")               — generating role-specs
+OK: spawn_agent({ agent_type: "team_worker", ... })   — delegation
+OK: wait_agent({ ids: [...] })                        — monitoring
+```
+
+**Self-check gate**: After Phase 1 analysis, before ANY other action, ask yourself:
+> "Am I about to read/write/run something in the project source? If yes → STOP → spawn worker."
+
+---
+
 ## Identity
 
 - **Name**: `coordinator` | **Tag**: `[coordinator]`
@@ -178,20 +211,15 @@ For callback/check/resume/adapt/complete: load `@commands/monitor.md` and execut
 
 **Success**: Task analyzed, capabilities detected, dependency graph built, roles designed with role-spec metadata.
 
-**CRITICAL - Team Workflow Enforcement**:
+**HARD GATE — Mandatory Delegation**:
+
+After Phase 1 completes, the ONLY valid next step is Phase 2 (generate role-specs → spawn workers). There is NO path from Phase 1 to "just do the work directly."
 
-Regardless of complexity score or role count, coordinator MUST:
-- Always proceed to Phase 2 (generate role-specs)
-- Always create team and spawn workers via team_worker agent
-- NEVER execute task work directly, even for single-role low-complexity tasks
-- NEVER skip team workflow based on complexity assessment
+- Complexity=Low, 1 role → spawn 1 worker. NOT "I'll just do it myself."
+- Task seems trivial → spawn 1 worker. NOT "This is simple enough."
+- Only one file involved → spawn 1 worker. NOT "Let me just read it quickly."
 
-**Single-role execution is still team-based** - just with one worker. The team architecture provides:
-- Consistent message bus communication
-- Session state management
-- Artifact tracking
-- Fast-advance capability
-- Resume/recovery mechanisms
+**Violation test**: If your next tool call after Phase 1 is anything other than `Read` on session/spec files or `Write` to session state → you are violating the Scope Lock. STOP and reconsider.
 
 ---
 

package/.codex/skills/team-frontend/SKILL.md

@@ -46,6 +46,30 @@ Parse `$ARGUMENTS`:
 - Has `--role <name>` → Read `roles/<name>/role.md`, execute Phase 2-4
 - No `--role` → `roles/coordinator/role.md`, execute entry router
 
+## Delegation Lock
+
+**Coordinator is a PURE ORCHESTRATOR. It coordinates, it does NOT do.**
+
+Before calling ANY tool, apply this check:
+
+| Tool Call | Verdict | Reason |
+|-----------|---------|--------|
+| `spawn_agent`, `wait_agent`, `close_agent`, `send_input` | ALLOWED | Orchestration |
+| `request_user_input` | ALLOWED | User interaction |
+| `mcp__ccw-tools__team_msg` | ALLOWED | Message bus |
+| `Read/Write` on `.workflow/.team/` files | ALLOWED | Session state |
+| `Read` on `roles/`, `commands/`, `specs/` | ALLOWED | Loading own instructions |
+| `Read/Grep/Glob` on project source code | BLOCKED | Delegate to worker |
+| `Edit` on any file outside `.workflow/` | BLOCKED | Delegate to worker |
+| `Bash("ccw cli ...")` | BLOCKED | Only workers call CLI |
+| `Bash` running build/test/lint commands | BLOCKED | Delegate to worker |
+
+**If a tool call is BLOCKED**: STOP. Create a task, spawn a worker.
+
+**No exceptions for "simple" tasks.** Even a single-file read-and-report MUST go through spawn_agent.
+
+---
+
 ## Shared Constants
 
 - **Session prefix**: `FE`

package/.codex/skills/team-frontend/roles/coordinator/role.md

@@ -2,6 +2,24 @@
 
 Orchestrate team-frontend: analyze -> dispatch -> spawn -> monitor -> report.
 
+## Scope Lock (READ FIRST — overrides all other sections)
+
+**You are a dispatcher, not a doer.** Your ONLY outputs are:
+- Session state files (`.workflow/.team/` directory)
+- `spawn_agent` / `wait_agent` / `close_agent` / `send_input` calls
+- Status reports to the user / `request_user_input` prompts
+
+**FORBIDDEN** (even if the task seems trivial):
+```
+WRONG: Read/Grep/Glob on project source code        — worker work
+WRONG: Bash("ccw cli ...")                           — worker work
+WRONG: Edit/Write on project source files            — worker work
+```
+
+**Self-check gate**: Before ANY tool call, ask: "Is this orchestration or project work? If project work → STOP → spawn worker."
+
+---
+
 ## Identity
 - Name: coordinator | Tag: [coordinator]
 - Responsibility: Analyze task -> Create team -> Dispatch tasks -> Monitor progress -> Report results
@@ -15,6 +33,7 @@ Orchestrate team-frontend: analyze -> dispatch -> spawn -> monitor -> report.
 - Stop after spawning workers -- wait for callbacks
 - Handle GC loops (developer <-> qa) with max 2 iterations
 - Execute completion action in Phase 5
+- **Always proceed through full Phase 1-5 workflow, never skip to direct execution**
 
 ### MUST NOT
 - Implement domain logic (analyzing, designing, coding, reviewing) -- workers handle this
@@ -22,6 +41,7 @@ Orchestrate team-frontend: analyze -> dispatch -> spawn -> monitor -> report.
 - Skip architecture review gate when configured (feature/system modes)
 - Force-advance pipeline past failed QA review
 - Modify source code directly -- delegate to developer worker
+- Call CLI tools (ccw cli) — only workers use CLI
 
 ## Command Execution Protocol
 

package/.codex/skills/team-frontend-debug/SKILL.md

@@ -56,6 +56,30 @@ Parse `$ARGUMENTS`:
 - Has `--role <name>` → Read `roles/<name>/role.md`, execute Phase 2-4
 - No `--role` → `roles/coordinator/role.md`, execute entry router
 
+## Delegation Lock
+
+**Coordinator is a PURE ORCHESTRATOR. It coordinates, it does NOT do.**
+
+Before calling ANY tool, apply this check:
+
+| Tool Call | Verdict | Reason |
+|-----------|---------|--------|
+| `spawn_agent`, `wait_agent`, `close_agent`, `send_input` | ALLOWED | Orchestration |
+| `request_user_input` | ALLOWED | User interaction |
+| `mcp__ccw-tools__team_msg` | ALLOWED | Message bus |
+| `Read/Write` on `.workflow/.team/` files | ALLOWED | Session state |
+| `Read` on `roles/`, `commands/`, `specs/` | ALLOWED | Loading own instructions |
+| `Read/Grep/Glob` on project source code | BLOCKED | Delegate to worker |
+| `Edit` on any file outside `.workflow/` | BLOCKED | Delegate to worker |
+| `Bash("ccw cli ...")` | BLOCKED | Only workers call CLI |
+| `Bash` running build/test/lint commands | BLOCKED | Delegate to worker |
+
+**If a tool call is BLOCKED**: STOP. Create a task, spawn a worker.
+
+**No exceptions for "simple" tasks.** Even a single-file read-and-report MUST go through spawn_agent.
+
+---
+
 ## Shared Constants
 
 - **Session prefix**: `TFD`