maestro-flow 0.3.14 → 0.3.16

package/.codex/skills/maestro-roadmap/SKILL.md

@@ -145,30 +145,15 @@ Each wave generates `wave-{N}.csv` with extra `prev_context` column.
 
 ### Session Initialization
 
-```javascript
-const getUtc8ISOString = () => new Date(Date.now() + 8 * 60 * 60 * 1000).toISOString()
-
-// Parse flags
-const AUTO_YES = $ARGUMENTS.includes('--yes') || $ARGUMENTS.includes('-y')
-const phasesMatch = $ARGUMENTS.match(/--phases\s+(\d+)/)
-const targetPhases = phasesMatch ? parseInt(phasesMatch[1]) : null
-const brainstormMatch = $ARGUMENTS.match(/--from-brainstorm\s+(\S+)/)
-const brainstormSession = brainstormMatch ? brainstormMatch[1] : null
-
-// Clean requirement text
-const requirementArg = $ARGUMENTS
-  .replace(/--yes|-y|--phases\s+\d+|--from-brainstorm\s+\S+/g, '')
-  .trim()
-
-const slug = requirementArg.toLowerCase()
-  .replace(/[^a-z0-9]+/g, '-')
-  .substring(0, 40)
-const dateStr = getUtc8ISOString().substring(0, 10).replace(/-/g, '')
-const sessionId = `${dateStr}-roadmap-${slug}`
-const sessionFolder = `.workflow/.csv-wave/${sessionId}`
-
-Bash(`mkdir -p ${sessionFolder}`)
-```
+Parse `$ARGUMENTS` to extract:
+- `AUTO_YES` from `--yes` / `-y`
+- `targetPhases` from `--phases N` (default: auto-determined)
+- `brainstormSession` from `--from-brainstorm <SESSION-ID>`
+- `requirementArg` = remaining text after stripping all flags
+- `slug` = requirementArg lowercased, non-alphanumeric → `-`, max 40 chars
+
+Session ID: `{YYYYMMDD}-roadmap-{slug}`
+Session folder: `.workflow/.csv-wave/{sessionId}/` — create via `mkdir -p`
 
 ### Phase 1: Requirement Parsing + CSV Generation
 
@@ -205,11 +190,7 @@ Strategy: >= 3 high -> progressive, >= 3 low -> direct, else -> ask user (or aut
 
 #### Wave 1: Requirement Analysis (Parallel)
 
-1. Read master `tasks.csv`
-2. Filter rows where `wave == 1` AND `status == pending`
-3. No prev_context needed (wave 1 has no predecessors)
-4. Write `wave-1.csv`
-5. Execute:
+Filter master `tasks.csv` for `wave == 1 AND status == pending` → write `wave-1.csv` (no prev_context needed).
 
 ```javascript
 spawn_agents_on_csv({
@@ -232,43 +213,24 @@ spawn_agents_on_csv({
 })
 ```
 
-6. Read `wave-1-results.csv`, merge into master `tasks.csv`
-7. Delete `wave-1.csv`
+Merge `wave-1-results.csv` into master `tasks.csv`, delete `wave-1.csv`.
 
 #### Wave 2: Roadmap Assembly (Sequential)
 
-1. Read master `tasks.csv`
-2. Filter rows where `wave == 2` AND `status == pending`
-3. Check deps -- if all wave 1 tasks failed, use degraded mode (requirement text only)
-4. Build `prev_context` from wave 1 findings:
-   ```
-   [Task 1: Scope Analysis] Features: auth, OAuth, 2FA. MVP: basic auth + OAuth. Size: M...
-   [Task 2: Risk Analysis] High risk: OAuth provider integration. Medium: 2FA delivery...
-   [Task 3: Dependency Analysis] Critical path: auth -> OAuth -> 2FA. Parallel: UI + API...
-   ```
-5. Inject strategy and `--phases N` constraint into assembly prompt
-6. Write `wave-2.csv` with `prev_context` column
-7. Execute `spawn_agents_on_csv` for assembly agent
-8. Merge results into master `tasks.csv`
-9. Delete `wave-2.csv`
+Filter master `tasks.csv` for `wave == 2 AND status == pending`. If all wave 1 tasks failed, use degraded mode (requirement text only).
+
+Build `prev_context` from wave 1 findings (format: `[Task N: Title] summary...` per task). Inject strategy and `--phases N` constraint into assembly prompt.
+Write `wave-2.csv` with `prev_context` column → execute `spawn_agents_on_csv` → merge results → delete `wave-2.csv`.
 
 ### Phase 3: Results Aggregation
 
 **Objective**: Generate final results, optional refinement, and write roadmap.
 
-1. Read final master `tasks.csv`
-2. Export as `results.csv`
+Export master `tasks.csv` as `results.csv`.
 
-3. **Interactive refinement** (skip if AUTO_YES):
-   - Present roadmap overview: phase count, milestone structure, dependency graph
-   - User feedback via AskUserQuestion (max 3 rounds):
-     - **Approve**: Proceed to output
-     - **Adjust Scope**: Move features between phases
-     - **Reorder**: Change phase sequencing
-     - **Split/Merge**: Break large phases or combine small ones
-   - Each round: update roadmap draft
+**Interactive refinement** (skip if AUTO_YES): Present roadmap overview, collect user feedback via AskUserQuestion (max 3 rounds). Options: Approve, Adjust Scope, Reorder, Split/Merge. Update draft each round.
 
-4. Generate `context.md`:
+Generate `context.md`:
 
 ```markdown
 # Roadmap Generation Report
@@ -297,12 +259,9 @@ spawn_agents_on_csv({
 - Deferred: {deferred_items}
 ```
 
-5. **Write outputs**:
-   - Write `.workflow/roadmap.md` using standard roadmap template structure
-   - Ensure `.workflow/scratch/` directory exists (phases are labels, not directories)
-   - Update `state.json` milestones array and set `current_milestone`
+**Write outputs**: `.workflow/roadmap.md` (standard template), ensure `.workflow/scratch/` exists, update `state.json` milestones array and `current_milestone`.
 
-6. Display summary:
+Display summary:
 
 ```
 === ROADMAP CREATED ===
@@ -338,11 +297,7 @@ Next steps:
 
 #### Protocol
 
-1. **Read** `{session_folder}/discoveries.ndjson` before own analysis
-2. **Skip covered**: If discovery of same type + dedup key exists, skip
-3. **Write immediately**: Append findings as found
-4. **Append-only**: Never modify or delete
-5. **Deduplicate**: Check before writing
+Read `{session_folder}/discoveries.ndjson` before own analysis. Deduplicate by type + dedup key before writing. Append-only — never modify or delete.
 
 ```bash
 echo '{"ts":"<ISO>","worker":"{id}","type":"risk_factor","data":{"name":"OAuth provider rate limits","severity":"medium","probability":"high","mitigation":"Implement token caching and retry logic"}}' >> {session_folder}/discoveries.ndjson

package/.codex/skills/maestro-spec-generate/SKILL.md

@@ -171,29 +171,15 @@ Each wave generates `wave-{N}.csv` with extra `prev_context` column.
 
 ### Session Initialization
 
-```javascript
-const getUtc8ISOString = () => new Date(Date.now() + 8 * 60 * 60 * 1000).toISOString()
-
-// Parse flags
-const AUTO_YES = $ARGUMENTS.includes('--yes') || $ARGUMENTS.includes('-y')
-const skipResearch = $ARGUMENTS.includes('--skip-research')
-const brainstormMatch = $ARGUMENTS.match(/--from-brainstorm\s+(\S+)/)
-const brainstormSession = brainstormMatch ? brainstormMatch[1] : null
-
-// Clean topic text
-const topicArg = $ARGUMENTS
-  .replace(/--yes|-y|--skip-research|--from-brainstorm\s+\S+/g, '')
-  .trim()
-
-const slug = topicArg.toLowerCase()
-  .replace(/[^a-z0-9]+/g, '-')
-  .substring(0, 40)
-const dateStr = getUtc8ISOString().substring(0, 10).replace(/-/g, '')
-const sessionId = `${dateStr}-spec-generate-${slug}`
-const sessionFolder = `.workflow/.csv-wave/${sessionId}`
-
-Bash(`mkdir -p ${sessionFolder}`)
-```
+Parse `$ARGUMENTS` to extract:
+- `AUTO_YES` from `--yes` / `-y`
+- `skipResearch` from `--skip-research`
+- `brainstormSession` from `--from-brainstorm <SESSION-ID>`
+- `topicArg` = remaining text after stripping all flags
+- `slug` = topicArg lowercased, non-alphanumeric → `-`, max 40 chars
+
+Session ID: `{YYYYMMDD}-spec-generate-{slug}`
+Session folder: `.workflow/.csv-wave/{sessionId}/` — create via `mkdir -p`
 
 ### Phase 1: Input Parsing + CSV Generation
 
@@ -224,11 +210,7 @@ Bash(`mkdir -p ${sessionFolder}`)
 
 #### Wave 1: Research (Parallel)
 
-1. Read master `tasks.csv`
-2. Filter rows where `wave == 1` AND `status == pending`
-3. No prev_context needed (wave 1 has no predecessors)
-4. Write `wave-1.csv`
-5. Execute:
+Filter master `tasks.csv` for `wave == 1 AND status == pending` → write `wave-1.csv` (no prev_context needed).
 
 ```javascript
 spawn_agents_on_csv({
@@ -252,38 +234,26 @@ spawn_agents_on_csv({
 })
 ```
 
-6. Read `wave-1-results.csv`, merge into master `tasks.csv`
-7. Delete `wave-1.csv`
+Merge `wave-1-results.csv` into master `tasks.csv`, delete `wave-1.csv`.
 
 #### Wave 2: Document Chain (Sequential)
 
-1. Read master `tasks.csv`
-2. Filter rows where `wave == 2` AND `status == pending`
-3. Check deps -- if all wave 1 tasks failed, use degraded mode (basic seed only)
-4. Build `prev_context` from wave 1 findings:
-   ```
-   [Task 1: Domain Research] Target users: developers building workflow tools. Market trends: ...
-   [Task 2: Competitive Analysis] Key competitors: X, Y, Z. Differentiation opportunities: ...
-   [Task 3: Tech Stack Analysis] Recommended: TypeScript + Node.js. Constraints: ...
-   ```
-5. Write `wave-2.csv` with `prev_context` column
-6. Execute `spawn_agents_on_csv` for document chain agent
-7. Merge results into master `tasks.csv`
-8. Delete `wave-2.csv`
+Filter master `tasks.csv` for `wave == 2 AND status == pending`. If all wave 1 tasks failed, use degraded mode (basic seed only).
+
+Build `prev_context` from wave 1 findings (format: `[Task N: Title] summary...` per task).
+Write `wave-2.csv` with `prev_context` column → execute `spawn_agents_on_csv` → merge results → delete `wave-2.csv`.
 
 ### Phase 3: Results Aggregation
 
 **Objective**: Generate final results, readiness check, and write spec package.
 
-1. Read final master `tasks.csv`
-2. Export as `results.csv`
-3. **Readiness check** -- score on 4 dimensions (25% each):
+Export master `tasks.csv` as `results.csv`. **Readiness check** -- score on 4 dimensions (25% each):
    - Completeness: all required documents generated with substantive content
    - Consistency: glossary terms used uniformly, scope containment
    - Traceability: goals -> requirements -> architecture -> epics chain
    - Depth: acceptance criteria testable, ADRs justified, stories estimable
 
-4. **Gate decision**:
+**Gate decision**:
 
 | Score | Gate | Action |
 |-------|------|--------|
@@ -291,7 +261,7 @@ spawn_agents_on_csv({
 | 60-79% | Review | Proceed with caveats logged |
 | < 60% | Fail | Log issues, proceed with available output |
 
-5. Generate `context.md`:
+Generate `context.md`:
 
 ```markdown
 # Spec Generate Report
@@ -327,9 +297,7 @@ spawn_agents_on_csv({
 - Overall: {score}% ({gate})
 ```
 
-6. Write spec package to `.workflow/.spec/SPEC-{slug}-{date}/`
-7. Write `.workflow/roadmap.md`
-8. Display summary.
+Write spec package to `.workflow/.spec/SPEC-{slug}-{date}/`, write `.workflow/roadmap.md`, display summary.
 
 ### Shared Discovery Board Protocol
 
@@ -353,11 +321,7 @@ spawn_agents_on_csv({
 
 #### Protocol
 
-1. **Read** `{session_folder}/discoveries.ndjson` before own analysis
-2. **Skip covered**: If discovery of same type + dedup key exists, skip
-3. **Write immediately**: Append findings as found
-4. **Append-only**: Never modify or delete
-5. **Deduplicate**: Check before writing
+Read `{session_folder}/discoveries.ndjson` before own analysis. Deduplicate by type + dedup key before writing. Append-only — never modify or delete.
 
 ```bash
 echo '{"ts":"<ISO>","worker":"{id}","type":"domain_term","data":{"term":"workflow","definition":"A sequence of orchestrated tasks","aliases":["pipeline","process"]}}' >> {session_folder}/discoveries.ndjson

package/.codex/skills/maestro-ui-design/SKILL.md

@@ -56,25 +56,13 @@ When `--yes` or `-y`: Skip interactive selection, auto-pick top-scored variant,
 1. Parse flags from `$ARGUMENTS`: `--styles N`, `--stack`, `--targets`, `--persist`, `--full`, `-y`
 2. **Phase mode** (number): resolve via state.json artifact registry to `.workflow/scratch/{YYYYMMDD}-{type}-{slug}/`
 3. **Scratch mode** (text): create `.workflow/scratch/ui-design-{slug}-{date}/` with minimal index.json
-4. Create output directories:
-   ```bash
-   mkdir -p "${PHASE_DIR}/design-ref/prototypes"
-   mkdir -p "${PHASE_DIR}/design-ref/layout-templates"
-   ```
+4. Create output directories: `${PHASE_DIR}/design-ref/prototypes/` and `${PHASE_DIR}/design-ref/layout-templates/`
 
 ### Step 2: Detect Skill Availability
 
-```bash
-SKILL_PATH=""
-for path in \
-  "skills/ui-ux-pro-max/scripts/search.py" \
-  "$HOME/.claude/plugins/cache/ui-ux-pro-max-skill/ui-ux-pro-max/*/scripts/search.py"; do
-  expanded=$(ls $path 2>/dev/null | tail -1)
-  if [ -n "$expanded" ]; then SKILL_PATH="$expanded"; break; fi
-done
-```
+Search for `ui-ux-pro-max` script at `skills/ui-ux-pro-max/scripts/search.py` or `$HOME/.claude/plugins/cache/ui-ux-pro-max-skill/ui-ux-pro-max/*/scripts/search.py`.
 
-- If `--style-skill PKG` provided: override `SKILL_PATH`
+- If `--style-skill PKG` provided: override detected path
 - If `--full`: force self-contained pipeline regardless of skill availability
 
 ### Step 3: Gather Requirements Context
@@ -106,16 +94,7 @@ Present all variants with key attributes (colors, typography, effects).
 
 ### Step 6: Solidify Selected Design
 
-Spawn Agent for token extraction from selected variant:
-
-```
-Agent({
-  subagent_type: "general-purpose",
-  description: "Extract design tokens from selected variant",
-  prompt: "Extract structured design-tokens.json and animation-tokens.json from the selected design variant. Colors in OKLCH format. Include component_styles, typography.combinations, spacing, border_radius, shadows, breakpoints. Animation tokens: duration, easing, transitions, keyframes, interactions, reduced_motion.",
-  run_in_background: false
-})
-```
+Spawn Agent to extract structured tokens from selected variant: `design-tokens.json` (OKLCH colors, component_styles, typography.combinations, spacing, border_radius, shadows, breakpoints) and `animation-tokens.json` (duration, easing, transitions, keyframes, interactions, reduced_motion).
 
 Write output artifacts:
 - `design-ref/MASTER.md` -- complete design system specification
@@ -125,38 +104,12 @@ Write output artifacts:
 
 ### Step 7: Optional Prototype Generation
 
-For each target, spawn Agent to generate standalone HTML prototype:
-
-```
-Agent({
-  subagent_type: "general-purpose",
-  description: "Generate HTML prototype for {target}",
-  prompt: "Generate standalone HTML+CSS prototype from design-tokens.json and animation-tokens.json. Realistic content (not lorem ipsum). SVG icons via CDN. Responsive at 375/768/1024px. WCAG AA contrast.",
-  run_in_background: false
-})
-```
+For each target, spawn Agent to generate standalone HTML+CSS prototype from design-tokens.json and animation-tokens.json. Requirements: realistic content (no lorem ipsum), SVG icons via CDN, responsive at 375/768/1024px, WCAG AA contrast.
 
 ### Step 8: Update State and Report
 
 1. Update index.json with `design_ref` status
-2. Display completion report:
-   ```
-   === UI DESIGN READY ===
-   Phase:   {phase_name}
-   Styles:  {style_count} variants, #{selected} selected
-   Stack:   {stack}
-   Targets: {target_list}
-
-   Design System:
-     MASTER.md:  {scratch_dir}/design-ref/MASTER.md
-     Tokens:     {scratch_dir}/design-ref/design-tokens.json
-     Animation:  {scratch_dir}/design-ref/animation-tokens.json
-     Prototypes: {scratch_dir}/design-ref/prototypes/
-
-   Next steps:
-     Skill({ skill: "maestro-plan", args: "{phase}" })
-     Skill({ skill: "maestro-ui-design", args: "{phase} --refine" })
-   ```
+2. Display completion report: phase, variant count + selected, stack, targets, design system artifact paths (`MASTER.md`, `design-tokens.json`, `animation-tokens.json`, `prototypes/`). Suggest next: `$maestro-plan {phase}` or `$maestro-ui-design {phase} --refine`.
 </execution>
 
 <error_codes>

package/.codex/skills/maestro-verify/SKILL.md

@@ -160,30 +160,20 @@ Each wave generates `wave-{N}.csv` with extra `prev_context` column.
 
 ### Session Initialization
 
-```javascript
-const getUtc8ISOString = () => new Date(Date.now() + 8 * 60 * 60 * 1000).toISOString()
-
-// Parse flags
-const AUTO_YES = $ARGUMENTS.includes('--yes') || $ARGUMENTS.includes('-y')
-const continueMode = $ARGUMENTS.includes('--continue')
-const concurrencyMatch = $ARGUMENTS.match(/(?:--concurrency|-c)\s+(\d+)/)
-const maxConcurrency = concurrencyMatch ? parseInt(concurrencyMatch[1]) : 4
+**Parse from `$ARGUMENTS`**:
 
-// Parse verify-specific flags
-const skipTests = $ARGUMENTS.includes('--skip-tests')
-const skipAntipattern = $ARGUMENTS.includes('--skip-antipattern')
+| Variable | Source | Default |
+|----------|--------|---------|
+| `AUTO_YES` | `--yes` or `-y` | false |
+| `continueMode` | `--continue` | false |
+| `maxConcurrency` | `--concurrency N` or `-c N` | 4 |
+| `skipTests` | `--skip-tests` | false |
+| `skipAntipattern` | `--skip-antipattern` | false |
+| `phaseArg` | remaining text after flag removal | — |
 
-// Clean phase text
-const phaseArg = $ARGUMENTS
-  .replace(/--yes|-y|--continue|--concurrency\s+\d+|-c\s+\d+|--skip-tests|--skip-antipattern/g, '')
-  .trim()
+**Session path** (UTC+8 date prefix): `.workflow/.csv-wave/{YYYYMMDD}-verify-P{phaseArg}-{phaseSlug}/`
 
-const dateStr = getUtc8ISOString().substring(0, 10).replace(/-/g, '')
-const sessionId = `${dateStr}-verify-P${phaseArg}-${phaseSlug}`
-const sessionFolder = `.workflow/.csv-wave/${sessionId}`
-
-Bash(`mkdir -p ${sessionFolder}`)
-```
+Create session directory.
 
 ### Phase 1: Phase Resolution -> CSV
 
@@ -237,11 +227,7 @@ Bash(`mkdir -p ${sessionFolder}`)
 
 #### Wave 1: Truth Checks + Artifact Existence (Parallel)
 
-1. Read master `tasks.csv`
-2. Filter rows where `wave == 1` AND `status == pending`
-3. No prev_context needed (wave 1 has no predecessors)
-4. Write `wave-1.csv`
-5. Execute:
+Filter `wave == 1 && status == pending` from master CSV. No prev_context (no predecessors). Write `wave-1.csv`.
 
 ```javascript
 spawn_agents_on_csv({
@@ -251,86 +237,32 @@ spawn_agents_on_csv({
   max_concurrency: maxConcurrency,
   max_runtime_seconds: 600,
   output_csv_path: `${sessionFolder}/wave-1-results.csv`,
-  output_schema: {
-    type: "object",
-    properties: {
-      id: { type: "string" },
-      status: { type: "string", enum: ["completed", "failed"] },
-      findings: { type: "string" },
-      gaps_found: { type: "string" },
-      fix_plan: { type: "string" },
-      error: { type: "string" }
-    },
-    required: ["id", "status", "findings"]
-  }
+  output_schema: { id, status: ["completed"|"failed"], findings, gaps_found, fix_plan, error }
+  // required: id, status, findings
 })
 ```
 
-6. Read `wave-1-results.csv`, merge into master `tasks.csv`
-7. Delete `wave-1.csv`
+Merge results into master `tasks.csv`, delete `wave-1.csv`.
 
-**Truth check agent protocol**:
-- For each truth, identify supporting artifacts
-- Check artifact existence and substance indicators
-- Check wiring indicators (import/usage grep)
-- Determine truth status: VERIFIED / FAILED / UNCERTAIN
-- Report gaps for FAILED truths with severity and fix direction
+**Truth check agent**: Identify supporting artifacts, check existence + substance + wiring indicators. Status: VERIFIED / FAILED / UNCERTAIN. Report gaps for FAILED with severity + fix direction.
 
-**Artifact existence agent protocol**:
-- Check file exists on disk via `ls` or `stat`
-- If missing, report gap with severity=critical
-- If exists, note file size and basic structure for wave 2
+**Artifact existence agent**: Check file on disk. Missing = gap (severity=critical). Exists = note size + structure for wave 2.
 
 #### Wave 2: Artifact Substance + Wiring (Parallel)
 
-1. Read master `tasks.csv`
-2. Filter rows where `wave == 2` AND `status == pending`
-3. Check deps -- if all wave 1 existence checks failed for a given artifact, skip substance check
-4. Build `prev_context` from wave 1 findings:
-   ```
-   [Task 1: Truth: User can see messages] VERIFIED - Chat.tsx renders message list from API response
-   [Task 3: Artifact Exists: Chat.tsx] completed - file exists, 142 lines
-   ...
-   ```
-5. Write `wave-2.csv` with `prev_context` column
-6. Execute `spawn_agents_on_csv` for substance + wiring agents
-7. Merge results into master `tasks.csv`
-8. Delete `wave-2.csv`
-
-**Substance check agent protocol**:
-- Files under ~10 lines of real logic -> STUB
-- Contains "placeholder", "coming soon", "TODO: implement" -> STUB
-- Real implementation with business logic -> SUBSTANTIVE
-
-**Wiring check agent protocol**:
-- `grep -r "import.*{artifact_name}" src/` -- check imported
-- `grep -r "{artifact_name}" src/ | grep -v "import"` -- check used beyond import
-- Status: WIRED / ORPHANED / NOT_WIRED
+Filter `wave == 2 && status == pending`. Skip substance check if all wave 1 existence checks failed for that artifact. Build `prev_context` from wave 1 findings (format: `[Task N: Title] status - summary`). Write `wave-2.csv`, execute `spawn_agents_on_csv`, merge results, delete temp CSV.
+
+**Substance check agent**: <10 lines real logic or contains placeholder markers ("placeholder", "coming soon", "TODO: implement") = STUB. Otherwise SUBSTANTIVE.
+
+**Wiring check agent**: Grep for import statements + actual usage beyond imports. Status: WIRED / ORPHANED / NOT_WIRED.
 
 #### Wave 3: Anti-Pattern Scan + Nyquist Audit (Parallel)
 
-1. Read master `tasks.csv`
-2. Filter rows where `wave == 3` AND `status == pending`
-3. If `--skip-antipattern`: mark antipattern task as `skipped`
-4. If `--skip-tests`: mark nyquist task as `skipped`
-5. Build `prev_context` from wave 1 + wave 2 findings
-6. Write `wave-3.csv` with `prev_context` column
-7. Execute `spawn_agents_on_csv` for remaining tasks
-8. Merge results into master `tasks.csv`
-9. Delete `wave-3.csv`
-
-**Anti-pattern scan agent protocol**:
-- Extract modified files from task summaries
-- Scan for: TODO/FIXME/XXX/HACK, placeholder content, empty returns, log-only functions, hardcoded test data, disabled tests
-- Categorize: Blocker (prevents goal) / Warning (incomplete) / Info (notable)
-- Report as JSON array in gaps_found
-
-**Nyquist audit agent protocol**:
-- Detect test framework (jest, vitest, pytest, etc.)
-- Map requirements (must-haves) to test files
-- Classify: COVERED / PARTIAL / MISSING
-- Run coverage command if available
-- Report gaps and coverage percentage
+Filter `wave == 3 && status == pending`. Mark as `skipped` per skip flags (`--skip-antipattern`, `--skip-tests`). Build `prev_context` from wave 1 + wave 2 findings. Write `wave-3.csv`, execute `spawn_agents_on_csv`, merge results, delete temp CSV.
+
+**Anti-pattern scan agent**: Extract modified files from task summaries. Scan for TODO/FIXME/XXX/HACK, placeholder content, empty returns, log-only functions, hardcoded test data, disabled tests. Categorize: Blocker / Warning / Info. Report as JSON array in `gaps_found`.
+
+**Nyquist audit agent**: Detect test framework, map requirements to test files, classify COVERED / PARTIAL / MISSING. Run coverage if available. Report gaps + coverage percentage.
 
 ### Phase 3: Results Aggregation
 
@@ -439,54 +371,25 @@ Issue Refs: {issue_ids}
 | Any truth FAILED, artifact MISSING/STUB, key link NOT_WIRED, or blocker found | gaps_found |
 | All automated checks pass but human verification items remain | human_needed |
 
-10. **Auto-create issues** from gaps + blocker anti-patterns (same ID generation as verify workflow: ISS-YYYYMMDD-NNN)
+10. **Auto-create issues** from gaps + blocker anti-patterns (ID format: `ISS-YYYYMMDD-NNN`).
 
-11. **Archive previous verification artifacts** before writing to phase directory:
-    - If `verification.json` or `validation.json` exists in phase dir, move to `.history/`
+11. **Archive previous artifacts**: Move existing `verification.json`/`validation.json` in phase dir to `.history/`.
 
-12. **Copy output files** to phase directory:
-    - `verification.json` -> `{artifact_dir}/verification.json`
-    - `validation.json` -> `{artifact_dir}/validation.json` (if generated)
+12. **Copy outputs** to phase directory: `verification.json`, `validation.json` (if generated).
 
 13. **Update phase index.json** with verification status and timestamps.
 
-14. **Display summary**:
-
-```
-=== VERIFICATION RESULTS ===
-Phase:         {phase_name}
-
-Goal-Backward: {verified_count}/{total_truths} truths verified
-  Artifacts:   {artifact_verified}/{artifact_total} (L1-L3)
-  Wiring:      {links_wired}/{links_total} key links
-Anti-patterns: {blocker_count} blockers, {warning_count} warnings
-Nyquist:       {coverage_pct}% coverage ({SKIPPED|status})
-
-Gaps: {gap_count}
-  Critical: {critical_count}
-  High:     {high_count}
-  Medium:   {medium_count}
-  Low:      {low_count}
-
-Fix Plans: {fix_plan_count} generated
-Issues Created: {issue_count}
-Human Verification: {human_items} items
-
-Files:
-  {session_folder}/verification.json
-  {session_folder}/validation.json (if generated)
-  {artifact_dir}/verification.json
-  {artifact_dir}/validation.json (if generated)
-```
+14. **Display summary**: Phase name, truths verified/total, artifacts L1-L3, wiring status, anti-pattern counts, Nyquist coverage, gaps by severity, fix plan count, issues created, human verification items, output file paths.
 
 15. **Post-verify Knowledge Inquiry** (before next step routing):
-   - **Anti-pattern detection**: If anti-pattern scan found blockers:
-     → Ask: "Verification found {N} anti-patterns. Should `quality-rules.md` be updated to enforce these checks? (`/spec-add quality`)"
-   - **Constraint violation**: If Goal-Backward check found constraint violations or missing wiring:
-     → Ask: "Verification found architecture constraint violations. Should `architecture-constraints.md` be updated? (`/spec-add arch`)"
-   - **Test coverage gaps**: If Nyquist gaps found with recurring pattern:
-     → Ask: "Persistent test coverage gap detected in {module}. Should it be added to `test-conventions.md` as a required test area? (`/spec-add test`)"
-   - If user confirms, append `<spec-entry>` to matching category file via `spec-add` mechanism
+
+| Signal | Prompt User | Spec Category |
+|--------|-------------|---------------|
+| Anti-pattern blockers found | "Update `quality-rules.md`?" | `quality` via `/spec-add` |
+| Constraint/wiring violations | "Update `architecture-constraints.md`?" | `arch` via `/spec-add` |
+| Recurring Nyquist coverage gaps | "Add to `test-conventions.md`?" | `test` via `/spec-add` |
+
+On user confirm, append `<spec-entry>` to matching category file.
 
 16. **Next step routing**: