oh-my-customcode 0.70.0 → 0.71.0

package/README.md

@@ -13,7 +13,7 @@
 
 **[한국어 문서 (Korean)](./README_ko.md)**
 
-46 agents. 100 skills. 21 rules. One command.
+46 agents. 99 skills. 21 rules. One command.
 
 ```bash
 npm install -g oh-my-customcode && cd your-project && omcustom init
@@ -146,20 +146,20 @@ Each agent declares its tools, model, memory scope, and limitations in YAML fron
 
 ---
 
-### Skills (100)
+### Skills (99)
 
 | Category | Count | Includes |
 |----------|-------|----------|
 | Best Practices | 24 | Go, Python, TypeScript, Kotlin, Rust, React, FastAPI, Spring Boot, Django, Flutter, Docker, AWS, Postgres, Redis, Kafka, dbt, Spark, Snowflake, Airflow, pipeline-architecture-patterns, alembic, and more |
 | Routing | 4 | secretary, dev-lead, de-lead, qa-lead |
-| Workflow | 15 | structured-dev-cycle, deep-plan, research, evaluator-optimizer, dag-orchestration, worker-reviewer-pipeline, reasoning-sandwich, workflow, workflow-runner, workflow-resume, and more |
+| Workflow | 13 | structured-dev-cycle, deep-plan, research, evaluator-optimizer, dag-orchestration, worker-reviewer-pipeline, reasoning-sandwich, pipeline, and more |
 | Development | 7 | dev-review, dev-refactor, analysis, create-agent, intent-detection, web-design-guidelines, omcustom-takeover |
 | Operations | 9 | update-docs, audit-agents, sauron-watch, monitoring-setup, fix-refs, release-notes, and more |
 | Memory | 3 | memory-save, memory-recall, memory-management |
 | Package | 3 | npm-publish, npm-version, npm-audit |
 | Optimization | 3 | optimize-analyze, optimize-bundle, optimize-report |
 | Security | 3 | adversarial-review, cve-triage, jinja2-prompts |
-| Other | 8 | codex-exec, vercel-deploy, skills-sh-search, result-aggregation, writing-clearly-and-concisely, and more |
+| Other | 9 | codex-exec, claude-native, vercel-deploy, skills-sh-search, result-aggregation, writing-clearly-and-concisely, and more |
 
 Skills use a 3-tier scope system: `core` (universal), `harness` (agent/skill maintenance), `package` (project-specific).
 
@@ -181,8 +181,8 @@ All commands are invoked inside the Claude Code conversation.
 | `/sdd-dev` | Spec-Driven Development workflow |
 | `/ambiguity-gate` | Pre-routing ambiguity analysis |
 | `/adversarial-review` | Attacker-mindset security code review |
-| `/workflow` | Execute YAML-defined workflow pipelines |
-| `/workflow:resume` | Resume a halted workflow from last failure point |
+| `/pipeline` | Execute YAML-defined pipelines |
+| `/pipeline resume` | Resume a halted pipeline from last failure point |
 
 ### Agent Management
 
@@ -282,7 +282,7 @@ your-project/
 ├── CLAUDE.md                   # Entry point
 ├── .claude/
 │   ├── agents/                 # 46 agent definitions
-│   ├── skills/                 # 100 skill modules
+│   ├── skills/                 # 99 skill modules
 │   ├── rules/                  # 21 governance rules (R000-R021)
 │   ├── hooks/                  # 15 lifecycle hook scripts
 │   ├── schemas/                # Tool input validation schemas

package/dist/cli/index.js

@@ -9325,7 +9325,7 @@ var init_package = __esm(() => {
     workspaces: [
       "packages/*"
     ],
-    version: "0.70.0",
+    version: "0.71.0",
     description: "Batteries-included agent harness for Claude Code",
     type: "module",
     bin: {

package/dist/index.js

@@ -1820,7 +1820,7 @@ var package_default = {
   workspaces: [
     "packages/*"
   ],
-  version: "0.70.0",
+  version: "0.71.0",
   description: "Batteries-included agent harness for Claude Code",
   type: "module",
   bin: {

package/package.json

@@ -3,7 +3,7 @@
   "workspaces": [
     "packages/*"
   ],
-  "version": "0.70.0",
+  "version": "0.71.0",
   "description": "Batteries-included agent harness for Claude Code",
   "type": "module",
   "bin": {

package/templates/.claude/skills/claude-native/SKILL.md

@@ -0,0 +1,215 @@
+---
+name: claude-native
+description: Monitor Claude Code releases and auto-generate GitHub issues for each new version
+scope: core
+user-invocable: true
+argument-hint: "[--backfill] [--dry-run]"
+version: 1.0.0
+---
+
+# Claude Native Skill
+
+Monitor Claude Code (the CLI tool) release history and auto-generate GitHub issues for each new version that has not yet been tracked. Replaces the deprecated customclaw Airflow-based monitoring (deprecated 2026-03-18).
+
+## Options
+
+```
+--backfill    Process ALL versions >= v2.1.86 (default behavior when flag is present)
+              Without flag: only check the latest 5 releases
+--dry-run     Show what issues would be created without actually creating them
+```
+
+## Workflow
+
+### Phase 1: Fetch CC Releases
+
+Fetch all Claude Code releases from the GitHub API:
+
+```bash
+gh api repos/anthropics/claude-code/releases \
+  --paginate \
+  --jq '.[] | {tag_name: .tag_name, published_at: .published_at, html_url: .html_url, body: .body}'
+```
+
+- Without `--backfill`: fetch only the latest 5 releases (`--limit 5` or first 5 results)
+- With `--backfill`: fetch all releases (use `--paginate`)
+- Filter: only process versions >= v2.1.86 (monitoring stopped after v2.1.85 / issue #683)
+
+### Phase 2: Check Existing Issues
+
+Search for existing tracking issues to avoid duplicates:
+
+```bash
+gh issue list \
+  --state all \
+  --search "[Claude Code v" \
+  --json number,title \
+  --limit 100
+```
+
+Build a set of already-tracked versions by extracting version strings from issue titles matching the pattern `[Claude Code v{version}]`.
+
+### Phase 3: Dedup
+
+For each fetched release version:
+- Parse the version string from `tag_name` (e.g., `v2.1.86`)
+- If a matching issue title already exists → skip (already tracked)
+- If no matching issue → add to "needs issue" list
+
+### Phase 4: Create Issues (or Dry-Run Report)
+
+#### Dry-Run Mode (`--dry-run`)
+
+Print a report of what would be created:
+
+```
+[Dry Run] Would create issues for:
+  - v2.1.86 (published: 2026-01-15)
+  - v2.1.87 (published: 2026-01-22)
+  ...
+No issues were created.
+```
+
+#### Live Mode
+
+For each version in the "needs issue" list, create a GitHub issue:
+
+```bash
+gh issue create \
+  --title "[Claude Code v{version}] New release detected" \
+  --label "automated,claude-code-release" \
+  --body "{body}"
+```
+
+Issue body format (matching the pattern established by issue #683):
+
+```markdown
+# Claude Code v{version}
+
+**Release:** v{version}
+**Published:** {published_at}
+**Link:** {html_url}
+
+## Release Summary
+
+{release_notes_body — truncated to first 2000 chars if too long}
+
+---
+
+## Action Items
+
+- [ ] Review release notes for impact on oh-my-customcode
+- [ ] Update agent definitions if new Claude Code features affect agents
+- [ ] Test compatibility with current oh-my-customcode version
+- [ ] Update CLAUDE.md if new capabilities are relevant
+
+---
+
+_This issue was created by the `/omcustom:claude-native` skill._
+```
+
+**Notes:**
+- If `body` from the release is empty, use `_No release notes provided._`
+- Truncate release body at 2000 characters and append `... (truncated)` if needed
+- The `automated` and `claude-code-release` labels must exist in the repository; create them if missing:
+  ```bash
+  gh label create "automated" --color "#0075ca" --description "Automated issue" 2>/dev/null || true
+  gh label create "claude-code-release" --color "#e4e669" --description "Claude Code release tracking" 2>/dev/null || true
+  ```
+
+### Phase 5: Report Results
+
+After processing all versions:
+
+```
+[claude-native] Scan complete
+
+Versions checked: {N}
+New issues created: {M}
+
+Created:
+  - #1234 [Claude Code v2.1.86] New release detected
+  - #1235 [Claude Code v2.1.87] New release detected
+
+Already tracked (skipped):
+  - v2.1.85 → #683
+```
+
+If no new releases found:
+
+```
+[claude-native] No new releases found. All versions >= v2.1.86 are already tracked.
+```
+
+## Version Filtering Logic
+
+```
+MIN_VERSION = "2.1.86"
+
+For each release:
+  version = strip_v_prefix(tag_name)   # "v2.1.86" → "2.1.86"
+  parts = split(version, ".")           # ["2", "1", "86"]
+  if compare_semver(version, MIN_VERSION) >= 0:
+    include
+  else:
+    skip
+```
+
+Semver comparison: major → minor → patch (all numeric). Pre-release suffixes (e.g., `-beta`) are included and compared lexicographically after numeric parts.
+
+## Error Handling
+
+| Error | Action |
+|-------|--------|
+| `gh` not authenticated | Report: "Error: gh CLI not authenticated. Run `gh auth login` first." |
+| Rate limit hit | Report current status, list remaining versions |
+| Label creation fails | Warn and continue (issue created without label) |
+| Release body parse error | Use empty body fallback, continue |
+
+## Integration Options
+
+### Manual
+
+```
+/omcustom:claude-native
+/omcustom:claude-native --backfill
+/omcustom:claude-native --dry-run
+```
+
+### Automatic (SessionStart Hook)
+
+Can be integrated into the SessionStart hook to check for new releases at session start:
+
+```json
+{
+  "SessionStart": [
+    {
+      "command": "bash .claude/hooks/scripts/claude-native-check.sh"
+    }
+  ]
+}
+```
+
+A lightweight wrapper script can run a `--dry-run` check and notify if new releases exist.
+
+### Scheduled (CronCreate)
+
+Can be set up as a scheduled remote agent using `/schedule`:
+
+```
+/schedule "daily at 9am: /omcustom:claude-native"
+```
+
+Or via CronCreate MCP tool for programmatic scheduling.
+
+## Prerequisites
+
+- `gh` CLI installed and authenticated (`gh auth status`)
+- Repository: `baekenough/oh-my-customcode` (default, detected from git remote)
+- Labels `automated` and `claude-code-release` (auto-created if missing)
+
+## Background
+
+- Last manually tracked release: v2.1.85 (issue #683)
+- Monitoring gap: v2.1.86 onwards (customclaw deprecated 2026-03-18)
+- This skill fills the monitoring gap and provides ongoing tracking

package/templates/.claude/skills/evaluator-optimizer/SKILL.md

@@ -379,7 +379,7 @@ When ecomode is active (R013), compress output:
 - The evaluator prompt MUST include the full rubric to ensure consistent scoring
 - Iteration state (best score, best output) is tracked by the orchestrator
 - The hard cap of 5 iterations prevents runaway refinement loops
-- For multi-sprint runs (5+ iterations), consider context reset: spawn a fresh evaluator agent rather than continuing with degraded context. The workflow-runner supports this via `context: fork` on individual steps. Anthropic's research confirms "context resets provide clean slates superior to compaction" for long-running evaluation.
+- For multi-sprint runs (5+ iterations), consider context reset: spawn a fresh evaluator agent rather than continuing with degraded context. The pipeline skill supports this via `context: fork` on individual steps. Anthropic's research confirms "context resets provide clean slates superior to compaction" for long-running evaluation.
 
 ## Domain Examples
 

package/templates/.claude/skills/pipeline/SKILL.md

@@ -0,0 +1,102 @@
+---
+name: pipeline
+description: Invoke and resume YAML-defined pipelines by name — /pipeline auto-dev runs the full release pipeline
+scope: harness
+user-invocable: true
+effort: high
+argument-hint: "<pipeline-name> | resume | (no args to list available)"
+source:
+  type: external
+  origin: github
+  url: https://github.com/baekenough/baekenough-skills
+  version: 1.0.0
+---
+
+# /pipeline — Pipeline Invocation
+
+## Usage
+
+```
+/pipeline auto-dev          # Run the auto-dev pipeline
+/pipeline                   # List available pipelines
+/pipeline resume            # Resume a halted pipeline
+```
+
+## Behavior
+
+### List Mode (no arguments or --list flag)
+
+Execute these steps to display available pipelines:
+
+1. **Scan built-in pipelines**: Use `Glob("workflows/*.yaml")` (NOT templates/) to find all pipeline definitions
+2. **Extract metadata**: For each YAML file found, use `Bash` to extract name and description:
+   ```bash
+   for f in workflows/*.yaml; do
+     name=$(grep -m1 '^name:' "$f" | sed 's/^name: *//' | tr -d '"')
+     desc=$(grep -m1 '^description:' "$f" | sed 's/^description: *//' | tr -d '"')
+     echo "  $name — $desc"
+   done
+   ```
+3. **Scan template pipelines**: Use `Glob("templates/workflows/*.yaml")` for template examples
+4. **Display formatted output**:
+   ```
+   Available pipelines:
+     {name} — {description}
+     {name} — {description}
+
+   Template pipelines (in templates/workflows/):
+     {name} — {description}
+   ```
+5. If no pipelines found, display: "No pipelines found in workflows/ directory."
+6. If YAML parsing fails for a file, skip it and show: `  {filename} — (parse error, skipped)`
+
+### Run Mode (with pipeline name)
+
+1. Validate pipeline exists: `workflows/{name}.yaml`
+2. Load and validate YAML structure:
+   - Required fields: `name`, `description`, `steps[]`
+   - Each step has either `skill:` or `prompt:` (not both)
+   - Referenced skills exist in `.claude/skills/`
+   - Skill names must match `^[a-z0-9-]+$` (kebab-case only) — reject path traversal attempts
+3. Announce: `[Pipeline] Starting {name} — {step_count} steps`
+4. Execute steps top-to-bottom:
+   - **Skill steps** (`skill: name`): Invoke via Skill tool — `Skill(skill: "{name}")`
+   - **Prompt steps** (`prompt: text`): Execute the described action using appropriate agents/tools
+   - **Foreach steps** (`foreach: collection`): Iterate over collection from previous step output
+5. Report completion or failure
+
+### Resume Mode (/pipeline resume)
+
+1. Scan `/tmp/.claude-pipeline-*-{PPID}.json` for state files
+2. If none found: "No halted pipelines found."
+3. If found: display pipeline name, failed step, error message
+4. Options:
+   - **Retry** — Re-execute the failed step
+   - **Skip** — Mark failed step as skipped, continue to next
+   - **Abort** — Delete state file, cancel pipeline
+5. On resume: execute from the failed step
+
+## State Tracking
+
+Track per-step state:
+```json
+{
+  "pipeline": "{name}",
+  "started": "ISO-8601",
+  "status": "running|completed|halted",
+  "current_step": 0,
+  "steps": [
+    {"name": "triage", "status": "completed", "duration_ms": 5000},
+    {"name": "plan", "status": "running"}
+  ]
+}
+```
+
+State saved to `/tmp/.claude-pipeline-{name}-{PPID}.json` on failure.
+
+## Error Handling
+
+- Pipeline not found → list available pipelines with suggestion
+- YAML parse error → report with line number
+- Step failure (error: halt-and-report) → stop execution, save state, report failure with context
+- All file writes delegated to subagents per R010

package/templates/CLAUDE.md

@@ -104,6 +104,7 @@ oh-my-customcode로 구동됩니다.
 | `/omcustom:fix-refs` | 깨진 참조 수정 |
 | `/omcustom:harness-eval` | 15 SE task 구조적 벤치마크 평가 |
 | `/omcustom:auto-improve` | 개선 사항 자동 적용 워크플로우 |
+| `/omcustom:claude-native` | Claude Code 릴리즈 모니터링 및 이슈 자동 생성 |
 | `/omcustom:improve-report` | eval-core 기반 개선 현황 리포트 |
 | `/omcustom-takeover` | 기존 에이전트/스킬에서 canonical spec 추출 |
 | `/adversarial-review` | 공격자 관점 보안 코드 리뷰 |
@@ -130,8 +131,8 @@ oh-my-customcode로 구동됩니다.
 | `/deep-verify` | 다중 관점 릴리즈 품질 검증 |
 | `/professor-triage` | 이슈 교차 분석 트리아지 (omc_issue_analyzer 댓글 기반) |
 | `/release-plan` | verify-done 이슈 릴리즈 유닛 계획 생성 |
-| `/omcustom:workflow` | YAML 워크플로우 실행 (예: /omcustom:workflow auto-dev) |
-| `/omcustom:workflow:resume` | 중단된 워크플로우 재개 |
+| `/pipeline` | YAML 파이프라인 실행 (예: /pipeline auto-dev) |
+| `/pipeline resume` | 중단된 파이프라인 재개 |
 | `/omcustom:sauron-watch` | 전체 R017 검증 |
 | `/sdd-dev` | Spec-Driven Development 워크플로우 (sdd/ 폴더 기반) |
 | `/structured-dev-cycle` | 6단계 구조적 개발 사이클 (Plan → Verify → Implement → Verify → Compound → Done) |
@@ -150,7 +151,7 @@ project/
 +-- CLAUDE.md                    # 진입점
 +-- .claude/
 |   +-- agents/                  # 서브에이전트 정의 (46 파일)
-|   +-- skills/                  # 스킬 (100 디렉토리)
+|   +-- skills/                  # 스킬 (99 디렉토리)
 |   +-- rules/                   # 전역 규칙 (R000-R021)
 |   +-- hooks/                   # 훅 스크립트 (보안, 검증, HUD)
 |   +-- contexts/                # 컨텍스트 파일 (ecomode)

package/templates/manifest.json

@@ -1,5 +1,5 @@
 {
-  "version": "0.70.0",
+  "version": "0.71.0",
   "lastUpdated": "2026-03-24T00:00:00.000Z",
   "components": [
     {
@@ -18,7 +18,7 @@
       "name": "skills",
       "path": ".claude/skills",
       "description": "Reusable skill modules (includes slash commands)",
-      "files": 100
+      "files": 99
     },
     {
       "name": "guides",

package/templates/workflows/auto-dev.yaml

@@ -1,5 +1,5 @@
 # /omcustom:workflow auto-dev — Full-auto release pipeline
-# Pre-triages professor-labeled issues → triage verify-done → plan → implement → verify → PR → followup
+# Pre-triages open issues → triage verify-done → plan → implement → verify → PR → followup
 
 name: auto-dev
 description: "Full-auto release pipeline: pre-triage → triage → plan → implement → verify → PR → followup"
@@ -9,8 +9,8 @@ error: halt-and-report
 steps:
   - name: pre-triage
     skill: professor-triage
-    description: Run professor-triage on professor-labeled issues that lack verify-done label
-    condition: "issues with label:professor but NOT label:verify-done exist"
+    description: Run professor-triage on open issues that lack verify-done label
+    condition: "open issues without label:verify-done exist"
 
   - name: triage
     skill: professor-triage
@@ -27,7 +27,7 @@ steps:
     foreach: release-group
 
   - name: implement
-    action: implement
+    prompt: "Execute implementation plan with appropriate agents"
     description: Execute implementation plan with appropriate agents
     foreach: planned-issue
 
@@ -36,7 +36,7 @@ steps:
     description: Multi-angle release quality verification
 
   - name: release
-    action: create-pr
+    prompt: "Create release branch and pull request"
     description: Create release branch and pull request
 
   - name: followup

package/templates/.claude/skills/workflow/SKILL.md

@@ -1,68 +0,0 @@
----
-name: omcustom:workflow
-description: Invoke YAML-defined workflows by name — /omcustom:workflow auto-dev runs the full pipeline
-scope: harness
-user-invocable: true
-effort: high
-argument-hint: "<workflow-name> | (no args to list available)"
----
-
-# /omcustom:workflow — Workflow Invocation
-
-## Usage
-
-```
-/omcustom:workflow auto-dev     # Run the auto-dev workflow
-/omcustom:workflow                  # List available workflows
-/omcustom:workflow:resume           # Resume a halted workflow
-```
-
-## Behavior
-
-### List Mode (no arguments or --list flag)
-
-Execute these steps to display available workflows:
-
-1. **Scan built-in workflows**: Use `Glob("workflows/*.yaml")` (NOT templates/) to find all workflow definitions
-2. **Extract metadata**: For each YAML file found, use `Bash` to extract name and description:
-   ```bash
-   for f in workflows/*.yaml; do
-     name=$(grep -m1 '^name:' "$f" | sed 's/^name: *//' | tr -d '"')
-     desc=$(grep -m1 '^description:' "$f" | sed 's/^description: *//' | tr -d '"')
-     echo "  $name — $desc"
-   done
-   ```
-3. **Scan template workflows**: Use `Glob("templates/workflows/*.yaml")` for template examples
-4. **Extract template metadata**: Same extraction as step 2 for `templates/workflows/*.yaml`
-5. **Display formatted output**:
-   ```
-   Available workflows:
-     {name} — {description}
-     {name} — {description}
-
-   Template workflows (in templates/workflows/):
-     {name} — {description}
-   ```
-6. If no workflows found, display: "No workflows found in workflows/ directory."
-7. If YAML parsing fails for a file, skip it and show: `  {filename} — (parse error, skipped)`
-
-### Run Mode (with workflow name)
-
-1. Validate workflow exists: `workflows/{name}.yaml`
-2. Load and validate YAML structure
-3. Announce: `[Workflow] Starting {name} — {step_count} steps`
-4. Invoke workflow-runner skill with the loaded definition
-5. Report completion or failure
-
-### Resume Mode (/omcustom:workflow:resume)
-
-1. Check for state file: `/tmp/.claude-workflow-*-{PPID}.json`
-2. If found: show halted workflow name and failed step
-3. Ask: "Resume from step {N} ({step_name})?"
-4. Re-invoke workflow-runner from the failed step
-
-## Error Handling
-
-- Workflow not found → list available workflows with suggestion
-- YAML parse error → report with line number
-- Step failure → halt-and-report per workflow error policy

package/templates/.claude/skills/workflow-resume/SKILL.md

@@ -1,26 +0,0 @@
----
-name: omcustom:workflow:resume
-description: Resume a halted workflow from its last failure point
-scope: harness
-user-invocable: true
-effort: medium
----
-
-# /omcustom:workflow:resume — Resume Halted Workflow
-
-## Usage
-
-```
-/omcustom:workflow:resume            # Find and resume the most recent halted workflow
-```
-
-## Behavior
-
-1. Scan `/tmp/.claude-workflow-*-$PPID.json` for state files
-2. If none found: "No halted workflows found."
-3. If found: display workflow name, failed step, error message
-4. Options:
-   - **Retry** — Re-execute the failed step
-   - **Skip** — Mark failed step as skipped, continue to next
-   - **Abort** — Delete state file, cancel workflow
-5. On resume: invoke workflow-runner with state file context

package/templates/.claude/skills/workflow-runner/SKILL.md

@@ -1,75 +0,0 @@
----
-name: workflow-runner
-description: Execute YAML-defined workflow pipelines — parse, validate, and run multi-step skill chains
-scope: harness
-user-invocable: false
-effort: high
----
-
-# Workflow Runner
-
-## Purpose
-
-Core engine for the workflow system. Parses YAML workflow definitions from `workflows/` directory, validates step structure, and executes each step sequentially by invoking the referenced skills or actions.
-
-## Execution Protocol
-
-### 1. Load Workflow
-
-Read the specified YAML file from `workflows/{name}.yaml`. Validate:
-- Required fields: `name`, `description`, `steps[]`
-- Each step has either `skill:` or `action:` (not both)
-- Referenced skills exist in `.claude/skills/`
-- Skill names must match `^[a-z0-9-]+$` (kebab-case only) — reject path traversal attempts
-- Action values must be one of: `implement`, `create-pr` — reject unknown actions with error
-
-### 2. Execute Steps
-
-Process steps top-to-bottom:
-
-**Skill steps** (`skill: name`):
-- Invoke via Skill tool: `Skill(skill: "{name}")`
-- Capture output for next step's `input` reference
-
-**Action steps** (`action: name`):
-- `implement` — Delegate to appropriate agents based on issue domain
-- `create-pr` — Delegate to mgr-gitnerd for branch creation, push, PR
-
-**Foreach steps** (`foreach: collection`):
-- Iterate over collection from previous step output
-- Execute the step once per item
-
-### 3. Error Handling
-
-Based on workflow `error` field:
-- `halt-and-report` — Stop execution, save state, report failure with context
-- State saved to `/tmp/.claude-workflow-{name}-{PPID}.json`
-
-### 4. State Tracking
-
-Track per-step state:
-```json
-{
-  "workflow": "{name}",
-  "started": "ISO-8601",
-  "status": "running|completed|halted",
-  "current_step": 0,
-  "steps": [
-    {"name": "triage", "status": "completed", "duration_ms": 5000},
-    {"name": "plan", "status": "running"}
-  ]
-}
-```
-
-### 5. Completion
-
-On all steps completed:
-- Delete state file
-- Report summary with per-step durations
-- Output final results
-
-## Notes
-
-- This skill is invoked by the workflow bridge skill (workflow/SKILL.md)
-- It does NOT appear in slash commands (user-invocable: false)
-- All file writes delegated to subagents per R010