wf-finalize

wf-finalize is a skill for Claude Code, Codex from ParkerM2/create-claude-workflow. It costs 36 tokens per session (1,160 once invoked), scanned D, original, MIT.

The final step of an agent-team workflow that stops active agents, removes temporary worktrees, pushes the feature branch, and optionally creates a pull request.

In plain words
What is it for?
Use it after the codebase guardian to shut down agents, remove workflow markers and worktrees, delete temporary branches, push the branch, and report the result.
Why use it?
It turns completed agent work into a clean handoff while ensuring the required guardian check has already passed.

Skill for Claude CodeCodex

Part of the claude-workflow plugin — 10 skills, 25 commands, 3 agents, 6 hooks shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/parkerm2/create-claude-workflow/wf-finalize
Any agent
npx skills add ParkerM2/create-claude-workflow --skill wf-finalize
Clone the repo
git clone --depth 1 https://github.com/ParkerM2/create-claude-workflow

Made for: Claude Code, Codex.

Or install claude-workflow, the plugin that ships this one along with the rest of its 10 skills, 25 commands, 3 agents, 6 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for wf-finalize

README.md
[![agentmods](https://agentmods.dev/badge/skills/parkerm2/create-claude-workflow/wf-finalize.svg)](https://agentmods.dev/skills/parkerm2/create-claude-workflow/wf-finalize)
Your own site
<a href="https://agentmods.dev/skills/parkerm2/create-claude-workflow/wf-finalize"><img src="https://agentmods.dev/badge/skills/parkerm2/create-claude-workflow/wf-finalize.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,160 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00036 $0.01160
Opus 5 $0.00018 $0.00580
Sonnet 5 $0.00007 $0.00232
Haiku 4.5 $0.00004 $0.00116

Measured 4d ago against content hash 8a4e52b8e962, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

wf-finalize scanned grade D with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat .claude/.workflow-state/guardian-passed.json

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf .claude/.workflow-state/
skills/wf-finalize/SKILL.md · 176 lines

How it starts

The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.

WF: Finalize

Gate Check

cat .claude/.workflow-state/guardian-passed.json

If the file does not exist: STOP — "Guardian check not complete. Run Step 5 (wf-guardian) first."

Load TICKET, TEAM_LEADER_NAME, featureBranch, mode from state files.


Your Task

Clean up everything, push the branch, and hand off to the user.

Order is mandatory: shut down agents BEFORE removing sentinel BEFORE emitting session.end.


Checklist

1. Shut Down All Agents

Send shutdown_request to every active agent on the team. Check wave-<N>-spawned.json files for agent names if unsure who is running:

SendMessage(to: "<agent-name>", message: {"type": "shutdown_request"})

Wait for each to acknowledge or time out (30s max per agent).

2. Remove Sentinel File

rm -f .claude/.workflow-active

3. Clean Remaining Worktrees

git worktree list --porcelain \
  | grep "worktree.*<worktreeDir>/<TICKET>" \
  | awk '{print $2}' \
  | xargs -r -I{} git worktree remove --force {}

git branch --list "<workPrefix>/<TICKET>/*" \
  | xargs -r git branch -D

4. Push Feature Branch

git push origin <featureBranch>

5. Create PR (if requested or strict mode)

Ask the user: "Create a PR for <featureBranch>? (y/n)"

If yes:

gh pr create \
  --title "<TICKET>: <feature summary>" \
  --body "$(cat << 'EOF'
## Summary

<bullet list of tasks completed>

## Changes

<files modified>

## Test plan

- [ ] QA passed all tasks
- [ ] Codebase Guardian passed
- [ ] Wave fence passed
EOF
)" \
  --base <baseBranch>

6. Compile & Write Run Report

Read ./progress/<TICKET>/events.jsonl and compile metrics from it.

From agent.spawned events — extract per-agent rows:

  • agent: agent name
  • model: model field from event data (if present)
  • role: role field from event data (if present)
  • start: timestamp of the agent.spawned event (HH:MM)
  • duration: difference between agent.spawned and the matching agent.completed event
  • input / output / cache_read / cache_write: token fields from event data (if present, else )
  • skills: skills field from event data (if present, else )

Read the full file on GitHub · 176 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 176 lines · 36 tokens per session scan D 8a4e52b8e962

Subscribe to this mod's changes

wf-finalize is a skill published in the GitHub repository ParkerM2/create-claude-workflow (4 stars, last pushed 5mo ago), licensed MIT. It adds 36 tokens to every session and 1,160 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens