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.
npx skills add pwdev-solucoes/pwdev-claude-marketplace --skill power-finishgit clone --depth 1 https://github.com/pwdev-solucoes/pwdev-claude-marketplaceWrote 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.
[](https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/power-finish)<a href="https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/power-finish"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/power-finish/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/power-finish"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/power-finish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00031 | $0.00518 |
| Opus 5 | $0.00015 | $0.00259 |
| Sonnet 5 | $0.00006 | $0.00104 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
power-finish scanned grade A with 0 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 7d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Finish a Branch
Read safety before acting.
Step 1 — Green first
Run the full suite. If it fails, report it and stop. The menu below does not appear until the suite is green — offering integration options over a red suite invites choosing one.
Step 2 — Capture the environment
Record WORKTREE_PATH and the current branch now, before any step changes directories.
Step 5 moves you, and a path captured after the move points at the wrong place.
Step 3 — Confirm the base
Ask which branch this integrates into. Do not assume main; do not read it from a config and
proceed silently.
Step 4 — The menu
Present exactly these, and wait:
- Merge locally into the base branch.
- Push and open a pull request.
- Leave it as is — keep the branch and the worktree.
In detached HEAD, only options 2 and 3 apply; say why.
Discarding is not on the menu. If the human asks to discard, require them to type the word
discard, and confirm what will be lost first.
Step 5 — Execute
Merge locally: merge before removing anything, then run the suite again on the merged result. Two branches that each pass can fail together, and that failure belongs to whoever merged them.
Pull request: push, open it, and keep the worktree. Review feedback gets fixed there, and a removed worktree means recreating it in an hour.
Leave it: record where it is and what state it is in, so the next session does not rediscover it.
Step 6 — Cleanup
Only remove worktrees under .worktrees/ or worktrees/, and only ones this work created.
git worktree remove <path>
git worktree prune
If removal is refused because of uncommitted files, do not add --force on your own
initiative. Show git status --porcelain -uall and offer: commit them, stash them, or leave
the worktree in place. The refusal is git protecting work that someone may want.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 62 lines · 31 tokens per session scan A e81d93c43086
power-finish is a skill published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed today), licensed Apache-2.0. It adds 31 tokens to every session and 518 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
verify-and-ship
Run all quality checks (tests, lint, typecheck), fix failures, update the changelog, commit, push, and create/update the pull request or merge request.
ship-workflow
Automated release pipeline: merges main, runs tests, pre-landing review, version bump, changelog, bisectable commits, and PR creation. Triggers on: "ship it", "release this", "prepare for release", "open a PR", "push and PR", "land this", "/ship-workflow".
AI Release Guardian
Analyze a git diff, map affected risks, select the tests that matter, detect coverage gaps on changed lines, run configurable quality gates, and produce a go/no-go release report with cited evidence. Recommends only; never merges or deploys.
mathodology-dev-test-release
Use when checking skill metadata, references or repository boundaries, or preparing an explicitly requested skills release.
repo-harness-check
Verification entrypoint for repo-harness workflow readiness. Runs workflow gates, task sync, contract checks, inspector, and migration dry-run before merge or release.