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 aegntic/compound-engineering --skill finishing-branchgit clone --depth 1 https://github.com/aegntic/compound-engineeringWrote 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/aegntic/compound-engineering/finishing-branch)<a href="https://agentmods.dev/skills/aegntic/compound-engineering/finishing-branch"><img src="https://agentmods.dev/badge/skills/aegntic/compound-engineering/finishing-branch/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/aegntic/compound-engineering/finishing-branch"><img src="https://agentmods.dev/badge/skills/aegntic/compound-engineering/finishing-branch.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 | $0.00024 | $0.01299 |
| Opus 5 | $0.00012 | $0.00649 |
| Sonnet 5 | $0.00005 | $0.00260 |
| Haiku 4.5 | $0.00002 | $0.00130 |
Grade A, and why
finishing-branch 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Finishing a Development Branch
A structured skill for completing work on a feature branch. Ensures all quality checks pass, presents clear options for what to do next, and handles cleanup.
Announce at start: "I'm using the finishing-branch skill to complete this work."
When to Use
- All implementation tasks are complete
- You are ready to ship or merge a feature branch
- Referenced at the end of
workflows:workPhase 4 - Referenced by
/lfgpipeline
When NOT to Use
- Work is still in progress (finish tasks first)
- You are on the default branch (nothing to finish)
The Process
Step 1: Final Verification
Run all quality checks and report results:
# 1. Run full test suite (detect project test command)
# npm test | pytest | cargo test | phpunit | go test | etc.
# 2. Run linting (detect project linter)
# eslint | ruff | clippy | pint | etc.
# 3. Check for uncommitted changes
git status
# 4. Check for untracked files that should be committed
git ls-files --others --exclude-standard
Report results clearly:
- Tests: X passed, Y failed (if any fail, stop here and fix first)
- Linting: pass/fail (if fail, fix first)
- Uncommitted changes: list them
- Untracked files: list them
Do NOT proceed if tests or linting fail. Fix issues first, then return to Step 1.
Step 2: Commit Remaining Changes
If there are uncommitted changes:
git add <relevant files>
git commit -m "feat(scope): final changes before merge
[description of what's included]"
Stage files selectively -- do not blindly git add . if there are files that should not be committed.
Step 3: Present Completion Options
Present the user with clear options:
Option A: Create a Pull Request (recommended for team projects)
- Push branch and generate PR description
- Include summary of changes, testing notes, screenshots (if UI)
- Include Post-Deploy Monitoring section
Option B: Merge to default branch (for solo projects or pre-approved changes)
- Verify the default branch is up to date
- Merge the feature branch
- Push the result
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.
- 9d ago First seen · 204 lines · 24 tokens per session scan A 8379bf043c14
finishing-branch is a skill published in the GitHub repository aegntic/compound-engineering (2 stars, last pushed 3mo ago), licensed MIT. It adds 24 tokens to every session and 1,299 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
bump-version
Bump the Logic-Lens version across all six metadata locations at once (package.json, the four plugin manifests, and the README badge), then validate. Use when cutting a release or when npm run validate reports a version mismatch.
Cross-File Leakage リファクタ後の caller 側残骸検出
A code review check for structural changes such as renamed functions, changed arguments, moved files, or split modules. It searches the rest of the project for callers that still use the old structure.
PRテンプレート品質チェック
A review skill for checking pull-request templates, which are forms that guide what developers include when proposing code changes. It checks items such as language, documentation types, verification commands, and checklists.
GitHubレビューコメント対応（修正案つき）
A review workflow for handling comments on a GitHub pull request, which is a proposed code change. It groups comments by importance, records what remains unresolved, and prepares replies and small fix plans.
commit
Git commit workflow with precommit hook handling, lint/type checking, README updates, and API reference updates. Use when the user wants to commit changes. Handles precommit hooks that modify files (formatting, linting) by re-staging and retrying. Runs ruff lint and pyright type checks on staged Python files, and…
update-pr
Update an existing pull request with new changes. Use when the user wants to update a PR, push follow-up changes to a PR, refresh a PR description, or sync a PR with latest commits. Triggers on: update pr, update-pr, update the pr, push to pr, refresh pr, sync pr, update pull request.