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 yash-gadodia/claude-init --skill finishgit clone --depth 1 https://github.com/yash-gadodia/claude-initWrote 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/yash-gadodia/claude-init/finish)<a href="https://agentmods.dev/skills/yash-gadodia/claude-init/finish"><img src="https://agentmods.dev/badge/skills/yash-gadodia/claude-init/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/yash-gadodia/claude-init/finish"><img src="https://agentmods.dev/badge/skills/yash-gadodia/claude-init/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 | $0.00039 | $0.00500 |
| Opus 5 | $0.00019 | $0.00250 |
| Sonnet 5 | $0.00008 | $0.00100 |
| Haiku 4.5 | $0.00004 | $0.00050 |
Grade A, and why
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 10d 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: Land Your Work
Verify, present options, execute, clean up.
When This Triggers
Automatically after all implementation tasks pass review and verification.
Process
1. Verify
Run the FULL test suite. If ANY test fails, STOP. Fix before proceeding.
If docs/definition-of-done.md exists, run through its checklist too — tests passing is necessary but not sufficient to land.
2. Determine Base Branch
Check what branch you split from (git log --oneline --graph -10). Usually main or master. Ask if unclear.
3. Present Options
Show exactly these four choices:
- Merge locally — merge feature branch into base, delete feature branch
- Push & create PR — push branch, create PR with summary + test plan
- Keep branch — preserve as-is for later
- Discard — permanently delete branch and all changes
4. Execute
Merge locally:
git checkout <base>andgit pullgit merge <feature-branch>- Run tests again — merges can introduce conflicts that break things
git branch -d <feature-branch>
Push & create PR:
git push -u origin <feature-branch>- Create PR via
gh pr createwith summary and test plan sections
Keep branch:
- Do nothing. Note branch name for the user.
Discard:
- Ask user to type "discard" to confirm
git checkout <base>git branch -D <feature-branch>- Remove worktree if applicable
5. Clean Up
- Remove git worktree if applicable
- Summarize what was done
Rules
- NEVER merge without passing tests
- NEVER delete work without typed "discard" confirmation
- Always present all 4 options — don't assume which one the user wants
- Re-run tests after merge (merge can introduce breakage)
- If on main/master (no feature branch), only offer PR/keep/discard
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.
- 10d ago First seen · 69 lines · 39 tokens per session scan A d06c619f6f8f
finish is a skill published in the GitHub repository yash-gadodia/claude-init (5 stars, last pushed 3d ago), licensed MIT. It adds 39 tokens to every session and 500 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 2026-08-31.
Other skills, from other repositories
release
Prepare code for release (version bumps, changelog, README updates) and create an annotated tag to trigger the GoReleaser workflow.
commit-msg
You receive a git diff of staged changes via stdin. Generate a commit message.
github-issue-fix-flow
Use when asked to take a GitHub issue number, implement a fix, run builds/tests, commit with a closing message, and push. End-to-end workflow using gh CLI, local code changes, and git.
release-app-store-changelog
Create user-facing App Store release notes from git history. Use when asked to generate release changelog, App Store "What's New" text, or release notes based on git tags.
commit
Use when committing changes, staging files, saving work, or making a git commit. Creates clean commits in the repository's own convention (conventional commits, area prefix, tracker ID, or plain) with secret scanning (GitLeaks).
create-pr
Use when opening a PR, submitting for review, pushing a branch, or creating a pull request. Pushes and creates GitHub PRs with auto-assignment and description.