finish

finish is a skill for Claude Code from yash-gadodia/claude-init. It costs 39 tokens per session (500 once invoked), scanned A, original, MIT.

A process for closing completed development work after checking tests and project requirements. It then offers ways to merge, publish, keep, or discard the work.

In plain words
What is it for?
Use it after implementation and review to run verification and choose what happens to the branch.
Why use it?
It reduces the chance of landing unfinished or unverified changes and makes the final repository action explicit.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the claude-init plugin — 11 skills, 1 command, 7 agents shipped together

Good fit Use it after implementation and review to run verification and choose what happens to the branch.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yash-gadodia/claude-init/finish
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.

Any agent
npx skills add yash-gadodia/claude-init --skill finish
Clone the repo
git clone --depth 1 https://github.com/yash-gadodia/claude-init

Made for: Claude Code.

Or install claude-init, the plugin that ships this one along with the rest of its 11 skills, 1 command, 7 agents.

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 finish

README.md
[![agentmods](https://agentmods.dev/badge/skills/yash-gadodia/claude-init/finish/github.svg)](https://agentmods.dev/skills/yash-gadodia/claude-init/finish)
Your own site
<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.

agentmods 80×15 button for finish

Your own site · 80×15
<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>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 500 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00039 $0.00500
Opus 5 $0.00019 $0.00250
Sonnet 5 $0.00008 $0.00100
Haiku 4.5 $0.00004 $0.00050

Measured 10d ago against content hash d06c619f6f8f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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.

templates/skills/finish/SKILL.md · 69 lines

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:

  1. Merge locally — merge feature branch into base, delete feature branch
  2. Push & create PR — push branch, create PR with summary + test plan
  3. Keep branch — preserve as-is for later
  4. Discard — permanently delete branch and all changes

4. Execute

Merge locally:

  1. git checkout <base> and git pull
  2. git merge <feature-branch>
  3. Run tests again — merges can introduce conflicts that break things
  4. git branch -d <feature-branch>

Push & create PR:

  1. git push -u origin <feature-branch>
  2. Create PR via gh pr create with 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
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. 10d ago First seen · 69 lines · 39 tokens per session scan A d06c619f6f8f

Subscribe to this mod's changes

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.