finish

finish is a skill for Claude Code from arbazkhan971/godmode. It costs 49 tokens per session (1,290 once invoked), scanned A, original, MIT.

A guide for closing out a development branch after work is complete. A branch is a separate line of code changes used to develop a feature or fix before it is merged into the main project.

In plain words
What is it for?
Use it to inspect branch changes, run build, lint, and test checks, squash commits, create or finalize a pull request, or keep or discard the branch as appropriate.
Why use it?
It checks that the branch is clean and validated before merging, helping avoid unfinished changes or failing builds entering the main codebase.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the godmode plugin — 132 skills, 1 command, 7 agents, 3 MCP servers shipped together

Good fit Use it to inspect branch changes, run build, lint, and test checks, squash commits, create or finalize a pull request, or keep or discard the branch as appropriate.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/arbazkhan971/godmode/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 arbazkhan971/godmode --skill finish
Clone the repo
git clone --depth 1 https://github.com/arbazkhan971/godmode

Made for: Claude Code.

Or install godmode, the plugin that ships this one along with the rest of its 132 skills, 1 command, 7 agents, 3 MCP servers.

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/arbazkhan971/godmode/finish/github.svg)](https://agentmods.dev/skills/arbazkhan971/godmode/finish)
Your own site
<a href="https://agentmods.dev/skills/arbazkhan971/godmode/finish"><img src="https://agentmods.dev/badge/skills/arbazkhan971/godmode/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/arbazkhan971/godmode/finish"><img src="https://agentmods.dev/badge/skills/arbazkhan971/godmode/finish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,290 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 165
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
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 $0.00049 $0.01290
Opus 5 $0.00024 $0.00645
Sonnet 5 $0.00010 $0.00258
Haiku 4.5 $0.00005 $0.00129

Measured 9d ago against content hash 247b9b0e3619, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 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.

skills/finish/SKILL.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Activate When

  • /godmode:finish, "done", "merge", "finalize"
  • Feature branch has commits ahead of main
  • Another skill completes and branch is ready

Auto-Detection

Routes here when:

  • git log main..HEAD --oneline returns 1+ commits AND user says "done", "merge", "finish"
  • /godmode:build completes all tasks
  • User explicitly invokes /godmode:finish

Workflow

1. Snapshot Branch State

branch=$(git branch --show-current)
commits=$(git log main..HEAD --oneline | wc -l | tr -d ' ')
files_changed=$(git diff main..HEAD --stat | tail -1)
echo "Branch: $branch | $commits commits | $files_changed"

# Check if on main
if [ "$branch" = "main" ]; then
  echo "ERROR: Already on main. Nothing to finish."
  exit 1
fi

2. Enforce Clean Worktree

staged=$(git diff --cached --name-only)
unstaged=$(git diff --name-only)
untracked=$(git ls-files --others --exclude-standard)
IF staged non-empty: STOP — commit or stash first
IF unstaged non-empty: STOP — commit, stash, or discard
IF untracked files: WARN — won't be in merge

3. Run Full Guard Suite

build_cmd && lint_cmd && test_cmd
THRESHOLDS:
  Build: must exit 0
  Lint: must exit 0 with --max-warnings=0
  Tests: 100% pass rate required
  IF any failure: STOP, run /godmode:fix first
  IF no test runner: WARN, continue

4. Check Merge Conflicts

git fetch origin main
git merge-tree \
  $(git merge-base HEAD origin/main) origin/main HEAD

IF conflicts: print files, recommend rebase.

5. Determine Outcome

PRIORITY (first match wins):
  DISCARD: user says "discard", "abandon" (confirm)
  KEEP: user says "keep", "not yet", "park it"
  MERGE: user says "merge" OR PR approved
  PR: default when checks pass

6. Execute Outcome

MERGE:

git checkout main && git pull origin main
git merge --squash {branch}
git commit -m "feat({module}): {title}

Squashed {N} commits from {branch}."
git branch -d {branch}

PR:

gh pr create --title "feat({module}): {title}" \
  --body "## Changes
$(git log main..HEAD --format='- %s')

## Guard Results
Build: PASS | Lint: PASS | Tests: PASS"

Read the full file on GitHub · 189 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. 9d ago First seen · 189 lines · 49 tokens per session scan A 247b9b0e3619

Subscribe to this mod's changes

finish is a skill published in the GitHub repository arbazkhan971/godmode (26 stars, last pushed 11d ago), licensed MIT. It adds 49 tokens to every session and 1,290 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 2026-08-30.