commit

commit is a skill for Claude Code from billbuchanan-code/claude-code-power-setup. It costs 34 tokens per session (624 once invoked), scanned A, original, MIT.

A workflow tool that stages selected project files, creates a conventional Git commit, and pushes the commit to a remote repository.

In plain words
What is it for?
Use it when you need to commit and push current work according to the project's conventions.
Why use it?
It gives a repeatable way to package and publish changes while avoiding accidental staging of unrelated files or secrets.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

Good fit Use it when you need to commit and push current work according to the project's conventions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/billbuchanan-code/claude-code-power-setup/commit
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 billbuchanan-code/claude-code-power-setup --skill commit
Clone the repo
git clone --depth 1 https://github.com/billbuchanan-code/claude-code-power-setup

Made for: Claude Code.

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 commit

README.md
[![agentmods](https://agentmods.dev/badge/skills/billbuchanan-code/claude-code-power-setup/commit/github.svg)](https://agentmods.dev/skills/billbuchanan-code/claude-code-power-setup/commit)
Your own site
<a href="https://agentmods.dev/skills/billbuchanan-code/claude-code-power-setup/commit"><img src="https://agentmods.dev/badge/skills/billbuchanan-code/claude-code-power-setup/commit/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 commit

Your own site · 80×15
<a href="https://agentmods.dev/skills/billbuchanan-code/claude-code-power-setup/commit"><img src="https://agentmods.dev/badge/skills/billbuchanan-code/claude-code-power-setup/commit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 624 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 $0.00034 $0.00624
Opus 5.5 $0.00014 $0.00250
Sonnet 5.5 $0.00007 $0.00125
Haiku 4.5 $0.00003 $0.00062

Measured 1mo ago against content hash eb255c6dcb23, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

commit 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 1mo 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/commit/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Commit Skill

Stage, commit, and push the current changes following the user's established conventions.

When to Activate

Trigger this skill when the user says any of:

  • /commit
  • "push it"
  • "commit this"
  • "commit and push"
  • "document, commit and push"
  • "document commit and push"

Process

Step 1: Gather State (parallel)

Run these commands in parallel:

  1. git status — see all modified, staged, and untracked files
  2. git diff --stat — summary of unstaged changes
  3. git diff --cached --stat — summary of already-staged changes
  4. git log --oneline -5 — recent commit messages for style reference

Step 2: Determine What to Stage

  • Stage all modified and new files that are part of the current work
  • Never use git add . or git add -A — always stage specific files by name
  • Skip .env files, credentials, secrets, and large binaries
  • If the user said "document" (e.g., "document, commit and push"), update relevant documentation before staging

Step 3: Write the Commit Message

  • Read the recent git log output from Step 1 to match the repository's commit style
  • Summarize the nature of changes: new feature, enhancement, bug fix, refactor, docs, etc.
  • Use imperative mood ("Add feature" not "Added feature")
  • Keep the first line under 72 characters
  • Add a blank line and body if the changes warrant explanation
  • End with: Co-Authored-By: Claude <[email protected]>
  • Use a HEREDOC to pass the message to git commit -m

Step 4: Commit and Push

Run sequentially:

  1. git add <specific files>
  2. git commit with the HEREDOC message
  3. git push
  4. git status — verify clean working tree

If the commit fails due to a pre-commit hook, fix the issue and create a new commit (never amend).

Step 5: Report

Output a brief summary:

  • Files committed
  • Commit message used
  • Push status (success or any errors)

Rules

  • Never amend a previous commit unless the user explicitly asks
  • Never use --no-verify or skip hooks
  • Never force push unless explicitly asked (and warn if targeting main/master)
  • If there are no changes to commit, say so and stop
  • If pushing fails (e.g., no upstream), set upstream with git push -u origin <branch>

Read the full file on GitHub · 77 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. 1mo ago First seen · 77 lines · 34 tokens per session scan A eb255c6dcb23

Subscribe to this mod's changes

commit is a skill published in the GitHub repository billbuchanan-code/claude-code-power-setup (2 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 624 once invoked, about $0.0001 per session on Opus 5.5. 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.