commit

commit is a skill for Claude Code, Codex from DJRHails/dotfiles. It costs 11 tokens per session (854 once invoked), scanned A, original, MIT.

Instructions for creating a Git commit, which is a saved checkpoint of code changes, using a standard subject format. They also cover which branch to use and what files to leave out.

In plain words
What is it for?
Use them when committing and pushing changes to a Git repository.
Why use it?
They make commits easier to understand and reduce the risk of committing secrets or pushing changes directly to the default branch.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions AGENTS.md.

Good fit Use them when committing and pushing changes to a Git repository.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/djrhails/dotfiles/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 DJRHails/dotfiles --skill commit
Clone the repo
git clone --depth 1 https://github.com/DJRHails/dotfiles

Made for: Claude Code, Codex.

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/djrhails/dotfiles/commit/github.svg)](https://agentmods.dev/skills/djrhails/dotfiles/commit)
Your own site
<a href="https://agentmods.dev/skills/djrhails/dotfiles/commit"><img src="https://agentmods.dev/badge/skills/djrhails/dotfiles/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/djrhails/dotfiles/commit"><img src="https://agentmods.dev/badge/skills/djrhails/dotfiles/commit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 11 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 854 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 $0.00011 $0.00854
Opus 5.5 $0.00004 $0.00342
Sonnet 5.5 $0.00002 $0.00171
Haiku 4.5 $0.00001 $0.00085

Measured 1mo ago against content hash bd89e0c67ae7, 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.

modules/agents/skills/commit/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create a git commit for the current changes using a concise Conventional Commits-style subject.

Format

<type>(<scope>): <summary>

  • type REQUIRED. Use feat for new features, fix for bug fixes. Other common types: docs, refactor, chore, test, perf.
  • scope OPTIONAL. Short noun in parentheses for the affected area (e.g., api, parser, ui).
  • summary REQUIRED. Short, imperative, <= 72 chars, no trailing period.

Notes

  • Body is OPTIONAL. If needed, add a blank line after the subject and write short paragraphs.
  • Do NOT include breaking-change markers or footers.
  • Do NOT add sign-offs (no Signed-off-by).
  • After committing, push to the current branch. Never push to main/the default branch — if you are on it (and the repo's AGENTS.md/CLAUDE.md doesn't forbid branching), create a feature branch (<github-username>/<feature-name>) first, then push with -u.
  • Skip files containing secrets (.env, credentials, tokens) and warn if any are staged. Skip .agents/settings.local.json / .claude/settings.local.json — add them to .gitignore if not already ignored.
  • If it is unclear whether a file should be included, ask the user which files to commit.
  • Treat any caller-provided arguments as additional commit guidance. Common patterns:
    • Freeform instructions should influence scope, summary, and body.
    • File paths or globs should limit which files to commit. If files are specified, only stage/commit those unless the user explicitly asks otherwise.
    • If arguments combine files and instructions, honor both.

If CI doesn't start after a push

A push to a PR branch that spawns no workflow run is almost never a credential problem. Check the cheap causes first, in order:

  1. Conflicted PR — gh pr view <n> --json mergeable,mergeStateStatus. A PR with mergeable: CONFLICTING / mergeStateStatus: DIRTY creates no pull_request runs at all: GitHub can't build the refs/pull/<n>/merge test-merge commit those runs execute against. Merge or rebase the base branch, resolve, push — CI resumes on its own.
  2. Trigger filters — read the workflow's on: block. push: branches: [main] means feature-branch pushes get CI only via the pull_request event; paths: filters can skip a commit entirely.
  3. Token type — only then suspect the credential (gh auth status): an Actions-issued ghs_ token suppresses workflow triggering; a user PAT (ghp_/github_pat_) does not.

Read the full file on GitHub · 54 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 · 54 lines · 11 tokens per session scan A bd89e0c67ae7

Subscribe to this mod's changes

commit is a skill published in the GitHub repository DJRHails/dotfiles (2 stars, last pushed today), licensed MIT. It adds 11 tokens to every session and 854 once invoked, about $0.0000 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.