commit-message

Guidance for writing a Git commit message, the short record that describes a set of code changes.

In plain words
What is it for?
Use it with staged or unstaged changes when drafting or finalising a commit message, including Conventional Commits formatting and issue references.
Why use it?
It turns a diff into a consistent summary that explains what changed and why, including a warning when a public contract is broken.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/tahirraufkeeyu/software-development-agent-stack--sdas/commit-message
Any agent
npx skills add tahirraufkeeyu/software-development-agent-stack--sdas --skill commit-message
Clone the repo
git clone --depth 1 https://github.com/tahirraufkeeyu/software-development-agent-stack--sdas

Made for: Claude Code, Codex.

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,622 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00055 $0.01622
Opus 5 $0.00028 $0.00811
Sonnet 5 $0.00011 $0.00324
Haiku 4.5 $0.00006 $0.00162

Measured 3d ago against content hash f97c21926808, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

commit-message 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 3d 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.

departments/developers/skills/commit-message/SKILL.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When to use

  • User runs git add and asks for a commit message.
  • User pastes a diff and asks "what's a good commit message for this".
  • User finishes a task and asks the agent to commit (combine with a separate commit tool/skill that actually runs git).

Do not use this skill to write a PR description (longer, audience-different) or a changelog entry (see the documentation skill).

Inputs

  • A staged diff (git diff --cached) or an unstaged diff. If none is provided, fetch git status and git diff --cached from the repo.
  • Optional: related issue/ticket id, prior commit for context, the branch name if it encodes intent.

Outputs

A commit message with:

  • Subject line: <type>[optional scope][!]: <imperative summary>, <= 72 characters.
  • Optional body: wrapped at 72 columns, explaining the why, constraints considered, alternatives rejected.
  • Optional footers: Refs: #123, Closes: #123, BREAKING CHANGE: <what>, Co-authored-by: ....

Tool dependencies

  • Bash for git status, git diff --cached, git log -n 20 --oneline (style calibration).
  • Read/Grep to glance at touched files when the diff alone is ambiguous.

Procedure

  1. Read the diff. If it is empty, ask for the staged changes or run git diff --cached.
  2. Calibrate to the repo's style. Run git log -n 20 --pretty=format:'%s'. If the repo already uses Conventional Commits, match exactly (types, scope format, capitalisation). If not, propose Conventional Commits and follow the user's existing conventions where they conflict.
  3. Classify the change into one type:
    • feat — a user-facing new capability.
    • fix — a bug fix observable to users or other systems.
    • perf — a change that improves performance without changing behaviour.
    • refactor — internal restructuring, no behaviour change.
    • docs — documentation only.
    • test — tests only.
    • build — build system, dependencies, packaging.
    • ci — CI/CD configuration.
    • chore — maintenance (bumping deps, cleanup) that is neither feat nor fix.
    • revert — reverts a previous commit.
  4. Pick a scope if the repo uses them. Scope is usually a package, module, or subsystem (auth, api, billing). Omit the scope entirely rather than invent one.
  5. Write the subject as an imperative phrase starting lowercase after the colon. "Add", "fix", "rename", never "added" or "adds". Cap at 72 characters; aim for <= 50.
  6. Decide on a body:
    • If the diff is a one-liner obvious from the subject, no body.
    • Otherwise, a body answering: why is this change needed; what is the approach; what alternatives were considered and rejected; what risks remain.
    • Hard-wrap at 72 columns. Separate subject and body with one blank line.
  7. Add footers:
    • Refs: #<n> or Closes: #<n> when linked to an issue.
    • BREAKING CHANGE: <description> when the diff removes or alters a public API, wire format, CLI flag, config key, database column, or event shape. Also append ! before the colon in the subject.
    • Co-authored-by: when pair programming.
  8. Never include implementation trivia the commit hash already captures ("changed 3 files", "added 42 lines"). Instead, state the user-visible or contract-level effect.
  9. Check length and wrap. Return the final message in a single fenced block so the user can paste it directly.

Read the full file on GitHub · 144 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. 3d ago First seen · 144 lines · 55 tokens per session scan A f97c21926808

Subscribe to this mod's changes

commit-message is a skill published in the GitHub repository tahirraufkeeyu/software-development-agent-stack--sdas (18 stars, last pushed 4mo ago), licensed MIT. It adds 55 tokens to every session and 1,622 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

git-workflow-and-versioning

Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, opening or reviewing a pull request (PR), pushing to a remote, or when you need to organize work across multiple parallel streams. Use when cutting a release, choosing a semantic version bump…

addyosmani/agent-skills · 74 tokens

prowler-commit

Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.

prowler-cloud/prowler · 33 tokens

git-commit

Generate well-formatted git commit messages following conventional commit standards.

ThinkInAIXYZ/deepchat · 15 tokens

git-workflow

This skill should be used when the user asks to "create git commit", "manage branches", "follow git workflow", "use Conventional Commits", "handle merge conflicts", or asks about git branching strategies, version control best practices, pull request workflows. Provides comprehensive Git workflow guidance for team…

Galaxy-Dawn/claude-scholar · 64 tokens

commits

Use this skill whenever the user asks to commit changes, write or fix a commit message, amend or rename a commit, or do a workflow that includes committing in the IntelliJ repository. This is a thin repo-specific overlay: use IntelliJ commit format, write full commit messages by default, and keep requested suffixes…

JetBrains/MPS · 78 tokens

contributing

How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the…

HugoRCD/evlog · 68 tokens