A command for creating Git commits that follow Conventional Commits, a shared format such as feat(scope): description or fix(scope): description. It checks the repository state and recent commit style before staging relevant files and committing.

Use it when changes are ready to save in Git. It helps choose a commit type, optional scope, concise description, breaking-change marker, and specific files to stage.

It reduces inconsistent commit messages and avoids accidentally staging unrelated changes. It also preserves normal verification hooks instead of skipping them.

commit — Skill for Claude Code by epicsagas/epic-harness

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 epicsagas/epic-harness --skill commit

Clone the repo

git clone --depth 1 https://github.com/epicsagas/epic-harness

Made for: Claude Code.

Or install epic, the plugin that ships this one along with the rest of its 27 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/epicsagas/epic-harness/commit/github.svg)](https://agentmods.dev/skills/epicsagas/epic-harness/commit)

Your own site

<a href="https://agentmods.dev/skills/epicsagas/epic-harness/commit"><img src="https://agentmods.dev/badge/skills/epicsagas/epic-harness/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/epicsagas/epic-harness/commit"><img src="https://agentmods.dev/badge/skills/epicsagas/epic-harness/commit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 630 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.

Model	Per session	Once invoked
Fable 5.1	$0.00031	$0.00630
Opus 5.5	$0.00012	$0.00252
Sonnet 5.5	$0.00006	$0.00126
Haiku 4.5	$0.00003	$0.00063

Measured 1mo ago against content hash f95270a92f92, 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 · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Commit — Conventional Commits Generator

When to Trigger

User wants to commit, save, or check in changes
User asks to commit after completing a task
Code changes are ready and user signals completion

Process

Gather context — run in parallel:
- git status — see what changed
- git diff HEAD — see the actual diff
- git log --oneline -5 — match existing commit style

Determine type:

Type	When
`feat`	New feature or capability
`fix`	Bug fix
`refactor`	Code change, no behavior change
`docs`	Documentation only
`test`	Adding or correcting tests
`build`	Build system or dependencies
`chore`	Maintenance task
`ci`	CI/CD configuration
`style`	Formatting, whitespace
`perf`	Performance improvement

Generate message: type(scope): description
- Lowercase type, optional scope
- Imperative mood, no period, under 72 chars
- Breaking changes: append ! before :
- Body only when diff needs extra context (max 3 bullet points)
Stage and commit:
- git add <specific files> — prefer explicit files over git add -A
- git commit -m "type(scope): description"
- Execute automatically — no confirmation needed

Anti-Rationalization

Excuse	Rebuttal	What to do instead
"I'll just use a generic message"	Generic messages make git history useless.	Spend 5 seconds analyzing the diff — the type and scope are obvious from the changes.
"The user didn't specify a format"	Conventional Commits is the project standard — guard will block non-CC messages anyway.	Always generate CC format.
"I'll commit everything together"	Unrelated changes in one commit make bisect and revert impossible.	If changes span multiple concerns, suggest splitting first.

Evidence Required

git status checked before staging
Only relevant files staged (not git add -A blindly)
Message follows type(scope): description format
Type accurately reflects the change (feat ≠ fix ≠ refactor)

Read the full file on GitHub · 65 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.

1mo ago First seen · 65 lines · 31 tokens per session scan A f95270a92f92

Subscribe to this mod's changes

commit is a skill published in the GitHub repository epicsagas/epic-harness (18 stars, last pushed 7d ago), licensed Apache-2.0. It adds 31 tokens to every session and 630 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 2026-08-30.

Claude Code Commits Git and workflow LLM ai-agent claude cli developer-tools

git

Run git version control commands for repository management. Use when the user asks to check status, view history or diffs, stage and commit changes, manage branches, merge or rebase, work with remotes, stash changes, tag releases, cherry-pick commits, bisect regressions, resolve conflicts, manage worktrees or…

bug-ops/zeph · 106 tokens

knowledge-shell-process-and-worktree

Shell and Git worktree support for running commands, managing long-lived processes, and giving sessions isolated working directories. A Git worktree is a separate checkout linked to the same repository.

echoVic/blade-code · 164 tokens

datalad

Retrieve, version, and publish scientific datasets with DataLad and git-annex, and capture computational provenance with datalad run, rerun, and containers-run. Use when cloning or fetching data from OpenNeuro, DANDI, datasets.datalad.org, or any DataLad dataset; when a file in a dataset reads as a broken symlink or a…

synthetic-sciences/openscience · 146 tokens

commit