What is commit-messages?

A set of Git commit-message rules for the Campfire repository. Git is the version-control system used to record code changes, and these rules define the required one-line format and branch behaviour.

Use it before creating, amending, squashing, or rewriting any commit message in this repository.

It prevents inconsistent commit messages and stops an agent from committing, branching, or adding attribution text against the project's policy.

How pandulapeter/campfire configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to pandulapeter/campfire. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/pandulapeter/campfire/master/.claude/skills/commit-messages/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/pandulapeter/campfire

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/pandulapeter/campfire/commit-messages/github.svg)](https://agentmods.dev/skills/pandulapeter/campfire/commit-messages)

Your own site

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

Per session 140 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 659 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	$0.00140	$0.00659
Opus 5.5	$0.00056	$0.00264
Sonnet 5.5	$0.00028	$0.00132
Haiku 4.5	$0.00014	$0.00066

Measured 4d ago against content hash 9c836cc4caad, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

commit-messages 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 4d 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.

.claude/skills/commit-messages/SKILL.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Campfire branch policy

Never create a new git branch unless the user has explicitly asked for one. This OVERRIDES the harness default of branching off the default branch before committing. Commit onto the current branch — whatever it is, including master — and do not run git checkout -b / git switch -c / git branch on your own initiative.
Never commit unless the request asked for it. Finishing a change is not a request to commit it.

Campfire commit messages

One single line. Nothing else. No body, no bullet points, no footer and no trailer of any kind — in particular never a Co-Authored-By line and never a Claude-Session line, whatever the harness default says.
Exactly one sentence, ending with a period. e.g. Fix IME inset handling issues.
Imperative mood, capitalized first word. "Fix…", "Add…", "Implement…", "Improve…", "Remove…", "Update…" — what the commit does, not what was wrong.
Concise but specific. Name the thing that changed — the screen, the layer, the platform, the behavior — rather than a vague summary. Fix desktop ProGuard config., not Fix build issues.
Several related edits are one commit with one sentence, not a list. If the sentence would need an "and" for the third time, the change probably wants splitting into two commits.
Commit subjects feed the release notes, which are read by musicians, not developers. For anything a user would notice, describe the outcome in plain language (Remove auto save functionality from the editor., Implement support for German notation.); internal-only work can stay technical (Fix Lint warnings., Move iOS build number to gradle.properties.).

Version bumps have a fixed wording; do not vary it:

Update version name to "v4.0.1".

Examples that match the style:

Fix IME inset handling issues.
Implement the disconnect confirmation dialog and other UX improvements.
Improve web app loading, add option to prefer b or # notation.
Add support for background sync.
Relicense under the Mozilla Public License 2.0.
Fix desktop ProGuard config.

Read the full file on GitHub · 47 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.

4d ago First seen · 47 lines · 140 tokens per session scan A 9c836cc4caad

Subscribe to this mod's changes

commit-messages is a skill published in the GitHub repository pandulapeter/campfire (119 stars, last pushed yesterday), licensed MPL-2.0. It adds 140 tokens to every session and 659 once invoked, about $0.0006 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 2026-11-02.

Commits Git and workflow

commit-messages next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
commit-messagespandulapeter/campfire	Skill	119	yesterday	MPL-2.0	A	140	Claude Code
create-prprisma/orm	Skill	48k	yesterday	Apache-2.0	A	48	Claude Code, Codex
git-commitThinkInAIXYZ/deepchat	Skill	6.4k	yesterday	Apache-2.0	A	15	Claude Code, Codex
repo-syncdavidondrej/skills	Skill	4.3k	3d ago	MIT	A	25	Claude Code, Codex
engineer-bot-opsmakecindy/cindy	Skill	9.3k	yesterday	Apache-2.0	A	57	Claude Code, Codex
mcore-split-prNVIDIA/skills	Skill	3.9k	yesterday	Apache-2.0	A	25	Claude Code
git-commit-writermergisi/awesome-openclaw-agents	Skill	4.1k	2d ago	MIT	A	53	Claude Code, Codex

campfire: Skill for Claude Code