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.
npx skills add dmythro/agent-skills --skill git-commitgit clone --depth 1 https://github.com/dmythro/agent-skillsWrote 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.
[](https://agentmods.dev/skills/dmythro/agent-skills/git-commit)<a href="https://agentmods.dev/skills/dmythro/agent-skills/git-commit"><img src="https://agentmods.dev/badge/skills/dmythro/agent-skills/git-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.
<a href="https://agentmods.dev/skills/dmythro/agent-skills/git-commit"><img src="https://agentmods.dev/badge/skills/dmythro/agent-skills/git-commit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00073 | $0.01248 |
| Opus 5.5 | $0.00029 | $0.00499 |
| Sonnet 5.5 | $0.00015 | $0.00250 |
| Haiku 4.5 | $0.00007 | $0.00125 |
Grade A, and why
git-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.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conventional Commits
Default commit format: Conventional Commits. Use this format for all commits and PR/MR titles unless the project defines its own commit conventions (in CLAUDE.md, AGENTS.md, contributing guides, or similar). Project-specific rules always take priority.
When to Use
- Making any git commit -- this skill defines the required format
- Creating PR/MR titles -- squash merges use the title as the commit message
- Writing squash merge messages -- must follow the same format
- Reviewing commit message format -- validate against these rules
Critical Rules
- Project rules override this skill -- if the project defines commit message conventions (issue number prefixes, custom formats, etc.), follow those instead. This skill is the default when no project-specific rules exist.
- Type is required -- never commit without a type prefix
- Description is lowercase, imperative mood, no period:
fix: handle null responsenotFix: Handled null response. - No
Co-Authored-Bytrailer -- never add it to commit messages - Describe the change, not the process -- never write review provenance (
fix: coderabbit round 2 fixes,fix: address review feedback) as the message; state what the commit changes. The trigger for the change already lives in the PR and its threads. - No filler -- the description alone is usually the whole message; add a body only for information the description and diff cannot carry (breaking change details, migration steps, non-obvious constraints). Never narrate the diff.
Provider Detection
Detect the git provider to use the correct CLI:
git remote get-url origin
| Remote URL contains | Provider | CLI | PR term |
|---|---|---|---|
github.com |
GitHub | gh |
PR |
gitlab.com or self-hosted GitLab |
GitLab | glab |
MR |
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 · 114 lines · 73 tokens per session scan A 580d1ec0bf04
git-commit is a skill published in the GitHub repository dmythro/agent-skills (7 stars, last pushed 7d ago), licensed MIT. It adds 73 tokens to every session and 1,248 once invoked, about $0.0003 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.
Other skills, from other repositories
commit-message-expert
Generates consistent, meaningful Git commit messages based on a diff or description of changes. Use when writing or reviewing a commit message, especially to follow Conventional Commits or a project's existing convention.
secrets-scanner
Narrowly scans code and config for hardcoded secrets, credentials, API keys, and tokens. Use before a commit/PR, or when auditing a codebase for accidentally-committed secrets.
git-hook-automation-designer
Configures pre-commit and pre-push hooks (Husky, Lefthook) for fast lint-staged, branch naming, and secret blocking.
changelog-generator
Converts commits or development updates into clean, categorized release notes and changelogs. Use when preparing a release and raw commit history needs to become human-readable notes.
git-conflict-resolver
Resolves complex git rebase and merge conflicts with AST-level context, preserving intent across concurrent branches.
contributor-guide-writer
Creates clear, welcoming CONTRIBUTING.md files, PR templates, and local dev onboarding guides for open source projects.