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 mir-am/skills-agents-ai-coding --skill git-commitgit clone --depth 1 https://github.com/mir-am/skills-agents-ai-codingWrote 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/mir-am/skills-agents-ai-coding/git-commit)<a href="https://agentmods.dev/skills/mir-am/skills-agents-ai-coding/git-commit"><img src="https://agentmods.dev/badge/skills/mir-am/skills-agents-ai-coding/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/mir-am/skills-agents-ai-coding/git-commit"><img src="https://agentmods.dev/badge/skills/mir-am/skills-agents-ai-coding/git-commit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00018 | $0.00982 |
| Opus 5.5 | $0.00007 | $0.00393 |
| Sonnet 5.5 | $0.00004 | $0.00196 |
| Haiku 4.5 | $0.00002 | $0.00098 |
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 22d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What I do
- Prevent commits to main/master by auto-creating feature branches
- Stage only files created/modified in current agent session
- Generate messages following Conventional Commits 1.0.0
- Auto-detect when to add
[skip ci]based on project rules
When to use me
Use this skill when the user asks to commit changes made during the current session.
Branch Protection Workflow
- Check current branch:
git branch --show-current - If on
mainormaster:- Analyze
git diffand agent conversation context - Generate descriptive branch name (format:
<type>/<brief-description>) - Examples:
feat/add-csv-export,fix/npe-in-builder,docs/update-readme - If context is unclear, ask user for branch name
- Create and switch:
git checkout -b <branch-name>
- Analyze
Staging Workflow
- Stage only files that the agent created or modified in this session
- Use specific file paths:
git add <file1> <file2> <file3> - Show what will be committed:
git diff --cached --stat
Commit Message Format
Follow Conventional Commits 1.0.0:
<type>[optional scope][!]: <description>
[optional body]
[optional footer(s)]
- Use
featfor a new feature andfixfor a bug fix. Other common types arebuild,chore,ci,docs,style,refactor,perf,test, andrevert; the specification does not restrict commits to this list. - Include a scope in parentheses when it clarifies the affected area, such as
fix(parser): handle empty input. Omit the scope when it adds no useful context. - Require a colon and space before the short description. Prefer lowercase types, a concise imperative description (e.g., "add", "fix"), and no trailing period. These style preferences and any project-specific length limits are separate from the specification, which imposes no 50-character limit.
- Add a body when useful to explain the change and its rationale, separated from the subject by a blank line. Separate footers from the body (or subject when there is no body) with a blank line; use trailer syntax such as
Refs: #123. - Mark breaking changes with
!immediately before the colon, an uppercaseBREAKING CHANGE: <explanation>footer, or both. Breaking changes can occur with any type. When using only!, describe the breaking change in the subject; use a footer for additional impact or migration guidance.
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.
- 22d ago Changed · +38 lines 3184ab1ab972
- 1mo ago First seen · 67 lines · 18 tokens per session scan A 5a5de3c5e610
git-commit is a skill published in the GitHub repository mir-am/skills-agents-ai-coding (2 stars, last pushed 23d ago), licensed MIT. It adds 18 tokens to every session and 982 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 2026-08-31.
Other skills, from other repositories
ci-autofix
Autonomous CI/CD remediation — parse GitHub/GitLab failure logs, find the root cause (lint/type/test), generate and commit a fix.
git-workflow
Conventional commits, PR creation, and quality gate verification.
clean-commits
Use when committing code - ensures atomic, descriptive commits that leave the codebase in a merge-ready state at every point.
review-gate
HARD GATE before PR creation - verifies review artifact exists in issue comments, all findings addressed or tracked, blocks PR creation if requirements not met.
github
GitHub CLI for issues, PRs, CI/check logs, comments, reviews, releases, repos, and gh api queries.
commit-context
Trace a file, function, or line back to the agent session that produced its current commit. Use when the user asks "why is this code here", "what was the agent doing when this changed", "who wrote this", or wants context on a specific location in the codebase.