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 sundegan/agent-skills --skill git-commitgit clone --depth 1 https://github.com/sundegan/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/sundegan/agent-skills/git-commit)<a href="https://agentmods.dev/skills/sundegan/agent-skills/git-commit"><img src="https://agentmods.dev/badge/skills/sundegan/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/sundegan/agent-skills/git-commit"><img src="https://agentmods.dev/badge/skills/sundegan/agent-skills/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 | $0.00055 | $0.00977 |
| Opus 5.5 | $0.00022 | $0.00391 |
| Sonnet 5.5 | $0.00011 | $0.00195 |
| Haiku 4.5 | $0.00006 | $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 2mo 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Commit
Goal
Create a clean Git commit for the current task. Include only changes that are related to the user's request and the work Agent performed in the current context, then use a mainstream Conventional Commits message in concise, direct English. For larger changes, include a short commit body with a bullet summary of the main code changes.
Workflow
- Confirm the repository root with
git rev-parse --show-toplevel. - Inspect the current Git state:
- Run
git status --short. - Check staged changes with
git diff --cached --statandgit diff --cached. - Check unstaged changes with
git diff --statand inspect relevant diffs. - Check untracked files with
git ls-files --others --exclude-standard.
- Run
- Determine what should be committed:
- Treat the current conversation, user request, and files Codex edited for that task as the primary commit boundary.
- If the user named files, paths, or a scope, commit only those changes.
- If the user simply says "commit", "提交", or similar, commit the changes related to the current task, not every dirty file in the repository.
- Commit all dirty files only when the user explicitly asks to commit everything/all changes, and still exclude secrets, local config, dependency caches, logs, and unsupported build artifacts.
- If changes were already staged before this request, verify whether they belong to the current task before including them. Unstage unrelated staged changes if needed, without discarding their content.
- If the worktree contains unrelated or ambiguous changes, ask before staging them.
- Stage the intended files with explicit paths whenever possible. Avoid broad staging commands when unrelated changes are present.
- Re-check
git status --shortandgit diff --cached --statbefore committing. - Compose an English Conventional Commits message:
- Use
<type>(<scope>): <summary>when a clear scope exists. - Use
<type>: <summary>when no concise scope is obvious. - Keep the subject under 72 characters when practical.
- Use imperative, present-tense English.
- Do not end the subject with a period.
- Use
- Add a commit body only when the change is large, multi-part, or not obvious from the subject:
- Leave a blank line after the subject.
- Add
Summary:followed by concise bullets. - Each bullet should describe a concrete code change or user-visible behavior.
- Run
git commitwith the prepared message. - Verify the result with
git status --shortandgit log -1 --pretty=fuller --stat.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 94 lines · 55 tokens per session scan A d4165e79cc76
git-commit is a skill published in the GitHub repository sundegan/agent-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 55 tokens to every session and 977 once invoked, about $0.0002 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.
git-commit compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| git-commitsundegan/agent-skills | Skill | 2 | 3mo ago | MIT | A | 55 | Claude Code, Codex |
| 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 |