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 LuisUrrutia/skills --skill commitgit clone --depth 1 https://github.com/LuisUrrutia/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/luisurrutia/skills/commit)<a href="https://agentmods.dev/skills/luisurrutia/skills/commit"><img src="https://agentmods.dev/badge/skills/luisurrutia/skills/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/luisurrutia/skills/commit"><img src="https://agentmods.dev/badge/skills/luisurrutia/skills/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 | $0.01946 |
| Opus 5.5 | $0.00007 | $0.00778 |
| Sonnet 5.5 | $0.00004 | $0.00389 |
| Haiku 4.5 | $0.00002 | $0.00195 |
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 15d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit
Create verified Conventional Commits, one atomic boundary at a time, using the existing checkout and branch. Ground state and completion claims in fresh Git evidence, including claims from earlier assistant messages.
Modes
Resolve authority from the active request, standing user instructions and authorized caller. A commit request alone authorizes neither pushing nor PR work.
| Mode | Action |
|---|---|
| Commit | Commit after applicable checks pass |
| Commit-and-push | Verify all intended commits, then publish within existing authority |
| Proposal | Stage the boundary and propose its message without committing |
| Amend | Apply the current-task conditions before amending |
| Split | Repeat the complete workflow for every clear atomic intent |
Preparing, reviewing or suggesting a commit selects Proposal mode. For material ambiguity in boundaries, order, grouping or authority, ask one concise question with concrete options and a recommended default.
Each boundary ends committed, amended, proposed, blocked or refused.
Stop changing that boundary; after a verified commit or amendment, continue the
next clear boundary from a fresh baseline. pushed ends a published run.
Resolve boundaries before writing
Inspect these conditions before staging; use existing authority and repository evidence, asking only when they leave a material decision unresolved:
- Secret-looking paths/content:
.env*, keys, certificates, tokens, credentials, databases and obvious secret names. - Independent or out-of-scope concerns, including changes that cannot be described in one or two sentences.
- Ambiguous staged and unstaged edits in the same file.
mainormaster, unless the user explicitly wants to commit there.- Unrequested publication, destructive Git actions, out-of-scope dependency or package-manager changes, or an amendment outside the linked conditions.
Inspect generated files, dependencies, lockfiles and binaries; their presence or size alone requires no approval. Treat existing staged entries as likely intent, including them only when coherent with the request. Branch-history rewrites belong to their authorized workflow.
What ships with it
4 files 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.
- 15d ago Changed · +16 lines b01b5a11da92
- 17d ago Changed · -2 lines cada75a31fcc
- 1mo ago Changed · +5 lines fb02823ecd1b
- 2mo ago First seen · 177 lines · 18 tokens per session scan A 2166778b4933
commit is a skill published in the GitHub repository LuisUrrutia/skills (2 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 1,946 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
git-workflow-and-versioning
Use when managing branches, commits, versioning, and release workflows for Android projects, or when cutting a release, choosing a version bump, tagging, or writing a changelog. Covers trunk-based development, atomic commits, versionCode/versionName derived from tags, semver for library modules, changelogs and Play…
wrap-phase
Wraps up a development phase by cleaning AGENTSYNC.md, summarizing work, and committing changes.
git-workflow-and-versioning
Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, splitting uncommitted work in a messy working tree into clean atomic commits, opening or reviewing a pull request (PR), pushing to a remote, or when you need to organize work across multiple…
agentic-jujutsu
Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination.
github-automation
GitHub workflow automation, PR management, issue tracking, and code review coordination. Integrates with GitHub Actions and repository management. Use when: PR creation, code review, issue management, release automation, workflow setup. Skip when: local-only changes, non-GitHub repositories.
chinese-commit-conventions
A Chinese-language guide to Conventional Commits, a format for writing consistent Git commit messages, plus related changelog, commit-checking, and commit-helper configuration.