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 yegor256/courier --skill commit-changes-to-gitgit clone --depth 1 https://github.com/yegor256/courierWrote 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/yegor256/courier/commit-changes-to-git)<a href="https://agentmods.dev/skills/yegor256/courier/commit-changes-to-git"><img src="https://agentmods.dev/badge/skills/yegor256/courier/commit-changes-to-git/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/yegor256/courier/commit-changes-to-git"><img src="https://agentmods.dev/badge/skills/yegor256/courier/commit-changes-to-git.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 | $0.00028 | $0.00307 |
| Opus 5.5 | $0.00011 | $0.00123 |
| Sonnet 5.5 | $0.00006 | $0.00061 |
| Haiku 4.5 | $0.00003 | $0.00031 |
Grade A, and why
commit-changes-to-git 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.
What it actually says
Scope
Operate on Git repository in current working directory. Refuse to bundle unrelated changes into one commit.
Boundaries
Commit files untouched, never reformatting, linting, testing, or building. Honor hooks and signing unless user asked to bypass them. Land one local commit, never amending, rebasing, force-pushing, or pushing.
Staging
Stage only paths user named, or everything when user said so. Refuse to stage secrets. Warn user about skipped secrets instead.
Message
Respect Conventional Commits standard.
Prepend ticket number to description with # when user named issue.
Derive message from diff and conversation, never from branch name.
Format
Shape commit as type: summary subject, then optional body.
Review
List staged files for user before committing. Show commit subject to user before committing.
Authorship
Limit message to its description.
Skip Co-authored-by: trailers, promotional lines, signatures, and emoji.
Preserve configured author and committer identity.
Example
User fixes typo in README.md and says "commit it".
Stage README.md alone.
Write subject docs: fix typo in README.
Land one commit carrying that subject.
Done
Confirm one new commit appears after run. Stop after single commit lands.
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 · 57 lines · 28 tokens per session scan A 2abfd23b4b12
commit-changes-to-git is a skill published in the GitHub repository yegor256/courier (3 stars, last pushed 2d ago), licensed MIT. It adds 28 tokens to every session and 307 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
github-pr-best-practices
Best practices for creating GitHub pull requests including conventional commits, PR formatting, and multi-language support (en/ja). Use when creating PRs, writing PR descriptions, or formatting commit messages.
implementer
Implements one issue inside its own git worktree (.worktrees/issue-N on agent/issue-N), makes the smallest change that satisfies the acceptance criteria, self-checks with the repo's own test/lint/typecheck commands, commits, and prints a JSON report for the orchestrator. Use when the orchestrator launches you with…
git-workflow
Enhanced git operations using lazygit, gh (GitHub CLI), and delta. Triggers on: stage changes, create PR, review PR, check issues, git diff, commit interactively, GitHub operations, rebase, stash, bisect.
git-commit
Use this skill when user asks to "commit changes", "create a commit", "stage and commit", or wants help with git commit workflow.
commit
Helps write conventional commit messages, create atomic commits, and follow git best practices. Use when the agent needs to help with git commits, commit message writing, or git workflow guidance.
implementing-code
Implements code changes and creates commits. Triggered when: implementation tasks, code changes, feature additions, bug fixes.