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.
git clone --depth 1 https://github.com/richkuo/rk-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/commands/richkuo/rk-skills/commit)<a href="https://agentmods.dev/commands/richkuo/rk-skills/commit"><img src="https://agentmods.dev/badge/commands/richkuo/rk-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/commands/richkuo/rk-skills/commit"><img src="https://agentmods.dev/badge/commands/richkuo/rk-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 | $0.00009 | $0.00356 |
| Opus 5.5 | $0.00004 | $0.00142 |
| Sonnet 5.5 | $0.00002 | $0.00071 |
| Haiku 4.5 | $0.00001 | $0.00036 |
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 18d 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
Create a git commit using the Haiku model following these steps:
- Read the current branch (
git rev-parse --abbrev-ref HEAD) and the default branch (gh repo view --json defaultBranchRef -q .defaultBranchRef.name, elsegit symbolic-ref --short refs/remotes/origin/HEADwithout itsorigin/part). When they match, stop and tell the user that changes land through a worktree and pull request (CLAUDE.md Git Workflow); do not commit - Run git status and git diff to see all changes
- Run git log to understand the commit message style
- Analyze all staged and unstaged changes
- Draft a concise commit message focusing on the "why" rather than the "what"
- Add relevant untracked files to staging if needed
- Create the commit with the message using a HEREDOC for proper formatting
- Run git status after to verify success
Important:
- End the message with the CLAUDE.md LLM Attribution Footer as its last lines (
---, thenCreated with LLM: <current model> | <effort> | Harness: Claude Code); add noCo-Authored-Bytrailer. A repo CLAUDE.md footer format overrides this - Do not commit files that likely contain secrets (.env, credentials.json, etc)
- If pre-commit hooks modify files, verify it's safe to amend
- Do not push unless explicitly asked
- Use the format:
git commit -m "$(cat <<'EOF'\nCommit message here.\nEOF\n)"
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.
- 18d ago Changed · +2 lines 9e5692f66e8c
- 1mo ago First seen · 22 lines · 9 tokens per session scan A 256b2ed0e42f
commit is a command published in the GitHub repository richkuo/rk-skills (50 stars, last pushed 3d ago), licensed MIT. It adds 9 tokens to every session and 356 once invoked, about $0.0000 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 2026-08-30.
Other commands, from other repositories
build
Implement tasks incrementally — build, test, verify, commit. Add "auto" to run the whole plan in one approved pass.
commit
Based on the above changes, create a single git commit.
vios-git
VIOS git conventions: branch names, commit messages, and merge-request descriptions. Use before creating any branch, commit, or MR.
commit
Run when user calls /commit or asks to generate a commit message. Analyzes staged changes and writes a structured commit message.
devkit.github.create-pr
Creates a GitHub pull request with branch creation, commits, and detailed description. Use when you need to submit changes for review.
amend
Amend the most recent commit with additional changes or an updated message.