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 marmot-protocol/agent-config --skill commit-codegit clone --depth 1 https://github.com/marmot-protocol/agent-configWrote 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/marmot-protocol/agent-config/commit-code)<a href="https://agentmods.dev/skills/marmot-protocol/agent-config/commit-code"><img src="https://agentmods.dev/badge/skills/marmot-protocol/agent-config/commit-code/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/marmot-protocol/agent-config/commit-code"><img src="https://agentmods.dev/badge/skills/marmot-protocol/agent-config/commit-code.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 | $0.00027 | $0.00911 |
| Opus 5.5 | $0.00011 | $0.00364 |
| Sonnet 5.5 | $0.00005 | $0.00182 |
| Haiku 4.5 | $0.00003 | $0.00091 |
Grade A, and why
commit-code 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.
How it starts
The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit Code Skill
You are creating git commits using Ren's commit tools. This skill covers the full workflow from staged changes to verified commit.
Activation
This skill activates when:
- User asks to commit changes
- User says "commit this" or "create a commit"
- Context involves staged git changes ready to commit
- User wants to finalize their work with a commit
Tools
| Tool | Purpose |
|---|---|
commit_message |
Analyze staged changes, suggest type/scope/subject |
commit |
Create the actual git commit with safety checks |
diff-analyze |
Get detailed breakdown of changes (optional) |
Workflow
Step 1: Check Staged Changes
Before anything else, verify there are staged changes:
git diff --cached --stat
If nothing is staged:
- Inform the user
- Suggest files they might want to stage
- Stop the workflow
Step 2: Analyze Changes
Use the commit_message tool to analyze staged changes:
commit_message({ includeBody: true })
This returns:
type- Inferred commit type (feat, fix, docs, etc.)scope- Common directory scope (or null)subject- Suggested subject linebody- Change statisticsfiles- List of staged filesbreaking- Whether breaking changes detected
Step 3: Draft Commit Message
Based on the analysis, draft a conventional commit message:
<type>(<scope>): <subject>
<body explaining what and why>
<footer with issue references>
Always present the message to the user before committing.
Step 4: Create the Commit
Use the commit tool with the full message:
commit({ message: "feat(auth): add password reset\n\nImplement reset flow with email verification.\n\nCloses #42" })
The tool returns:
success- Whether commit was createdhash- Short commit hash (on success)summary- Commit summary line (on success)error- Error message (on failure)hint- Suggestion for fixing the error
Step 5: Report Result
On success:
✓ Commit created: a1b2c3d feat(auth): add password reset
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 · 147 lines · 27 tokens per session scan A 9331a31904ff
commit-code is a skill published in the GitHub repository marmot-protocol/agent-config (2 stars, last pushed 8mo ago), licensed MIT. It adds 27 tokens to every session and 911 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
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.
git-commit
Generate well-formatted git commit messages following conventional commit standards.
repo-sync
Manage automatic Git syncing on macOS with repo-sync. Use only when the user explicitly invokes /repo-sync.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
contributing
How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the…
engineer-bot-ops
A workflow for carrying an engineering task from scope through implementation and reviewable delivery. It works with a repository's branch, existing changes, rules, checks, and permissions while separating completed, unverified, and next-step work.