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 agentmods add skills/marmot-protocol/agent-config/write-commitnpx skills add marmot-protocol/agent-config --skill write-commitgit clone --depth 1 https://github.com/marmot-protocol/agent-configWhat 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 | $0.00029 | $0.00760 |
| Opus 5 | $0.00015 | $0.00380 |
| Sonnet 5 | $0.00006 | $0.00152 |
| Haiku 4.5 | $0.00003 | $0.00076 |
Grade A, and why
write-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 yesterday.
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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write Commit Skill
You are an expert at crafting clear, informative commit messages following conventional commit standards.
Activation
This skill activates when:
- User asks for help with a commit message
- User wants to commit changes
- Context involves staged git changes
- User mentions "conventional commit"
Conventional Commit Format
<type>(<scope>): <subject>
[optional body]
[optional footer]
Commit Types
| Type | Use When |
|---|---|
feat |
Adding new functionality |
fix |
Fixing a bug |
docs |
Documentation only changes |
style |
Formatting, missing semicolons (no code change) |
refactor |
Code change that neither fixes nor adds |
test |
Adding or correcting tests |
chore |
Maintenance, build process, dependencies |
perf |
Performance improvement |
ci |
CI configuration changes |
revert |
Reverting a previous commit |
Writing Guidelines
Subject Line (First Line)
- 50 characters or less (hard limit: 72)
- Imperative mood: "add feature" not "added feature"
- No period at the end
- Lowercase after the colon
- Specific: "add user logout button" not "update UI"
Scope (Optional)
- Module or component affected
- Keep it short:
auth,api,ui,db - Use consistently across project
Body (Optional but Recommended)
- Wrap at 72 characters
- Explain what and why, not how
- Separate from subject with blank line
- Use bullet points for multiple items
Footer (Optional)
- Breaking changes:
BREAKING CHANGE: description - Issue references:
Fixes #123,Closes #456 - Co-authors:
Co-authored-by: Name <email>
Tools to Use
commit_message- Analyze staged changes and suggest messagecommit- Create the actual git commitdiff-analyze- Detailed change breakdown
Examples
Simple Feature
feat(auth): add password strength indicator
Display real-time password strength feedback during registration.
Uses zxcvbn library for accurate strength estimation.
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.
- yesterday First seen · 124 lines · 29 tokens per session scan A 9f6b381bd40a
write-commit is a skill published in the GitHub repository marmot-protocol/agent-config (2 stars, last pushed 7mo ago), licensed MIT. It adds 29 tokens to every session and 760 once invoked, about $0.0001 per session on Opus 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…