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/ivy00johns/skill-madness/git-commitnpx skills add ivy00johns/Skill-Madness --skill git-commitgit clone --depth 1 https://github.com/ivy00johns/Skill-MadnessWhat 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 | $0.00111 | $0.00906 |
| Opus 5 | $0.00056 | $0.00453 |
| Sonnet 5 | $0.00022 | $0.00181 |
| Haiku 4.5 | $0.00011 | $0.00091 |
Grade A, and why
git-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 2d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Commit Conventions
Commit Message Format
type: short description in imperative mood
Optional body paragraph.
- No scope — use
feat: add X, notfeat(module): add X. - Lowercase type and description.
- Imperative mood: "add X", "fix Y", "remove Z" — not "added", "adding", "fixes".
- No period at the end.
- Max ~72 characters on the subject line.
- Optional body (blank line after subject): use for context, not mechanics.
Allowed Types
| Type | When to use |
|---|---|
feat |
New feature or behaviour |
fix |
Bug fix |
test |
Adding or fixing tests only |
docs |
Documentation only |
refactor |
Code change with no feature/fix |
chore |
Build, tooling, config, deps |
build |
Build system changes |
perf |
Performance improvement |
style |
Formatting, whitespace — no logic change |
revert |
Reverts a previous commit |
Examples
A complete commit with body:
feat: add retry policy to HTTP client
Wrap outbound calls in a retry with exponential backoff so
transient failures from downstream services don't fail the request.
A minimal commit:
fix: handle null input in prompt builder
Subject-only quick reference:
test: add unit tests for retry backoff logic
chore: update dependencies
docs: document skill frontmatter spec
refactor: extract connection string builder to helper
Branch Naming
{type}/{short-description}
- Use the commit type directly (
feat,fix,chore, etc.) — not expanded forms. - Description uses hyphens to separate words, kept to 3–5 meaningful words.
Branch Name Examples
feat/add-query-meter-api
fix/api-client-retry-policy
chore/update-skill-frontmatter
docs/add-orchestrator-guide
Merge Strategy
PRs merge with a squash merge by default unless the branch has a meaningful commit history worth preserving.
Co-Authored-By Trailer
Commits in this repo end with a Co-Authored-By: Claude ... <[email protected]> trailer and a Claude-Session: line. These are applied automatically from the agent's environment/system instructions — do not hand-type them into the message body, and do not invent or alter the email or session URL. Write your type: description subject and optional body as normal; the trailers are appended below the body, separated by a blank line, as the last lines of the message.
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.
- 2d ago First seen · 128 lines · 111 tokens per session scan A 58cd732313ae
git-commit is a skill published in the GitHub repository ivy00johns/Skill-Madness (11 stars, last pushed 22d ago), licensed MIT. It adds 111 tokens to every session and 906 once invoked, about $0.0006 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 2026-08-30.
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…