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/sleeyax/promptfiles/git-commitnpx skills add sleeyax/promptfiles --skill git-commitgit clone --depth 1 https://github.com/sleeyax/promptfilesWhat 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 | $0.00046 | $0.01045 |
| Opus 5 | $0.00023 | $0.00522 |
| Sonnet 5 | $0.00009 | $0.00209 |
| Haiku 4.5 | $0.00005 | $0.00104 |
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 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Commit
Write a commit message for the current changes and commit it. The message MUST match the style already used in this repo — do NOT default to any particular format.
Hard rules
- Commit without asking. Pick the single best message and create the commit — no options, no confirmation gate. The user amends or resets afterwards if the message is wrong, which is cheaper than a round trip on every commit.
- Only commit what the change is about. Never
git add -Ablindly. Stage the files that belong to the change, and leave anything unrelated, generated, or secret-looking alone — say what you skipped. - Keep the context small. This skill almost always runs at the end of a long session, where every extra round trip and every line of diff is re-sent along with the whole conversation. Gather in one call, bound the diff, and never re-run a command whose output you already have.
Steps
1. Gather the evidence — one call
Run all of it as a single command, not one tool call per fact:
git log --oneline -20
git status --short
git diff --cached --stat
ls -d commitlint.config.* .commitlintrc* 2>/dev/null
grep -l '"commitlint"' package.json 2>/dev/null
If the staged stat is empty, nothing is staged — the scope is the unstaged changes instead (git diff --stat), and every later --cached command below drops the flag to match.
From the log output, identify the repo's style:
- Whether messages use a prefix/type convention or are freeform
- Capitalization (sentence case vs lowercase)
- Tense and mood (imperative vs past tense)
- Use of scopes, tags, or ticket references
- Typical length and level of detail
If a commitlint config turned up, read it — its rules take precedence over what the log suggests.
2. Read the diff, bounded
The diff is the single largest thing this skill puts in context, and it stays there for every later call. Never pull in more of it than the message needs.
git diff --cached -- . ':(exclude)*.lock' ':(exclude)*-lock.json' ':(exclude)*.sum'
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 · 82 lines · 46 tokens per session scan A 8e9bbb162d00
git-commit is a skill published in the GitHub repository sleeyax/promptfiles (2 stars, last pushed 3d ago), licensed MIT. It adds 46 tokens to every session and 1,045 once invoked, about $0.0002 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…