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/kolodkin/devpowers/git-commitnpx skills add kolodkin/devpowers --skill git-commitgit clone --depth 1 https://github.com/kolodkin/devpowersWhat 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 | $0.00052 | $0.00935 |
| Opus 5 | $0.00026 | $0.00467 |
| Sonnet 5 | $0.00010 | $0.00187 |
| Haiku 4.5 | $0.00005 | $0.00093 |
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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Commit Skill
Create a git commit with the user's staged changes using the project's commit type convention, and handle pre-commit hook modifications safely.
Invocation Format
/git-commit [optional commit message]
Examples:
/git-commit
/git-commit fix login redirect loop
/git-commit add user profile endpoint
Step 1 — Inspect Staged Changes
Run these in parallel:
git diff --staged --name-only
git diff --staged
Use --name-only output as the authoritative list of originally staged files — you will need it verbatim if a pre-commit hook modifies files. Use the full staged diff to draft the commit message.
If the output of --name-only is empty, stop and tell the user nothing is staged — do NOT run git add on their behalf.
If git status reveals a mid-rebase, mid-merge, mid-cherry-pick, or detached HEAD, stop and surface that to the user before committing.
Step 2 — Determine the Commit Message
If the user supplied a message in the invocation:
- If it already has a recognized type prefix (e.g.
feature:,bugfix:), use it verbatim. - If it's a bare phrase, prepend the most appropriate type based on the staged diff (see types below).
- Preserve any multi-line body the user provided.
Otherwise, analyze the staged diff and draft a message using this project's type convention:
feature:— new featuresbugfix:— bug fixesrefactor:— code refactoringcleanup:— code cleanup
Multiple types can be combined when appropriate, e.g. [feature, cleanup]: description.
Message structure:
<type>: <short description>
<optional longer description>
Keep the subject line concise (target 50 chars, hard wrap at 72) and focus the body on the "why".
Step 3 — Get User Approval
Show the proposed message to the user and wait for approval before committing. Let them edit it. Skip this step only if the user supplied a complete message (subject + body, or an explicit "commit as-is" instruction).
Step 4 — Create the Commit
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 · 111 lines · 52 tokens per session scan A 119180447841
git-commit is a skill published in the GitHub repository kolodkin/devpowers (2 stars, last pushed 22d ago), licensed MIT. It adds 52 tokens to every session and 935 once invoked, about $0.0003 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…