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/masonegger/bpe-claude-code-plugin/commit-messagenpx skills add MasonEgger/bpe-claude-code-plugin --skill commit-messagegit clone --depth 1 https://github.com/MasonEgger/bpe-claude-code-pluginWhat 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 | $0.00018 | $0.00738 |
| Opus 5 | $0.00009 | $0.00369 |
| Sonnet 5 | $0.00004 | $0.00148 |
| Haiku 4.5 | $0.00002 | $0.00074 |
Grade A, and why
commit-message 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit Message Command
Inspect the staged changes, write a commit message that captures the why of the change, and save it to commit-msg.md at the repo root for the user to feed into git commit -F commit-msg.md.
Step 1: Inspect the Changes
Run these in parallel:
git status: see all untracked files and modifications.git diff --staged: the exact set of changes that will be committed.git diff: what is modified but NOT yet staged. Do not narrate work that is in this diff but not the staged one.git log --oneline -10andgit log -3 --pretty=full: match the repository's commit-message style and signing/conventions.
Step 2: Identify the Why
Analyze the staged diff. Answer:
- What problem does this commit solve, or what capability does it add?
- Why is this approach the right one, only if non-obvious from the code.
- Was anything explicitly NOT changed that a reader might expect (deferred, out of scope, separate commit)?
If the user passed an argument, treat it as a focusing hint; bias the message toward the threads they named, not the full diff.
Step 3: Compose the Message
Format:
- Subject line: imperative mood, ~50 characters target, ~72 characters hard cap. No trailing period.
- Blank line.
- Body: one or more paragraphs, wrapped at ~72 characters. Lead with the why (the problem solved or the capability added), then the what only when not obvious from the diff. Use bulleted lists where they actually help; flowing prose otherwise.
Avoid:
- Restating WHAT the diff already says when the WHY is obvious.
- Listing every file changed.
- Marketing language ("dramatically improves", "robust", "comprehensive", "powerful").
- Self-references like "this commit" or "this PR"; the message is the commit.
- Co-authored-by or AI-attribution trailers unless the user explicitly asks.
- Bumping versions, regenerating lockfiles, or any side action; this command only writes the message.
Match the repository's existing style observed in git log (subject-line case, conventional-commits prefix or not, trailers).
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 · 80 lines · 18 tokens per session scan A 09ddc93d841f
commit-message is a skill published in the GitHub repository MasonEgger/bpe-claude-code-plugin (7 stars, last pushed 9d ago), licensed MIT. It adds 18 tokens to every session and 738 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…