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 skills add alphacornutum/layercake --skill commitgit clone --depth 1 https://github.com/alphacornutum/layercakeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/alphacornutum/layercake/commit)<a href="https://agentmods.dev/skills/alphacornutum/layercake/commit"><img src="https://agentmods.dev/badge/skills/alphacornutum/layercake/commit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/alphacornutum/layercake/commit"><img src="https://agentmods.dev/badge/skills/alphacornutum/layercake/commit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00100 | $0.00560 |
| Opus 5.5 | $0.00040 | $0.00224 |
| Sonnet 5.5 | $0.00020 | $0.00112 |
| Haiku 4.5 | $0.00010 | $0.00056 |
Grade A, and why
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 20d 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.
What it actually says
Commit
Write a commit message that follows the project's conventions and clearly explains what changed and why.
Steps
- Run
git diff --cached(orgit diffif nothing is staged) to see all changes. - Run
git log --oneline -10to detect the project's existing commit style — copy it. Match what's there rather than imposing a different convention. - Analyze the changes: feature, fix, refactor, docs, or chore? What is the motivation?
- Write the commit:
- First line: imperative mood, ≤72 chars, matching the style from step 2.
- Body (only if the subject can't carry the meaning): blank line, then why, not what.
- Stage relevant files explicitly by path.
git add .sweeps in generated files, secrets, and unrelated changes. - Create the commit.
Default style
If the project has no established convention (step 2 returns mixed messages), default to Conventional Commits: <type>: <subject> where <type> is feat, fix, refactor, docs, test, or chore. Use feat: for new behavior, fix: for bug fixes, refactor: for behavior-preserving changes; the others are self-explanatory.
Gotchas
- Create a new commit rather than amending the previous one — reach for
--amendonly on explicit user request. - Keep one logical change per commit. Split unrelated work into separate commits.
- Leave
.env, credentials, and generated lockfiles out of the index unless the project clearly tracks them. - When a pre-commit hook fails, fix the cause and create a new commit. Reach for
--no-verifyonly when the user explicitly authorizes it. - Never add attribution or tooling trailers (
Co-Authored-By:,Generated with …, agent/model signatures) to the subject or body — the commit records the human author only. - Match the project's existing style (gitmoji, ticket-prefixed, plain-English) rather than inventing a new one.
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.
- 20d ago First seen · 33 lines · 100 tokens per session scan A f1c69585d1a7
commit is a skill published in the GitHub repository alphacornutum/layercake (0 stars, last pushed 2d ago), licensed MIT. It adds 100 tokens to every session and 560 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-26.
Other skills, from other repositories
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.
git-commit
Generate well-formatted git commit messages following conventional commit standards.
repo-sync
Manage automatic Git syncing on macOS with repo-sync. Use only when the user explicitly invokes /repo-sync.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
git-commit-writer
Trigger when the user asks to write a commit message, generate a commit from staged changes, review a diff before committing, or says "/commit". Reads git diff --staged and produces an opinionated, convention-matching commit message.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.