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 reviewgit 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/review)<a href="https://agentmods.dev/skills/alphacornutum/layercake/review"><img src="https://agentmods.dev/badge/skills/alphacornutum/layercake/review/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/review"><img src="https://agentmods.dev/badge/skills/alphacornutum/layercake/review.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 | $0.00094 | $0.00500 |
| Opus 5.5 | $0.00038 | $0.00200 |
| Sonnet 5.5 | $0.00019 | $0.00100 |
| Haiku 4.5 | $0.00009 | $0.00050 |
Grade A, and why
review 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
Code Review
Systematically review changes for correctness, security, and maintainability.
Steps
- Read the full diff. Understand the scope before commenting.
- Check PR description or commit messages for context — what problem is being solved?
- Review in priority order:
- Correctness — Logic errors, off-by-one bugs, missing edge cases, race conditions.
- Security — Injection risks, hardcoded secrets, missing validation, exposed PII.
- Error handling — Unhandled failures, swallowed exceptions, missing error paths.
- Architecture — Does this follow existing patterns? Are boundaries respected?
- Testing — Are new behaviors tested? Are error paths covered?
- Naming & clarity — Would a new team member understand this?
- For each issue:
- Point to the exact file and line.
- Explain why it's a problem, not just what to change.
- Suggest a fix when possible.
- Mark as blocking (must fix) or suggestion (nice to have).
- When the code is solid, say so plainly. Manufactured criticism erodes review trust.
Output Format
## Summary
[1-2 sentence overview]
## Issues
- **[blocking]** file.ts:42 — [problem and suggested fix]
- **[suggestion]** file.ts:15 — [observation and reasoning]
## Verdict
[Approve / Request changes / Needs discussion]
Gotchas
- Skip style nitpicks that a formatter or linter would catch — those are noise.
- Review what's there, not what you would have written. The author's approach stands unless it has a concrete flaw.
- Resolve every blocking issue before approving — politeness is not a reason to ship a known bug.
- Check the full PR, not just the latest commit — bugs often hide in earlier commits.
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 · 48 lines · 94 tokens per session scan A 2cf2f5f10b29
review is a skill published in the GitHub repository alphacornutum/layercake (0 stars, last pushed 3d ago), licensed MIT. It adds 94 tokens to every session and 500 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
after-effects-scripting
Drive a running After Effects instance directly from the shell to build, edit and render motion graphics — no MCP, plugin or panel required. Use whenever the user wants Claude to work inside After Effects: building animations, title sequences, logo stings, UI/product motion, data visualisations, or fixing an existing…
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…