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 commands/alphacornutum/layercake/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/commands/alphacornutum/layercake/review)<a href="https://agentmods.dev/commands/alphacornutum/layercake/review"><img src="https://agentmods.dev/badge/commands/alphacornutum/layercake/review.svg" alt="Measured on agentmods" 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 | $0.00012 | $0.00287 |
| Opus 5 | $0.00006 | $0.00143 |
| Sonnet 5 | $0.00002 | $0.00057 |
| Haiku 4.5 | $0.00001 | $0.00029 |
Grade A, and why
review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Review the current changes in this repo$ARGUMENTS.
Embedded context:
git status: !git status -sbgit diff: !git diffgit diff --staged: !git diff --staged- recent commits: !
git log --oneline -8
Focus on:
- MCP contract — tool names, Zod schemas, JSON field renames/removals in inventory or
server.ts. - Host protocol —
script-wrapperOK/ERR format, AppleScript escaping, timeout behavior. - Id namespaces — Layer.id vs Item.id; join keys documented in tool descriptions.
- ExtendScript — ES3 constraints; reliance on injected JSON polyfill; modal/dialog risk.
- Tests — unit coverage for parse/filter/wrapper; AE tests still correctly
skipIf-gated. - Docs —
README.md/ linkeddocs/*(especiallymcp-tools,setup,troubleshooting) /.env.example/ OpenSpec specs updated when behavior changed.
Output: findings first (severity-ordered), then open questions. Prefer concrete file references. Do not rewrite unrelated code.
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.
- 4d ago First seen · 26 lines · 12 tokens per session scan A 64d8727e54e3
review is a command published in the GitHub repository alphacornutum/layercake (0 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 287 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 commands, from other repositories
report-ae-issue
Send a problem you hit with the After Effects tools to the people who maintain them.
init-after-effects
Set up After Effects from scratch — install the panel, create a project folder, and capture a house style.
create-style-guide
Capture or update the look of this project — palette, type, motion and layout — into the style guide that shapes everything built afterwards.
start
Set up Editor Pro Max for first use. Run these steps automatically without asking.
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.