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/verifygit clone --depth 1 https://github.com/alphacornutum/layercakeWhat 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 | $0.00028 | $0.00266 |
| Opus 5 | $0.00014 | $0.00133 |
| Sonnet 5 | $0.00006 | $0.00053 |
| Haiku 4.5 | $0.00003 | $0.00027 |
Grade A, and why
verify 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 2d 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
Run the LayerCake full verification suite and fix failures you introduce.
Full QA always includes AgentSync. If you edited .ai/src/, run agentsync sync before agentsync check.
In Cursor, run the QA Shell with required_permissions: ["all"]. agentsync check fails in the sandbox every time (Failed to prepare temporary workspace for check / .cursor/: Operation not permitted) — that is not drift; skip the sandboxed attempt.
- Run:
agentsync check
npm audit --audit-level=high
npm run typecheck
npm run lint
npm run fmt:check
npm test
npm run build
- If
$ARGUMENTScontainsae(or the user asked for host tests), also run:
npm run test:ae
Host tests skip when AE env is unset — report skips clearly rather than treating them as failures.
- Summarize: commands run, pass/fail/skip, and any fixes applied. Keep changes scoped to making verification green.
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.
- 2d ago First seen · 34 lines · 28 tokens per session scan A 7ae7f379ef1b
verify is a command published in the GitHub repository alphacornutum/layercake (0 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 266 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
tests
Run the Week 4 backend test workflow. Build TESTARGS from $ARGUMENTS: use backend/tests when it is empty; prepend backend/tests when it starts with an option such as -k; otherwise use the supplied path or node ID as-is.
verify
Grade work that already exists and decide whether it can merge. Runs the project's current unit, integration, and E2E suites plus security scanning and type checking, scores every dimension 0-10, and returns a merge verdict with a VERIFIED-vs-CLAIMED evidence manifest. Writes no test files and edits no source. Use…
go-test
Go TDD workflow with table-driven tests.
kill-mutants
Analyze surviving mutants from a mutation testing run and write targeted unit tests to kill them. Re-runs mutations to confirm kills.
test-ts
Run TypeScript tests for Solana frontends and Anchor programs.
increase-coverage
分析当前分支改动并补充单测覆盖率.