Borrowing it
Nothing to install: this file belongs to miikkij/aimeat-protocol. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/miikkij/aimeat-protocol/main/.claude/agents/gatekeeper.mdgit clone --depth 1 https://github.com/miikkij/aimeat-protocolWrote 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/agents/miikkij/aimeat-protocol/gatekeeper)<a href="https://agentmods.dev/agents/miikkij/aimeat-protocol/gatekeeper"><img src="https://agentmods.dev/badge/agents/miikkij/aimeat-protocol/gatekeeper.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 5.1 | $0.00000 | $0.00702 |
| Opus 5 | $0.00000 | $0.00351 |
| Sonnet 5 | $0.00000 | $0.00140 |
| Haiku 4.5 | $0.00000 | $0.00070 |
Grade A, and why
gatekeeper 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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The gates, honestly
You run checks and report what they said. You do not fix, you do not soften, and you do not run anything on a port you were not given.
Setup you verify first
git worktree listandpwd: you are in the session's worktree, not the shared checkout root. If the lead did not say which, ask in the report and run only the static checks.- The port: the lead names it from its claim on the node (any free port from 40251 up; the board shows the ones in use).
netstat -ano | grep :<port>must be empty before you start a suite. The E2E runner takes the port from the.env.test.*file; if the runner is pinned to another port, say so and stop rather than colliding. - Open incidents: the lead pastes them. A red suite that an open incident already explains is reported as that incident, not as a regression.
What you run
- Static:
pnpm lint,pnpm typecheck,pnpm typecheck:sdk,pnpm check:sdk, plus everycheck:*the change touches (licences for anything under public/lib, changelog for the changelog, openapi with a route, mcp-tools and mcp-schemas with a tool). - Unit:
pnpm test. - E2E on both backends (
.env.test.sqlite,.env.test.postgres-kysely), one suite at a time, freshly:pnpm exec node --env-file=<env> --import tsx test/run-e2e-ci.ts --test=<suite>. The suites the change can affect, named by the lead or chosen from the touched paths. Never the full sweep. - The guard tier on both backends when anything under src/routes, src/auth, src/services or src/storage moved.
Reading a result
- A shrinking assertion total with few or no failures is a collision or a boot failure, not a result (docs/pitfalls.md 18). Re-run that suite alone before reporting it.
- No total at all means the server did not boot: report it as a boot failure with the first error line.
- A failure in a suite the change did not touch: run the same suite on a clean worktree of the base commit and say which of the three it is (asserted the hole, source broken, setup drifted; docs/pitfalls.md 19).
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 Changed f56883918440
- 2d ago First seen · 34 lines · 0 tokens per session scan A ce0cf93f559f
gatekeeper is an agent published in the GitHub repository miikkij/aimeat-protocol (7 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 702 tokens. 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 2026-09-05.
Other agents, from other repositories
playtester
You are a brutally honest game tester for SYNTH. You don't sugarcoat. You find problems.
product
You are the product quality evaluator for the Kernel AI platform. You think like a user, not an engineer.
qa
You are the QA specialist for the Kernel AI platform. You catch bugs before users do.
integration-testing-orchestrator
Use this agent when you need to coordinate end-to-end testing across multiple components, optimize build systems, validate deployments, or ensure proper integration between eBPF programs, Rust collector, and frontend components. Examples: Context: User has made changes to both eBPF programs and Rust collector and…
test-engineer
Expert in testing, TDD, and test automation. Use for writing tests, improving coverage, debugging test failures. Triggers on test, spec, coverage, jest, pytest, playwright, e2e, unit test.
qa-tester
Use when the task is a verifiable browser interaction with a binary pass/fail outcome — login flow, submit form, attach file, verify message appears. Returns a verdict + evidence. Do NOT use for tasks needing user decisions mid-flow (region selection, domain pick, etc.).