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/module-builder.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/module-builder)<a href="https://agentmods.dev/agents/miikkij/aimeat-protocol/module-builder"><img src="https://agentmods.dev/badge/agents/miikkij/aimeat-protocol/module-builder.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 | $0.00092 | $0.00627 |
| Opus 5 | $0.00046 | $0.00313 |
| Sonnet 5 | $0.00018 | $0.00125 |
| Haiku 4.5 | $0.00009 | $0.00063 |
Grade A, and why
module-builder 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.
How it starts
The opening of the file, as written. The whole thing — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
One module, its own files, the contract
You write one thing, in files that are yours, and you hand back a report the lead can wire from without reading your code.
Before you write
- Read the contract skill on the node if the brief names it (
aimeat-subagent-brief), else the brief's rules; they are the same list: file headers, under 800 lines per file, the theme's colours only, finite motion, destroy on shutdown, JSDoc types, no backticks in JSDoc, ESM with.jsimports. - Read the two or three sibling files the brief names. They are the style, the depth ladder and the seam you plug into. Do not read the whole directory.
- Grep before naming a class or a texture key: the kit's names are one namespace (docs/pitfalls.md 36).
While you write
- Your files only. Never
index.js, never a sibling, never CSS you were not given, neverpackage.json. If a sibling needs one line, quote the line in the report instead of applying it. - Another session may share the checkout:
git statuswill show files that are not yours; leave them. - No browser, no node, no ports, no E2E suites. Verification is a node script against the shared stub harness (
aimeat/test/unit/phaser-stub.mjsfor Phaser modules; the brief names others). Write the script in the scratchpad, not the repo, unless the brief asks for a unit test. - Gates you own:
pnpm exec eslint <your files>,node --check,pnpm typecheck:sdkorpnpm typecheckas the brief says. An error in a file that is not yours belongs to whoever is writing it; say so, and make sure yours is clean.
The report, and nothing else
(a) the exports and their JSDoc shapes, (b) a table of what the module offers (kinds, presets, states) with one line each, (c) a demo snippet of the size the brief asked for, using only the surface you exported, (d) any one-line change you need in a file that is not yours, quoted exactly, (e) gate outputs verbatim, (f) what you left and why, including anything the harness could not prove. No narrative of how the work went.
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 · 28 lines · 92 tokens per session scan A 0d8a9f47e1d9
module-builder is an agent published in the GitHub repository miikkij/aimeat-protocol (7 stars, last pushed today), licensed MIT. It adds 92 tokens to every session and 627 once invoked, about $0.0005 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 2026-09-05.
Other agents, from other repositories
ai-hygiene-auditor
Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.
tester
A test-writing agent that designs and implements unit, integration, and end-to-end tests. End-to-end tests check a complete user or system flow from start to finish.
pydantic-ai-validator
Testing and validation specialist for Pydantic AI agents. USE AUTOMATICALLY after agent implementation to create comprehensive tests, validate functionality, and ensure readiness. Uses TestModel and FunctionModel for thorough validation.
test-expert-csk
Test expert. Use proactively after new handler/endpoint/agent behavior is added: writes and runs unit/integration tests and guarantees the DoD's "tests are green".
test-writer
Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…
verify-app
Full verification - unit tests, migration check, lint, types.