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 instructions/floomhq/moto/agents-mdgit clone --depth 1 https://github.com/floomhq/motoWrote 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/instructions/floomhq/moto/agents-md)<a href="https://agentmods.dev/instructions/floomhq/moto/agents-md"><img src="https://agentmods.dev/badge/instructions/floomhq/moto/agents-md.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 | $0.00868 | $0.00868 |
| Opus 5 | $0.00434 | $0.00434 |
| Sonnet 5 | $0.00174 | $0.00174 |
| Haiku 4.5 | $0.00087 | $0.00087 |
Grade A, and why
moto AGENTS.md 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 3d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Floom Agent Instructions
Hard Rule: Primitive-First Architecture
You may NOT propose, design, or implement custom infrastructure unless you have completed the lock below. This rule takes precedence over any user urgency or task description.
"Infrastructure" includes: Dockerfiles, docker-compose, K8s, Terraform, Pulumi, self-hosted queues, custom API gateways, hand-rolled OpenAPI specs, systemd services, custom sandbox/containers, and unnecessary wrapper services around managed APIs.
The Lock (Mandatory Before Any Infra Proposal)
-
State the primitive. One sentence. No brands. No implementation.
- ❌ "We need a FastAPI service in Docker."
- ✅ "We need to safely execute untrusted user code and return stdout."
-
Search for managed services. You MUST use
SearchWeborFetchURL. Training data is not sufficient. List 3+ candidates with real URLs and one hard limit each.- If the primitive is code execution / sandboxes: e2b.dev is the default. You must evaluate it first.
- If the primitive is background jobs: default to Inngest, Trigger.dev, or QStash.
- If the primitive is auth: default to Clerk, Auth.js, or Supabase Auth.
- If the primitive is file uploads: default to UploadThing or Cloudflare R2.
- If the primitive is databases: default to Supabase, Neon, or PlanetScale.
-
Managed service is the default. Custom infrastructure requires ALL of the following:
- Specific, falsifiable rejection of each managed candidate (cite docs)
- Actual cost comparison at current scale (numbers, not guesses)
- Proof the managed service lacks a required feature
Banned justifications: "more control", "flexibility", "might scale later", "vendor lock-in", "simple to self-host", "we want a thin wrapper".
-
Wrapper anti-pattern. Using a managed service does NOT mean building a platform around it.
- ❌ Wrong: Proposing a custom
floom-code-runnerFastify service that wraps e2b with extra abstraction layers. - ✅ Right: Using the e2b SDK directly in the existing API route or serverless function.
- Do not propose new services, microservices, or abstraction layers unless the user explicitly asked for them.
- ❌ Wrong: Proposing a custom
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.
- 3d ago First seen · 61 lines · 868 tokens per session scan A 0422c1f12f59
moto AGENTS.md is an instructions file published in the GitHub repository floomhq/moto (32 stars, last pushed 2mo ago), licensed MIT. It adds 868 tokens to every session, about $0.0043 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 2026-08-30.
Other instructions, from other repositories
agent-ready-repo AGENTS.md
AGENTS.md instructions for eugenelim/agent-ready-repo, covering agents.md, project overview, rule lookups, documentation and development workflow.
AmbyKit CLAUDE.md
Instructions for ambystechcom/AmbyKit, covering claude code — notes for the ambykit repo and claude-specific.
better-codebase CLAUDE.md
Claude Code instructions for NicolasYusim/better-codebase: Read and follow AGENTS.md when developing this repository.
AIWiki CLAUDE.md
Claude Code instructions for XuebinMa/AIWiki, covering claude.md — aiwiki 项目记忆, 这是什么, 每次动手前必读(按顺序), 写作 / 翻译用 skill(不要手搓流程) and 保持连贯的硬规则(防止跨会话的风格 / 内容漂移).
Agentic-Ground-Rules GEMINI.md
Gemini CLI instructions for criger/Agentic-Ground-Rules, a project described as: Model-agnostic AGENTS.md templates and project instructions for AI coding agents such as Codex, Claude Code and Gemini CLI.
peky AGENTS.md
AGENTS.md instructions for regenrek/peky, covering strict implementation rules, workflow, testing and coding rules.