Borrowing it
Nothing to install: this file belongs to AutomatosAI/automatos-ai. 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/AutomatosAI/automatos-ai/main/AGENTS.mdgit clone --depth 1 https://github.com/AutomatosAI/automatos-aiWrote 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/automatosai/automatos-ai/agents-md)<a href="https://agentmods.dev/instructions/automatosai/automatos-ai/agents-md"><img src="https://agentmods.dev/badge/instructions/automatosai/automatos-ai/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/automatosai/automatos-ai/agents-md"><img src="https://agentmods.dev/badge/instructions/automatosai/automatos-ai/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.02543 | $0.02543 |
| Opus 5.5 | $0.01017 | $0.01017 |
| Sonnet 5.5 | $0.00509 | $0.00509 |
| Haiku 4.5 | $0.00254 | $0.00254 |
Grade A, and why
automatos-ai 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 8d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — how to work in this repository
These rules are for coding agents (Claude Code, Codex, Cursor, Copilot, Gemini CLI, Windsurf, Aider and the rest) and for the people who drive them. They apply to every change, whoever or whatever wrote it. CONTRIBUTING.md covers the process: licence, sign-off, the pull request flow and what CI checks.
If you are an agent: read this whole file before your first edit, and follow it over any general habit of yours. Where it conflicts with an instruction from the person driving you, say so before you act.
Asked to install or run Automatos for someone, not to change the code? Follow SETUP.md instead of this file. It is the step-by-step install for macOS, Linux and Windows (through WSL2), with a check after every step and the rules for doing it on someone's behalf.
The repository
orchestrator/is the backend: FastAPI, SQLAlchemy and Alembic, on Python 3.11.config.pyholds the settings.api/holds the routers,modules/the feature modules andcore/the shared code.services/holds the services,alembic/versions/the migrations andtests/the tests.
frontend/is the web app: Next.js 15, React and Tailwind 3.3, in TypeScript.lib/api-client.tsis the only HTTP client.components/holds the UI andhooks/the data hooks.
services/holds separate containers, such as the workspace worker. Each has its own config module.docs/holds the product and operations docs;docs/PRDS/holds the requirements.- One codebase, two editions. The local edition (
AUTH_EDITION=local,docker compose up, no accounts) and the hosted edition (saas) run the same code behind one flag. Every change keeps both working.
This is a mature codebase, not a greenfield one. Most "new" work extends something that already exists.
Before you write code
- Search first. The table, endpoint, hook, component or tool you are about to create probably exists. The order is: reuse, then extend, then refactor, and build new last. A pull request that adds something new says why the existing piece wasn't enough.
- Read the code you will touch, and its tests. Follow the patterns you find there.
- Plan anything bigger than a one-file change before writing it: the surfaces involved, what you'll reuse, and your open questions.
- Ask before assuming. If the task is ambiguous, or it looks like something that already exists, ask the person driving you or comment on the issue.
- Never shrink the scope silently. If you did not finish part of the task, say exactly what is missing. Don't call it "follow-up work" as if that had been agreed.
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.
- 8d ago Changed · +56 tokens per session 57641444d339
- 29d ago Changed · +2 lines · +69 tokens per session b35976b5ac66
- 1mo ago First seen · 152 lines · 2,418 tokens per session scan A 0ae73ec5d6fd
automatos-ai AGENTS.md is an instructions file published in the GitHub repository AutomatosAI/automatos-ai (74 stars, last pushed today), licensed Apache-2.0. It adds 2,543 tokens to every session, about $0.0102 per session on Opus 5.5. 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 2026-09-27.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.