Borrowing it
Nothing to install: this file belongs to starmynd-org/infinite-brain-os. 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/starmynd-org/infinite-brain-os/main/AGENTS.mdgit clone --depth 1 https://github.com/starmynd-org/infinite-brain-osWrote 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/starmynd-org/infinite-brain-os/agents-md)<a href="https://agentmods.dev/instructions/starmynd-org/infinite-brain-os/agents-md"><img src="https://agentmods.dev/badge/instructions/starmynd-org/infinite-brain-os/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/starmynd-org/infinite-brain-os/agents-md"><img src="https://agentmods.dev/badge/instructions/starmynd-org/infinite-brain-os/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 | $0.01549 | $0.01549 |
| Opus 5.5 | $0.00620 | $0.00620 |
| Sonnet 5.5 | $0.00310 | $0.00310 |
| Haiku 4.5 | $0.00155 | $0.00155 |
Grade A, and why
infinite-brain-os 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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- infinite-brain-os CLAUDE.md — 98% identical, 6 lines differ
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Infinite Brain, Working Repo (Codex)
This repo is the brain for running a business with AI agents. You have full write autonomy here. Codex does the heavy lifting; this file orients it.
If the task touches architecture, routing, knowledge structure, sessions, swarms, or planning, orient from this file and the doctrine first.
Forced startup for every non-trivial chat
For every non-trivial session that reads or writes repo state, do this before substantive work:
- Read
knowledge/ai-architecture/canon/doctrine-card.md. It is the compressed operating projection of core-doctrine: the hard rules, the control spine, the entity types, and the drill-down pointers. - If the task touches a knowledge domain, read
_system/retrieval-routing-map.mdand load the namespaces it routes to, entering each through itsINDEX.md. - For architecture-touching, contract-touching, or canon-touching work,
knowledge/ai-architecture/canon/core-doctrine.mdand_system/README.mdare mandatory reads. - Start the session ledger unless the task is truly trivial and leaves no durable change.
A trivial task is a one-line factual lookup or a no-file explanation. Hard rule: if the task creates, edits, moves, or deletes any file, it is non-trivial.
Forced session discipline
Unless the task is truly trivial, every chat session uses the sessions/ layer: register
under sessions/active/, declare a transcript path under sessions/logs/, keep running
notes, write a closeout review under sessions/reviews/, then move the record to
sessions/closed/. The contract is _system/session-ledger-rules.md; the technique is
entities/skills/manage-ai-session.md.
If a chat operates inside a swarm sprint, dual-write: sessions/ for the conversation
trail, swarms/Sprints/... for execution artifacts and receipts.
Disposable test artifacts default to outputs/, never to knowledge surfaces.
The eleven entities
Everything you build is one of eleven typed entities:
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.
- 1mo ago Changed · -2 tokens per session 1eec682487b0
- 2mo ago First seen · 136 lines · 1,551 tokens per session scan A ee7a667fcba3
infinite-brain-os AGENTS.md is an instructions file published in the GitHub repository starmynd-org/infinite-brain-os (273 stars, last pushed 17d ago), licensed MIT. It adds 1,549 tokens to every session, about $0.0062 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 2026-08-30.
infinite-brain-os AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| infinite-brain-os AGENTS.mdstarmynd-org/infinite-brain-os | Instructions file | 273 | 17d ago | MIT | A | 1,549 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |