infinite-brain-harness: Instructions file for Claude Code

CLAUDE.md

infinite-brain-harness CLAUDE.md is an instructions file for Claude Code from starmynd-org/infinite-brain-harness. It costs 1,714 tokens per session, scanned A, a copy of infinite-brain-harness AGENTS.md, MIT.

Instructions for a shared parent folder that routes work to the right repository and keeps those repositories backed up and registered. A repository is a project folder tracked by version control.

In plain words
What is it for?
It helps orient an agent, register and sync owned repositories, mount shared or personal workspaces, copy their commands into the parent folder, and route other projects without mounting them.
Why use it?
It clarifies which folders are shared or personal workspaces and prevents product repositories from being treated like the special workspaces that provide shared commands.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code; mentions AGENTS.md; mentions Codex.

This is starmynd-org/infinite-brain-harness's own configuration. It tells Claude Code how to work on infinite-brain-harness itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything infinite-brain-harness configures →

Reuse

Borrowing it

Nothing to install: this file belongs to starmynd-org/infinite-brain-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/starmynd-org/infinite-brain-harness/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/starmynd-org/infinite-brain-harness

Made for: Claude Code.

Wrote 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.

agentmods badge for infinite-brain-harness CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/starmynd-org/infinite-brain-harness/claude-md/github.svg)](https://agentmods.dev/instructions/starmynd-org/infinite-brain-harness/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/starmynd-org/infinite-brain-harness/claude-md"><img src="https://agentmods.dev/badge/instructions/starmynd-org/infinite-brain-harness/claude-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.

agentmods 80×15 button for infinite-brain-harness CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/starmynd-org/infinite-brain-harness/claude-md"><img src="https://agentmods.dev/badge/instructions/starmynd-org/infinite-brain-harness/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,714 This file is loaded in full into every session.
When invoked 1,714 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 94% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01714 $0.01714
Opus 5 $0.00857 $0.00857
Sonnet 5 $0.00343 $0.00343
Haiku 4.5 $0.00171 $0.00171

Measured 10d ago against content hash 8a8d0022dcbc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

infinite-brain-harness CLAUDE.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 10d 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.

Origin

This is a copy

94% identical to infinite-brain-harness AGENTS.md — 17 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Harness (Claude Code orientation)

This is the harness: the shared-parent tier of the Infinite Brain topology, and the folder you open in Claude Code. It holds no work of its own. Its job is to route your work to the right brain, keep every brain backed up and synced, and keep an inventory of every repo you run. Orient from this file first. AGENTS.md is the Codex mirror; keep the two in sync.

One folder for everything you own: internal/

internal/ holds every repo your own operation owns and operates end to end. It carries two kinds of child, and the difference is what the harness does with them, not where they sit:

Kind What it is What the harness does
A mounted brain Your shared work brain (a company brain, or a department brain that graduated to its own repo) and your individual brain (individual-<your-name>/) Clones it in, validates it, registers it, syncs it, and copies its commands up so they work here
Any other repo Product code, client-facing apps, tools: anything you own that is not a brain Registers it and routes to it. Never mounts it, never copies its commands up

The harness tells them apart structurally, not from a list: a child is a mounted brain when it carries both .claude/ and _system/validate.sh, the marker every brain built from the Infinite Brain OS starter has and no app repo does. A hand-kept list would be wrong the first time a brain was added, and the failure would be silent: the new brain's commands would simply never appear and nobody would be told why. It also means an app repo can carry its own .claude/ without leaking commands into this root, which matters, because plenty of them do.

external/ is the other half of the ownership axis: repos a client owns or that are co-operated with an outside party, with one client's several repos grouped under external/<group>/. Brains are never mounted from external/; a client's brain is theirs to mount in their own harness.

Read the full file on GitHub · 114 lines

Changes

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.

  1. 10d ago First seen · 114 lines · 1,714 tokens per session scan A 8a8d0022dcbc

Subscribe to this mod's changes

infinite-brain-harness CLAUDE.md is an instructions file published in the GitHub repository starmynd-org/infinite-brain-harness (23 stars, last pushed 10d ago), licensed MIT. It adds 1,714 tokens to every session, about $0.0086 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to infinite-brain-harness AGENTS.md, differing in 17 lines, and is treated as a copy.

Related

Other instructions, from other repositories

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.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

deepseek-ai/deepseek-harness · 3,735 tokens