What is brain-v42 AGENTS.md?

Repository instructions for coding agents working on the brain-v42 project. They point agents to the shared rules, required reading, testing process, project structure, and operational cautions.

Use them when an agent must understand how to work safely in the brain-v42 repository, including its tests, memory system, measurements, installation, and releases.

They reduce mistakes caused by an agent missing project-specific rules or relying on outdated information. They also clarify which instructions apply when several agent tools are used.

How hawkixs/brain-v42 configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to hawkixs/brain-v42. 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/hawkixs/brain-v42/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/hawkixs/brain-v42

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/hawkixs/brain-v42/agents-md/github.svg)](https://agentmods.dev/instructions/hawkixs/brain-v42/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/hawkixs/brain-v42/agents-md"><img src="https://agentmods.dev/badge/instructions/hawkixs/brain-v42/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/hawkixs/brain-v42/agents-md"><img src="https://agentmods.dev/badge/instructions/hawkixs/brain-v42/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,697 This file is loaded in full into every session.

When invoked 1,697 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 original No closer match found 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.

Model	Per session	Once invoked
Fable 5.1	$0.01697	$0.01697
Opus 5.5	$0.00679	$0.00679
Sonnet 5.5	$0.00339	$0.00339
Haiku 4.5	$0.00170	$0.00170

Measured 18d ago against content hash b52fe4bdf7ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

brain-v42 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 18d 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.

AGENTS.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — brain-v42

Common instructions — mandatory reading

Before any action on this project, read CLAUDE.md in full, even though this AGENTS.md exists. If the output is truncated, resume reading section by section until the whole document has been read.

CLAUDE.md is the shared source of this project's rules for Claude Code, Codex and OpenCode. Its working instructions apply to every harness, not just its facts and commands. This file provides the Codex / OpenCode adaptation and keeps the GitNexus instructions; it does not duplicate the shared rules, so that their next updates stay aligned. System instructions, developer instructions and explicit user requests keep their precedence; a nearer AGENTS.md narrows its own scope.

Mandatory reading covers in particular:

Domain	`CLAUDE.md` sections to apply
Real state and provenance of measurements	"Living state does NOT live in this file"
TDD and verification	"TDD workflow", "Tests", "Code conventions"
Brain: project key, sessions, memory and tools	"Second Cerveau"
Installation and code organisation	"Quick start", "Project structure"
Production, releases, data and secrets	"Architecture", "Configuration"
CI, commits, PRs and language on GitHub	"CI/CD", "Git workflow"
Impact analysis and index freshness	"GitNexus — operating notes"

This repository is public

hawkixs/brain-v42 is public (Apache-2.0). Anything you write here is published.

No LAN address, no username, no SSH key path, no personal filesystem path, no token. Machine access lives in brain: brain_get(entity_type="learning", entity_id="2a23883d"), or brain_search(query="dev machines access", project_key="brain-v42").
Everything is written in English: commits, branches, PRs, docs, code comments, test names, and these instruction files. Conversation with the operator stays in French.
Plans, specs, design notes, receipts and handoffs go under internal/ (the private brain-v42-internal repository cloned there, git-ignored), never directly under docs/. See CLAUDE.md, "Internal working material".

Read the full file on GitHub · 117 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.

18d ago Changed · +1 lines · +18 tokens per session b52fe4bdf7ed
20d ago Changed · +15 tokens per session c7e09c4c65a3
1mo ago Changed · +3 lines · +58 tokens per session 8723cf94d85d
1mo ago First seen · 113 lines · 1,606 tokens per session scan A 25d294b56947

Subscribe to this mod's changes

brain-v42 AGENTS.md is an instructions file published in the GitHub repository hawkixs/brain-v42 (3 stars, last pushed 19d ago), licensed Apache-2.0. It adds 1,697 tokens to every session, about $0.0068 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 2026-09-23.

Memory and context Project management claude fastmcp knowledge-base mcp pgvector

brain-v42 AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
brain-v42 AGENTS.mdhawkixs/brain-v42	Instructions file	3	19d ago	Apache-2.0	A	1,697	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	yesterday	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

brain-v42: Instructions file for Codex