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.
curl -O https://raw.githubusercontent.com/hawkixs/brain-v42/main/CLAUDE.mdgit clone --depth 1 https://github.com/hawkixs/brain-v42Wrote 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/hawkixs/brain-v42/claude-md)<a href="https://agentmods.dev/instructions/hawkixs/brain-v42/claude-md"><img src="https://agentmods.dev/badge/instructions/hawkixs/brain-v42/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.
<a href="https://agentmods.dev/instructions/hawkixs/brain-v42/claude-md"><img src="https://agentmods.dev/badge/instructions/hawkixs/brain-v42/claude-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 | $0.08783 | $0.08783 |
| Opus 5.5 | $0.03513 | $0.03513 |
| Sonnet 5.5 | $0.01757 | $0.01757 |
| Haiku 4.5 | $0.00878 | $0.00878 |
Grade A, and why
brain-v42 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 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.
How it starts
The opening of the file, as written. The whole thing — 643 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - brain_v42
Overview
Second Cerveau v42 — persistent memory for Claude Code over MCP.
- Type: mcp-server
- Stack: Python 3.12+, FastMCP 3.x, SQLAlchemy 2.0 async, asyncpg, Alembic, pgvector, httpx, Pydantic 2, structlog
- Status: in active production; maintenance, hardening and ticket-driven work in progress
MCP transport: production (red-base) = HTTP on the host's WireGuard address (BIND_ADDRESS, port 8765, path /mcp) in credentials mode, every call authenticated; local HTTP (workstation/dev) = loopback http://127.0.0.1:8765/mcp (the configuration default bind); configuration default and dev/fallback transport = stdio.
Embedding topology: production uses hosted embeddings via deploy/compose.yaml (x-embedding-env: EMBEDDING_BACKEND=openai, Mistral codestral-embed-2505, 1536 dimensions). The local endpoint http://localhost:8003 is optional for development only; the former workstation deployment is retired.
⚠️ Living state does NOT live in this file
This document describes RULES and a SHAPE. Everything that can be measured lives in brain, or on the machine.
This is not a style preference, it is a correction. This file announced a wrong schema revision for ten days and a wrong killswitch for ten nights, and it contradicted itself on the same number three paragraphs apart — because it copied measurements. A document that copies a measurement cannot know it has aged: it stays green through the drift.
| What you want to know | Where to read it |
|---|---|
| Alembic head in production | brain_fact_get("alembic_head") |
| Head shipped with the release | brain_fact_get("alembic_head_shipped") |
| Live image release | brain_fact_get("live_release_sha") |
| Declared Dream killswitches | brain_fact_get("dream_killswitches_declared") |
| Last Dream night | brain_fact_get("dream_last_night") |
| Last nightly claim verification | brain_fact_get("claims_verification_last_night") |
| Graph projection lag | brain_fact_get("graph_projection_lag") |
| Full catalogue of facts | brain_fact_list |
| Focus, tickets, blockers, the night's failure | the brain_session_start briefing |
| Decisions, learnings, snippets, runbooks, ADRs | brain_search |
| State of an observable delivery | brain_delivery_get / brain_delivery_list |
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 · +3 lines · +54 tokens per session e1d93ce07fab
- 20d ago Changed · +2 lines · +15 tokens per session f5b189319e3c
- 21d ago Changed · +7 tokens per session 54c71598d20f
- 23d ago Changed · +15 tokens per session 9e93808a7425
- 27d ago Changed 79a829564b24
- 1mo ago Changed 8345015d9516
- 1mo ago Changed · +4 lines · +313 tokens per session fddac90cfbac
- 1mo ago Changed · +18 lines · +581 tokens per session 16a038a15d4f
- 1mo ago Changed 2e772f1bd0fc
- 1mo ago First seen · 616 lines · 7,798 tokens per session scan A f7958b947faf
brain-v42 CLAUDE.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 8,783 tokens to every session, about $0.0351 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.
brain-v42 CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| brain-v42 CLAUDE.mdhawkixs/brain-v42 | Instructions file | 3 | 19d ago | Apache-2.0 | A | 8,783 | Claude Code |
| 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 |