Borrowing it
Nothing to install: this file belongs to bbarrosdavi/mechabrain. 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/bbarrosdavi/mechabrain/main/CLAUDE.mdgit clone --depth 1 https://github.com/bbarrosdavi/mechabrainWrote 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/bbarrosdavi/mechabrain/claude-md)<a href="https://agentmods.dev/instructions/bbarrosdavi/mechabrain/claude-md"><img src="https://agentmods.dev/badge/instructions/bbarrosdavi/mechabrain/claude-md.svg" alt="Measured on agentmods" 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 | $0.01314 | $0.01314 |
| Opus 5 | $0.00657 | $0.00657 |
| Sonnet 5 | $0.00263 | $0.00263 |
| Haiku 4.5 | $0.00131 | $0.00131 |
Grade A, and why
mechabrain 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 6d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — governança do agente no repositório mechabrain
Guia para agentes (Claude e afins) que trabalham neste repositório — o kernel do
Mecha-Brain (CLI mechabrain + servidor MCP + templates). O contrato que vai para dentro
das vaults hospedeiras é gerado de src/mechabrain/templates/agents.md.tmpl; este
arquivo governa o trabalho sobre o código do kernel.
Orientação rápida
- O que é este repo: o kernel, instalado fora da vault (via
uv tool). Ele não contém nenhum caminho, nome de vault ou nome de agente de deployment — esses valores vêm sempre do manifest (_meta/config.yaml). Não codifique nada específico de deployment aqui. - Fontes de verdade — a documentação vive na VAULT, não neste repo. A casa canônica da
spec normativa é a nota
2026-07-16_DOC_Mecha_Brain_Specna vault; o setup e os guias são a série de docs do Mechabrain (02_Docs/). Mudança de comportamento do kernel que contradiga a spec exige emenda marcada na spec da vault (viamecha-scribe), citando a versão do kernel — não "no mesmo commit", já que a spec não mora mais no repositório. - Nunca documente no repositório. Não crie um
docs/nem specs/guias em Markdown aqui — documentação é conteúdo e vai para a vault (Classe B /mecha-scribe). Exceção única: quando o Davi pedir explicitamente. - Idioma: código, docstrings e mensagens de erro em inglês; README e docs de usuário em PT-BR.
- Dev:
uv venv --python 3.13 uv pip install -e ".[dev]" uv run pytest -q # testes uv run ruff check . # lint
Pilar 1 — Restrição de ferramentas e isolamento de escrita (sandboxing)
O contrato de fronteiras de escrita do host-vault é único e gerado: veja
src/mechabrain/templates/agents.md.tmpl §1 (Fronteiras P4) e §2 (tools MCP), deployado como
mecha-brain/AGENTS.md. Não repita as regras aqui; se precisarem mudar, edite o template
e rode mechabrain sync.
Recorte deste repo (o que o template não cobre):
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.
- 6d ago First seen · 89 lines · 1,314 tokens per session scan A 2dc4669b452f
mechabrain CLAUDE.md is an instructions file published in the GitHub repository bbarrosdavi/mechabrain (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,314 tokens to every session, about $0.0066 per session on Opus 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 2026-08-31.
Other instructions, from other repositories
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.
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.
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 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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.