cerebro-skill CLAUDE.md

cerebro-skill CLAUDE.md is an instructions file for coding agents from microhustlestack/cerebro-skill. It costs 378 tokens per session, scanned A, original, MIT.

A project guide for CEREBRO, a Python package and agent skill that analyzes Obsidian-style markdown vaults, which are folders of linked notes.

In plain words
What is it for?
It helps inspect vaults, find missing structure and links, detect urgency, identify bottlenecks, and produce Markdown or JSON reports.
Why use it?
It explains the project's commands, file layout, and rules so contributors can validate the skill and keep analysis based on note structure rather than guesswork.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/microhustlestack/cerebro-skill/claude-md
Clone the repo
git clone --depth 1 https://github.com/microhustlestack/cerebro-skill

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 cerebro-skill CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/microhustlestack/cerebro-skill/claude-md.svg)](https://agentmods.dev/instructions/microhustlestack/cerebro-skill/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/microhustlestack/cerebro-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/microhustlestack/cerebro-skill/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 378 This file is loaded in full into every session.
When invoked 378 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00378 $0.00378
Opus 5 $0.00189 $0.00189
Sonnet 5 $0.00076 $0.00076
Haiku 4.5 $0.00038 $0.00038

Measured 5d ago against content hash 801d5b7ce271, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cerebro-skill 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 5d 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.

CLAUDE.md · 51 lines

What it actually says

CLAUDE.md

Guidance for Claude Code when working in this repository.

What this is

CEREBRO is a strategic intelligence engine for markdown vaults. It parses an Obsidian-style vault, scores notes, detects urgency, and surfaces structural gaps and connections.

It ships as both a Python package and an Agent Skill (SKILL.md at root).

Commands

pip install -e ".[dev]"      # setup
pytest                       # 107 tests, sub-second
python3 scripts/validate_skill.py SKILL.md

cerebro /path/to/vault --gaps --report cerebro_report.md
cerebro /path/to/vault out.json --gaps --quiet

Layout

src/cerebro/
  models.py     dataclasses only
  parser.py     VaultParser — file walking, graphs, scoring
  analysis.py   AnalysisMixin — gaps, implicit connections, bottlenecks
  report.py     ReportMixin — markdown + JSON rendering
  cli.py        argparse entrypoint
scripts/
  vault_parser.py     back-compat shim, forwards to the package
  validate_skill.py   SKILL.md frontmatter validator (runs in CI)

VaultParser(ReportMixin, AnalysisMixin) — one object, separated sources.

Conventions

Analysis findings must be structural: derived from links, tags and frontmatter the author wrote. Do not add findings inferred from prose statistics; an unverifiable finding is worse than no finding.

Version lives in src/cerebro/__init__.py and nowhere else. pyproject.toml and the JSON export both read from it.

scripts/vault_parser.py is a compatibility shim. Existing installs call that path — don't delete it, and don't add logic to it.

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. 5d ago First seen · 51 lines · 378 tokens per session scan A 801d5b7ce271

Subscribe to this mod's changes

cerebro-skill CLAUDE.md is an instructions file published in the GitHub repository microhustlestack/cerebro-skill (21 stars, last pushed 4d ago), licensed MIT. It adds 378 tokens to every session, about $0.0019 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 2026-08-30.