claw-brain CLAUDE.md

claw-brain CLAUDE.md is an instructions file for coding agents from Lanzelot1/claw-brain. It costs 1,242 tokens per session, scanned A, original, MIT.

A set of instructions for Claw Brain, a workspace that stores personal context, source documents, and synthesized knowledge. It organizes incoming files into an archive, knowledge pages, and generated outputs.

In plain words
What is it for?
It is for managing a knowledge workspace with memory files, archived originals, source documents, wiki pages, and dated output files.
Why use it?
It defines where information belongs and how it should move through the workspace, reducing inconsistent notes and lost source material.

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/lanzelot1/claw-brain/claude-md
Clone the repo
git clone --depth 1 https://github.com/Lanzelot1/claw-brain

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 claw-brain CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lanzelot1/claw-brain/claude-md.svg)](https://agentmods.dev/instructions/lanzelot1/claw-brain/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/lanzelot1/claw-brain/claude-md"><img src="https://agentmods.dev/badge/instructions/lanzelot1/claw-brain/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,242 This file is loaded in full into every session.
When invoked 1,242 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 $0.01242 $0.01242
Opus 5 $0.00621 $0.00621
Sonnet 5 $0.00248 $0.00248
Haiku 4.5 $0.00124 $0.00124

Measured 4d ago against content hash 88364e2eadd2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claw-brain 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 4d 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 · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claw Brain

About

  • Purpose: [What this brain is for]
  • Context: [Team, company, or personal use]

Workspace Structure

  • memory/_index.mdRead this first. Table of contents linking to all knowledge files.
  • memory/me.md — Personal profile (gitignored).
  • memory/lessons.md — Learnings from past sessions (gitignored).
  • memory/log.md — Chronological activity log (gitignored). Append here after ingestions, queries, synthesis, lint.
  • knowledge/ — All knowledge documents. Two types: source files (raw facts, data, quotes) and wiki pages (synthesized entity/concept/comparison pages). Single source of truth.
  • raw/ — Immutable source document archive. Originals from drop/ land here during processing. Never modify files in raw/.
  • drop/ — Inbox for new files. Process immediately when files are present.
  • output/ — All generated files. Format: YYYY-MM-DD-description.md

Knowledge flow

drop/ → originals archived to raw/ (immutable) → facts extracted to knowledge/ as source files (type: source) → wiki pages (type: wiki) synthesize across multiple source files with ## Sources and ## Related cross-links. Wiki pages can be deleted and regenerated from source files. Source files are the ground truth.

Personal Context

Read memory/me.md first for personal context (writing style, priorities, tone). This file is gitignored — never committed.

Also check memory/lessons.md for learnings from past sessions — workarounds, preferences, and patterns worth remembering.

If memory/me.md doesn't exist yet, suggest running /onboard to create it.

Rules

  • Index first — Before any task, read memory/_index.md, then open the relevant knowledge/ files as needed.
  • No summaries of individual sources — Source files (type: source) contain raw facts, data, quotes. Don't create a distilled copy of a single source file. Wiki pages (type: wiki) are the exception: they synthesize across multiple sources and must link back to all of them.
  • Two knowledge types — Files in knowledge/ have a type: field in frontmatter: source (default, raw facts) or wiki (synthesized page). Omitted type: is treated as source.
  • Wiki pages must cite sources — Every wiki page needs a ## Sources section at the bottom listing the knowledge files it synthesizes from, using standard markdown links.
  • Outputs as files — Always save to output/YYYY-MM-DD-description.md.
  • No messages without explicit confirmation.
  • English for everything.
  • When writing outreach/content: read memory/me.md for personal writing style.
  • Source required — Every file in knowledge/ needs source: frontmatter. Can be a URL, internal JSON file path, or description (e.g. "interview with client X"). No knowledge without provenance.
  • Facts over fluff — Knowledge files must contain specific facts, data, quotes, or raw information. Never write vague summaries or AI filler.
  • Raw is immutable — Never modify, rename, or delete files in raw/. It's the archive of original source documents.
  • Log activity — After ingestions, synthesis, queries that produce wiki updates, and lint passes, append an entry to memory/log.md.
  • Cross-reference when substantive — When creating or updating knowledge files, add standard markdown links to related files in other areas. Use [title](../area/file.md) format. Don't force connections — only link when the relationship is genuinely useful.

Read the full file on GitHub · 87 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. 4d ago First seen · 87 lines · 1,242 tokens per session scan A 88364e2eadd2

Subscribe to this mod's changes

claw-brain CLAUDE.md is an instructions file published in the GitHub repository Lanzelot1/claw-brain (11 stars, last pushed 4mo ago), licensed MIT. It adds 1,242 tokens to every session, about $0.0062 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.