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.
npx agentmods add instructions/lanzelot1/claw-brain/claude-mdgit clone --depth 1 https://github.com/Lanzelot1/claw-brainWrote 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/lanzelot1/claw-brain/claude-md)<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>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 | $0.01242 | $0.01242 |
| Opus 5 | $0.00621 | $0.00621 |
| Sonnet 5 | $0.00248 | $0.00248 |
| Haiku 4.5 | $0.00124 | $0.00124 |
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.
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.md— Read 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 fromdrop/land here during processing. Never modify files inraw/.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 relevantknowledge/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 atype:field in frontmatter:source(default, raw facts) orwiki(synthesized page). Omittedtype:is treated assource. - Wiki pages must cite sources — Every wiki page needs a
## Sourcessection 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.mdfor personal writing style. - Source required — Every file in
knowledge/needssource: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.
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.
- 4d ago First seen · 87 lines · 1,242 tokens per session scan A 88364e2eadd2
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.
Other instructions, from other repositories
zeroclaw CLAUDE.md
Claude Code instructions for zeroclaw-labs/zeroclaw, covering claude.md — zeroclaw (claude code), claude code settings, hooks and slash commands.
ReMe AGENTS.md
AGENTS.md instructions for agentscope-ai/ReMe, covering agents.md, project principles, sources of truth, repository map and development setup.
framework AGENTS.md
AGENTS.md instructions for ai-driven-dev/framework, covering agents.md, behavior, communication, action and memory management.
braindb CLAUDE.md
Claude Code instructions for dimknaf/braindb, covering braindb — claude instructions, ⚠ tool priority — read this first, it overrides habit, at the start of every session, 1. get always-on rules (behavioral guidelines) and project structure.
lobu AGENTS.md
Instructions for lobu-ai/lobu, covering repo map, unrecoverable — never do these, facts you cannot derive, ship a change and how to work.
souls-directory AGENTS.md
Instructions for thedaviddias/souls-directory, covering agents.md, learned user preferences and learned workspace facts.