Borrowing it
Nothing to install: this file belongs to xz0831/openclaw-brain. 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/xz0831/openclaw-brain/main/CLAUDE.mdgit clone --depth 1 https://github.com/xz0831/openclaw-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/xz0831/openclaw-brain/claude-md)<a href="https://agentmods.dev/instructions/xz0831/openclaw-brain/claude-md"><img src="https://agentmods.dev/badge/instructions/xz0831/openclaw-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 5.1 | $0.06067 | $0.06067 |
| Opus 5 | $0.03034 | $0.03034 |
| Sonnet 5 | $0.01213 | $0.01213 |
| Haiku 4.5 | $0.00607 | $0.00607 |
Grade A, and why
openclaw-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 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 — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What This Is
openclaw-brain is an engineering knowledge graph and memory system. It ingests PDFs (semiconductor textbooks, papers), extracts concepts/equations/relationships via LLM, and stores them in a Neo4j graph. It serves as the "brain" for OpenClaw's Rick agent — an AI mentor for a Samsung CIS circuit design engineer.
Exposed as an MCP server (stdio transport). OpenClaw and other MCP-compatible agents call tools like ingest_pdf, analyze_circuit_image, query_knowledge, merge_concepts, retract_node, update_stage_model.
The deeper purpose (see
docs/DEVLOG.md): the graph is the substrate, not the product. The product is a weight-free alignment harness that distills the circuit-domain reasoning of golden-reference models (Opus 4.8 + Codex GPT-5.5) into procedures — an ontology, S1–S5 scaffolds, and a sealed gold — to externally align a small local model (Qwen 27B) to reason like frontier, with no weight training.
The current frontier — executable-circuit substrate (v2;
docs/DECISIONS.mdADR-040/041): for the circuit domain the model no longer only reads PDFs into text — it operates topologies. AVerificationReciperenders a SKY130 SPICE deck (or a Verilog deck) → runs it on ngspice/iverilog → a deterministic oracle (judge_quant) certifies a falsifiable, scope-honest claim-card → the card is projected additively onto the graph. The knowledge atom becomes an oracle-certified claim that knows its own scope, and a teaching loop (Hermes) narrates it under citation audit. See Executable-Circuit Substrate + Teaching Loop below. The PDF→KG pipeline remains — it is now a SEED source alongside the executable corpus.
Development history
Why things are the way they are — read before re-deciding a settled question:
docs/DEVLOG.md— chronological development log (what / why / outcome / dead-ends / evidence), per phase, every claim cited to a commit/file/number and independently fact-checked.docs/DECISIONS.md— the Architecture Decision Records (ADRs): context → decision → rationale → consequences.
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 · 292 lines · 6,067 tokens per session scan A a76c05db08ed
openclaw-brain CLAUDE.md is an instructions file published in the GitHub repository xz0831/openclaw-brain (0 stars, last pushed 2mo ago), licensed MIT. It adds 6,067 tokens to every session, about $0.0303 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.