Borrowing it
Nothing to install: this file belongs to dryow1/steel-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/dryow1/steel-brain/main/CLAUDE.mdgit clone --depth 1 https://github.com/dryow1/steel-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/dryow1/steel-brain/claude-md)<a href="https://agentmods.dev/instructions/dryow1/steel-brain/claude-md"><img src="https://agentmods.dev/badge/instructions/dryow1/steel-brain/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/dryow1/steel-brain/claude-md"><img src="https://agentmods.dev/badge/instructions/dryow1/steel-brain/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00281 | $0.00281 |
| Opus 5 | $0.00140 | $0.00140 |
| Sonnet 5 | $0.00056 | $0.00056 |
| Haiku 4.5 | $0.00028 | $0.00028 |
Grade A, and why
steel-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 8d 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.
What it actually says
steel-brain — project rules
MCP tool server: steel domain knowledge for other people's agents. Spec: GATE1-STEEL-BRAIN.md (frozen — do not expand scope).
Hard rules
- NO BMS, NO YHF data, NO prices, NO stock. Ever.
- Unknown grade -> honest "not in KB" response. Never infer or guess properties.
- Every KB entry needs "verified_by": "kee" + date. Unverified entries are NOT served.
- One feature per commit. Update STATE.md after every commit.
- Tests first. Gate 2 scorecard = tests/test_gate2.py (10 tests).
Layout
kb/ grades.json, substitutions.json, certs.json (THE PRODUCT) src/steel_brain/ kb.py loader + validation (rejects malformed/unverified) tools.py grade_lookup, substitution_check, cert_guide shell/ auth.py (API keys), metering.py, ratelimit.py http_api.py FastAPI app (public HTTP door, X-API-Key header) mcp_server.py MCP stdio server (registry door) scripts/ validate_kb.py, issue_key.py deploy/ setup_vps.sh, steel-brain.service, RUNBOOK.md registry/ metadata for the 4 registry submissions
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.
- 8d ago First seen · 23 lines · 281 tokens per session scan A 2f096e131a65
steel-brain CLAUDE.md is an instructions file published in the GitHub repository dryow1/steel-brain (0 stars, last pushed 13d ago), licensed MIT. It adds 281 tokens to every session, about $0.0014 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
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.