ClawRouter is a local service that chooses among language models for each request and handles payment for their use. Autonomous agents use it to access multiple LLM providers through one routing and billing system.
Borrowing it
Nothing to install: this file belongs to BlockRunAI/ClawRouter. 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/BlockRunAI/ClawRouter/main/CLAUDE.mdgit clone --depth 1 https://github.com/BlockRunAI/ClawRouterWrote 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/blockrunai/clawrouter/claude-md)<a href="https://agentmods.dev/instructions/blockrunai/clawrouter/claude-md"><img src="https://agentmods.dev/badge/instructions/blockrunai/clawrouter/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/blockrunai/clawrouter/claude-md"><img src="https://agentmods.dev/badge/instructions/blockrunai/clawrouter/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 | $0.00726 | $0.00726 |
| Opus 5.5 | $0.00290 | $0.00290 |
| Sonnet 5.5 | $0.00145 | $0.00145 |
| Haiku 4.5 | $0.00073 | $0.00073 |
Grade A, and why
ClawRouter 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 today.
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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ClawRouter
Smart LLM router for autonomous agents. 91 models. Two ways to pay:
- Wallet (default) — x402 USDC micropayments signed per call, against
blockrun.ai/api(Base),sol.blockrun.ai/api(Solana) orarc.blockrun.ai/api(Circle's Arc, same EVM key as Base). New installs default to Solana. Per-chain facts (gateway, label, CAIP-2) live insrc/payment-chain.ts. - API key —
brk_live_…from user.blockrun.ai, billed against card-funded account credit, againstapi.blockrun.ai.src/api-key.tsresolves it (env →~/.blockrun/.api-key→~/.openclaw/blockrun/api-key); a key present anywhere wins over a wallet, and no wallet is generated or read in that mode.
Commands
npm install # install dependencies
npm run build # compile with tsup
npm run dev # watch mode
npm test # run vitest
npm run typecheck # type checking
npm run lint # eslint
npm run format # prettier
npm run test:resilience:quick # error + lifecycle resilience tests
npm run test:resilience:full # full resilience suite (4hr stability)
npm run test:e2e:tool-ids # end-to-end tool ID sanitization
npm run test:docker:install # Docker install test
npm run test:docker:edge-cases # Docker edge case tests
npm run test:docker:integration # Docker integration tests
Project structure
src/
├── index.ts # Library entry point
├── cli.ts # CLI entry point
├── auth.ts # Wallet-based authentication
├── api-key.ts # BlockRun API-key auth (api.blockrun.ai)
├── balance.ts # USDC balance management
├── models.ts # Model registry and scoring
├── config.ts # Configuration
├── errors.ts # Error classification
├── logger.ts # Logging
├── journal.ts # Request journaling
├── exclude-models.ts # Model exclusion logic
├── dedup.ts # Request deduplication
├── fs-read.ts # Filesystem reading
├── compression/ # Request/response compression
├── doctor.ts # Diagnostic tool
└── partners/ # Partner integrations
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.
- today Changed a7b07ce74c4c
- 8d ago Changed · +40 tokens per session ae5c19945a7d
- 16d ago Changed 7818ce0626eb
- 26d ago Changed 85262a9f1b66
- 1mo ago Changed 448541f1ef1f
- 1mo ago Changed 3ae5866eca28
- 1mo ago Changed 33e2df8157c0
- 2mo ago Changed · +4 lines · +151 tokens per session 80cadee8dd68
- 2mo ago Changed 12f4b5e6a29f
- 2mo ago First seen · 60 lines · 535 tokens per session scan A 3afba690cf78
ClawRouter CLAUDE.md is an instructions file published in the GitHub repository BlockRunAI/ClawRouter (6,652 stars, last pushed yesterday), licensed MIT. It adds 726 tokens to every session, about $0.0029 per session on Opus 5.5. 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.
ClawRouter CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ClawRouter CLAUDE.mdBlockRunAI/ClawRouter | Instructions file | 6.7k | yesterday | MIT | A | 726 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |