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.
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/blockrunai/clawrouter/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.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 | $0.00535 | $0.00535 |
| Opus 5 | $0.00267 | $0.00267 |
| Sonnet 5 | $0.00107 | $0.00107 |
| Haiku 4.5 | $0.00053 | $0.00053 |
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 2d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ClawRouter
Smart LLM router for autonomous agents. 76 models. Wallet-based auth. USDC micropayments via x402.
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
├── 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
Key dependencies
@x402/fetch,@x402/evm,@x402/svm— x402 payment protocolviem— Ethereum interaction@solana/kit— Solana interaction@scure/bip32,@scure/bip39— Wallet key derivation
Conventions
- TypeScript strict mode, ESM
- Build with tsup, test with vitest
- Lint with eslint, format with prettier
- Node >= 22
- MIT license
- npm registry:
@blockrun/clawrouter
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.
- 2d ago Changed 12f4b5e6a29f
- 5d 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 (6,578 stars, last pushed yesterday), licensed MIT. It adds 535 tokens to every session, about $0.0027 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
opentrade CLAUDE.md
Claude Code instructions for brandononchain/opentrade, covering opentrade agent — decision guide, which skill to apply, tool decision tree, reading the chart and multi-timeframe analysis.
InvestSkill copilot-instructions.md
Copilot instructions for yennanliu/InvestSkill, covering investskill — github copilot setup & usage guide, installation & setup, automatic setup, verify setup and core stock analysis (6 frameworks).
InvestSkill GEMINI.md
Gemini CLI instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).
AI-MarkDone copilot-instructions.md
Instructions for zhaoliangbin42/AI-MarkDone, covering ai copy enhance - ai coding agent instructions, project overview, architecture patterns, adapter pattern for multi-platform support and shadow dom isolation.
AI-MarkDone AGENTS.md
Instructions for zhaoliangbin42/AI-MarkDone, covering ai-markdone engineering guide, project facts, read order, common commands and non-negotiables.
bob-plugin-ollama-translator CLAUDE.md
Instructions for CaicoLeung/bob-plugin-ollama-translator, covering claude.md, agent skills, issue tracker, triage labels and domain docs.