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 skills add BlockRunAI/ClawRouter --skill surfgit 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/skills/blockrunai/clawrouter/surf)<a href="https://agentmods.dev/skills/blockrunai/clawrouter/surf"><img src="https://agentmods.dev/badge/skills/blockrunai/clawrouter/surf/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/skills/blockrunai/clawrouter/surf"><img src="https://agentmods.dev/badge/skills/blockrunai/clawrouter/surf.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 77 Subtle instructions detected that may alter agent decision-making or introduce hidden biases.Fix: Review content for implicit steering or bias. Ensure instructions are explicit and align with the skill's stated purpose.
- medium Data Exfiltration · line 233 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00148 | $0.04094 |
| Opus 5.5 | $0.00059 | $0.01638 |
| Sonnet 5.5 | $0.00030 | $0.00819 |
| Haiku 4.5 | $0.00015 | $0.00409 |
Grade A, and why
surf scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl 'http://127.0.0.1:8402/v1/surf/wallet/detail?address=vitalik.eth' How it starts
The opening of the file, as written. The whole thing — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Surf — Unified Crypto Data API (via ClawRouter)
Surf bundles 83 endpoints across 12 domains into one paid HTTP API. ClawRouter exposes them at http://127.0.0.1:8402/v1/surf/*, paid the same way ClawRouter pays for LLM calls — an x402 USDC micropayment from the local wallet, or a draw on BlockRun account credit if an API key is configured (verified working on both, 2026-09-05). No Surf account and no Surf API key either way. Upstream lives at api.asksurf.ai/gateway/v1 — ClawRouter forwards transparently.
Pricing — flat per call, the same for every endpoint.
Surf used to be tiered at $0.001 / $0.005 / $0.020. It is not any more: upstream
now prices all three tiers identically (SURF_TIER_{1,2,3}_PRICE are equal). The
Tier column in the catalog below still describes endpoint weight, but it no
longer affects what you pay. Anything quoting the old tier prices is stale.
| Rail | Price per call |
|---|---|
API key (api.blockrun.ai) |
$0.0075 — base rate, no transaction fee |
| Wallet, Solana | $0.0075 |
| Wallet, Base | $0.0085 |
Verified 2026-09-05 by measurement, not from a price page: the API-key figure by
diffing the account ledger across one call, the wallet figures by reading the
amount in the x402 402 challenge, which quotes the price before anything is
signed. Base and Solana genuinely differ for the same endpoint.
A 402 quote is authoritative for the rail that issued it — and only that rail. On the wallet rail the price arrives in the challenge before you pay, so if this table disagrees with it, believe the challenge and treat the table as stale.
Do NOT carry a wallet-rail 402 figure over to the API-key rail. The key rail issues no 402 at all, and the wallet quote includes the chain's transaction fee that account credit does not pay — on Base that is $0.0085 quoted against $0.0075 actually billed to an account. Reading across rails turns a correct number into a wrong one; it has already happened once.
The Base/Solana difference is deliberate, not drift: the $0.001 is the Base transaction fee, and Solana omitting it is a migration incentive. Solana being cheaper is expected — Solana priced above Base would be the bug worth reporting, since estimates generally assume the Base figure is the ceiling.
The legacy surf-1.5 chat surface is intentionally NOT exposed yet — it's held until per-token settlement is wired. Trying
/v1/surf/chat/completionsreturns 404 ("Unknown Surf endpoint"), no payment is taken.
All requests use GET unless the table below says otherwise. Path parameters that look like ?symbol= are query params on a GET. POST endpoints take a JSON body. ClawRouter attaches payment transparently — an x402 header in wallet mode, a bearer token in API-key mode.
Required-param pre-check. 56 of the 83 endpoints have required query params (e.g. pair, symbol, address, chain, q, interval). The route validates them before settlement — call with missing params and you get 400 { missing_params, all_required, docs } and you are NOT charged. Check each row in the catalog below for the correct param name (e.g. mindshare is q + interval, not project + window).
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.
- 1mo ago Changed · +27 lines · +18 tokens per session 816b2e2a814c
- 1mo ago First seen · 248 lines · 130 tokens per session scan A 1a977464e6b8
surf is a skill published in the GitHub repository BlockRunAI/ClawRouter (6,628 stars, last pushed today), licensed MIT. It adds 148 tokens to every session and 4,094 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
insurance-expert
Expert-level insurance systems, underwriting, claims processing, actuarial analysis, risk assessment, and insurtech solutions. Use when the user mentions underwriting, claims, actuarial, risk, or insurtech, or when the task involves Insurance Systems, Insurance Types, Standards and Regulations, or Claims Processing.
trading-expert
Expert-level algorithmic trading, market systems, quantitative analysis, and trading platforms. Use when the user mentions algorithmic trading, quant, markets, finance, or high-frequency trading, or when the task involves Trading Systems, Market Data, or Execution.
finops-expert
Expert-level cloud financial operations, cost optimization, and cloud economics. Use when the user mentions cloud cost, optimization, cloud economics, or AWS cost, or when the task involves FinOps Fundamentals, Cost Management, FinOps Practices, or Cost Visibility.
blockchain-expert
Expert-level blockchain, Web3, smart contracts, DeFi, and cryptocurrency development. Use when the user mentions Web3, smart contracts, DeFi, Ethereum, or Solidity, or when the task involves Blockchain Fundamentals, Web3 & DeFi, Smart Contract Security, or Gas Optimization.
accountant-expert
Expert-level accounting, tax, financial reporting, and accounting systems. Use when the user mentions accounting, tax, financial reporting, GAAP, or IFRS, or when the task involves Accounting Principles, Financial Statements, Tax & Compliance, or Accounting Systems.
banking-expert
Expert-level banking systems, core banking, regulations, and banking technology. Use when the user mentions finance, core banking, regulations, or payments, or when the task involves Banking Systems or Key Technologies.