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 phonegit 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/phone)<a href="https://agentmods.dev/skills/blockrunai/clawrouter/phone"><img src="https://agentmods.dev/badge/skills/blockrunai/clawrouter/phone/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/phone"><img src="https://agentmods.dev/badge/skills/blockrunai/clawrouter/phone.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 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 132 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 137 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 144 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 141 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00072 | $0.02402 |
| Opus 5.5 | $0.00029 | $0.00961 |
| Sonnet 5.5 | $0.00014 | $0.00480 |
| Haiku 4.5 | $0.00007 | $0.00240 |
Grade A, and why
phone 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.
- For programmatic polling, see the `voice_status` tool — for one-off CLI checks, hit `curl http://localhost:8402/v1/voice/call/{call_id}` directly How it starts
The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phone & Voice
Phone-number intelligence (Twilio Lookup) and AI-powered outbound voice calls (Bland.ai) through ClawRouter's local proxy. Payment is automatic via x402 from the user's BlockRun wallet.
Shortcuts:
- Slash:
/cr-call +1<E.164> "<task>" [--voice nat] [--max-duration 5] [--from +1<owned-number>] [--language en-US] - CLI:
clawrouter phone numbers list/buy/renew/release,clawrouter phone lookup <+E.164>,clawrouter phone fraud <+E.164> - Partner tools (LLM-callable):
blockrun_phone_lookup,blockrun_phone_lookup_fraud,blockrun_phone_numbers_buy/renew/list/release,blockrun_voice_call,blockrun_voice_status
⚠️ Real-world side effects.
blockrun_voice_callplaces a real outbound phone call to a real number. Only invoke when the user has explicitly asked for a call to be placed. Server enforces an emergency-number blocklist.
Phone Number Intelligence (Twilio)
Carrier + Line Type Lookup — $0.01
POST to http://localhost:8402/v1/phone/lookup:
{ "phoneNumber": "+14155552671" }
Returns carrier name, line type (mobile / landline / voip), country, mobile country/network codes. Use to verify whether a number is reachable, detect VoIP/spam patterns, or route SMS appropriately.
Fraud Risk Check — $0.05
POST to http://localhost:8402/v1/phone/lookup/fraud:
{ "phoneNumber": "+14155552671" }
Adds SIM-swap recency and call-forwarding signals on top of carrier+line type. Run this before sending sensitive SMS codes or initiating account-recovery flows — a number flagged for recent SIM swap is high-risk for account takeover.
Wallet-Owned Phone Numbers
Numbers are leased for 30 days, bound to the wallet's payer address. Use one as the from parameter of voice_call to present a stable caller ID.
Buy — $5.00 / 30 days
POST to http://localhost:8402/v1/phone/numbers/buy:
{ "country": "US", "areaCode": "415" }
country is "US" or "CA". areaCode is optional (3-digit, best-effort match). Returns { phone_number, expires_at, chain }.
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 · +1 lines 32f3d6df1039
- 1mo ago First seen · 209 lines · 72 tokens per session scan A a550c4796a33
phone is a skill published in the GitHub repository BlockRunAI/ClawRouter (6,628 stars, last pushed 2d ago), licensed MIT. It adds 72 tokens to every session and 2,402 once invoked, about $0.0003 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
route
Route a task to the best LLM based on task type and complexity.
routing
Route tasks to the cheapest capable model automatically using llmrouter MCP tools.
savings
Report how much routing has saved by sending tasks to cheaper models.
ai-engineer-expert
Expert-level AI implementation, deployment, LLM integration, and production AI systems. Use when the user mentions AI engineering, LLM, deployment, production AI, or integration, or when the task involves LLM Patterns, LLM Integration, or Production Systems.
data-science-expert
Expert-level data science, analytics, visualization, and statistical modeling. Use when the user mentions analytics, visualization, statistics, pandas, or NumPy, or when the task involves Data Analysis, Machine Learning, Data Visualization, or Feature Engineering.
api-design-expert
Expert-level API design principles, REST, GraphQL, versioning, and API best practices. Use when the user mentions REST, GraphQL, API versioning, or API security, or when the task involves API Design Principles, API Styles, or Documentation.