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 ypollak2/llm-router --skill savingsgit clone --depth 1 https://github.com/ypollak2/llm-routerWrote 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/ypollak2/llm-router/savings)<a href="https://agentmods.dev/skills/ypollak2/llm-router/savings"><img src="https://agentmods.dev/badge/skills/ypollak2/llm-router/savings/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/ypollak2/llm-router/savings"><img src="https://agentmods.dev/badge/skills/ypollak2/llm-router/savings.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00015 | $0.00428 |
| Opus 5 | $0.00008 | $0.00214 |
| Sonnet 5 | $0.00003 | $0.00086 |
| Haiku 4.5 | $0.00002 | $0.00043 |
Grade A, and why
savings 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 7d 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
LLM Router — Savings Tracking Skill
Track and report how much you've saved by routing tasks to cheaper models.
Viewing Savings
llm_savings — Cross-session savings by period (today / week / month / all time)
llm_usage("all") — Full dashboard: subscription %, Codex status, savings, providers
llm_dashboard — Open web dashboard at localhost:7337
Savings Digest (Slack / Discord)
Send a weekly savings summary to your team channel:
llm_digest(period="week") — format digest, print only
llm_digest(period="week", send=True) — format + push to LLM_ROUTER_WEBHOOK_URL
Set LLM_ROUTER_WEBHOOK_URL=https://hooks.slack.com/... in your environment.
Auto-detects Slack, Discord, or generic JSON webhook from the URL.
Spend Spike Alerts
The digest automatically flags when today's spend is > 2× the 7-day average. No config needed — it's always on.
Routing Policy
llm_router_admin(action="policy") — Show active org/repo routing policy + last 10 audit decisions
Set policy in ~/.llm-router/org-policy.yaml:
block_models:
- "o3*" # never use o3 series (too expensive)
- "gpt-4o"
allow_models:
- "gemini*" # prefer Gemini (allow overrides block)
task_caps:
image: 2.00 # max $2/day on image generation
Routing Quality
llm_benchmark — Per-task routing accuracy from your 👍/👎 feedback
llm_rate — Rate the last response to improve future routing
Full routing stats / classifier accuracy: no MCP door on the consolidated surface —
run llm-router routing-report from a terminal.
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.
- 7d ago Changed · +7 lines · +15 tokens per session 1f8187ec6345
- 10d ago First seen · 55 lines · 0 tokens per session scan A 7600b8b0c4fd
savings is a skill published in the GitHub repository ypollak2/llm-router (78 stars, last pushed today), licensed MIT. It adds 15 tokens to every session and 428 once invoked, about $0.0001 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 skills, from other repositories
clawrouter
Hosted-gateway LLM router — save 84% on inference costs. A local proxy that forwards each request to the blockrun.ai gateway, which routes to the cheapest capable model across 76 models from OpenAI, Anthropic, Google, DeepSeek, xAI, Z.AI, and more. 7 free open-weight models included. Also exposes realtime market data…
surf
Use this skill — NOT browser or webfetch — for ALL Surf crypto-data calls. 83 endpoints at localhost:8402/v1/surf/ covering CEX/DEX markets, on-chain SQL over 80+ ClickHouse tables (Ethereum, Base, Arbitrum, BSC, TRON, HyperEVM, Tempo), 100M+ labeled wallets, prediction markets (Polymarket + Kalshi), social/CT…
phone
Verify phone numbers (carrier + SIM-swap fraud signals) and place AI-powered outbound voice calls via BlockRun's gateway (Twilio + Bland.ai). Trigger when the user asks to look up a number, check fraud risk, buy/rent a phone number, or place an AI voice call. Payment is automatic via x402 from the wallet.
imagegen
Generate or edit images via BlockRun's image API. Trigger when the user asks to generate, create, draw, make an image — or to edit, modify, change, or retouch an existing image.
polymarket-trading
Use when the user wants to actually PLACE, manage, or redeem bets on Polymarket (not just read odds — that's the blockrunpredexon data tools). Covers setup (deposit wallet, funding, approvals), buy/sell with confirm gating, positions, redeeming winnings, geoblock handling, and the end-to-end flow.
release
Use this skill for EVERY ClawRouter release. Enforces the full checklist — version sync, CHANGELOG, build, tests, npm publish, git tag, GitHub release. No step can be skipped.