Skip to content
TrustedSkillsbeta
Back to all skills

Iblai Router

Listed
iblai·v1.4.0·ai-ml·MIT

Cost-optimizing model router for OpenClaw. Automatically routes each request to the cheapest capable Claude model (Haiku/Sonnet/Opus) using weighted scoring. Use when setting up smart model routing, reducing API costs, or configuring multi-tier LLM routing. Supports Anthropic models directly and OpenAI/Google models via OpenRouter.

Repository

Install on your platform

Showing OpenClaw.

  1. 1

    Run this in your terminal

    terminal
    $ openclaw skills install iblai-router

What we know about this skill

Publisher

iblai

Taken from the source listing. We haven't verified who controls this account.

Install target

Pinned to 1e75b80b

Installs fetch a stored snapshot of that commit, so the code can't change after the fact.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill failed 2 of 6 checks. A failure is not proof of bad intent; it means something in the code needs a human to look at it before you run it.

  • No undeclared network calls: failed

    Contacts 2 hosts that are neither well-known infrastructure nor declared in the skill's frontmatter: api.moonshot.ai, api.z.ai.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

    Hosts contacted

    127.0.0.1localapi.anthropic.commodel provideropenrouter.aimodel providerapi.z.aiundeclaredapi.moonshot.aiundeclared

    What it found

    • config.json:18contacts api.z.ai
      "baseUrl": "https://api.z.ai/api/anthropic",
    • config.json:24contacts api.moonshot.ai
      "baseUrl": "https://api.moonshot.ai/anthropic",

  • No pipe-to-shell installers: failed

    Runs code fetched at install time in 1 place.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

    What it found

    • README.md:57remote script piped into an interpreter
      curl -s http://127.0.0.1:8402/stats | python3 -m json.tool

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • Pinned to a commit: passed

    Scanned iblai/iblai-openclaw-router at 319b951e6d.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
319b951e6d
Manifest
SKILL.md
Scanned
7 files, 2,239 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

The iblai-router is a Node.js proxy that optimizes costs when using OpenClaw with Anthropic's Claude models. It automatically routes each request to the cheapest Claude model capable of handling it, achieving savings of up to 80% compared to always using the most expensive model like Opus. The router operates locally and does not send data to third parties.

When to use it

  • Routine tasks: Ideal for automating repetitive operations such as inbox checks or operational alerts where cost efficiency is paramount.
  • Subagent workflows: Use it when delegating tasks to subagents, like issue triage or communications, to minimize expenses.
  • Cost-sensitive environments: When operating within a budget and seeking significant reductions in LLM API costs.
  • OpenClaw deployments: Specifically designed for use with OpenClaw agents.

Key capabilities

  • Automatic model routing based on cost optimization.
  • Local operation – no data leaves your server.
  • Compatibility with Anthropic, OpenRouter, and other providers using your API key.
  • Zero dependencies installation process.
  • Excludes system prompts from scoring to ensure accurate cost assessment.

Example prompts

Tips & gotchas

The router scores user messages, not system prompts. Since OpenClaw sends a large, keyword-rich system prompt with every request, scoring it would inflate costs and negate savings; this is why the system prompt is excluded from the routing calculation.