Route every substantive user request to the optimal LLM model. Trigger on EVERY substantive request. Score across 12 dimensions, pick the best model, switch...

This skill appears to do what it says: it scores messages and recommends a model, reading ~/.openclaw/openclaw.json to see which models are available. Before installing: - Run the provided --setup once and inspect the generated models.json and models database (capabilities_defaults.json) so automatic switching uses sensible defaults for your environment. If you don't configure models, the router intentionally returns fallback/default and will not switch. - Be aware the router executes on every substantive request (it will run the bundled Python script), which can add latency; test in a safe environment first. - The README suggests adding a note to AGENTS.md to reinforce agent compliance — avoid making the agent override other safety controls just to satisfy the skill. Only add such enforcement if you trust the skill and your agent's policy setup. - Confirm that ~/.openclaw/openclaw.json contains the model IDs you expect; the router filters out models not present there, which may cause no candidates if your config differs from the skill's database. No scan alerts were found in the supplied bundle, and no unrelated credentials or network endpoints are present in the code. If you want higher assurance, run the script locally and review its output on representative prompts before enabling automatic routing.

Type: OpenClaw Skill Name: model-router-pro Version: 1.1.0 The 'model-router-pro' skill is a legitimate utility designed to optimize LLM usage by routing tasks to models based on a 12-dimension complexity analysis. It includes a setup script (`router.py`) that reads the local OpenClaw configuration (`~/.openclaw/openclaw.json`) to identify available models, a process that is transparently declared in `SKILL.md`. The bundle relies solely on the Python standard library, performs no network operations, and shows no signs of malicious intent or data exfiltration.