Model Cost Advisor

Analyze any task and recommend the most cost-effective LLM — with live pricing data from 30+ models, tier analysis, token estimation, and projected cost. Per...

This skill appears to do what it claims: it downloads a community-maintained pricing JSON from GitHub and caches it in ~/.hermes, then analyzes task text locally to recommend models. Before installing/run: (1) verify you trust the litellm source (the script fetches raw.githubusercontent.com/BerriAI/litellm/...); (2) review the cached file (~/.hermes/model_pricing.json) if you want to inspect the data before use; (3) if you prefer no persistent files, run the scripts in a disposable environment or delete the ~/.hermes directory after use; (4) be aware it may optionally read HERMES_CURRENT_MODEL for comparison — set that only if you intend to share your current model. No credentials are required by the skill.

Type: OpenClaw Skill Name: model-cost-advisor Version: 1.0.0 The model-cost-advisor skill is a legitimate utility designed to help users estimate LLM costs by analyzing task complexity and fetching live pricing data from the LiteLLM GitHub repository. The scripts (advise.py and fetch_pricing.py) perform keyword-based analysis and standard HTTP requests to update a local cache in ~/.hermes/, with no evidence of data exfiltration, unauthorized command execution, or malicious prompt injection. While the documentation and code reference future-dated model versions (e.g., Claude 4.7), this appears to be speculative or synthetic data for demonstration purposes rather than a security risk.