Arya Model Router

Router that selects between cheap, default, and pro GPT models to save tokens, using sub-agents and optional briefing for heavy tasks.

This skill appears to be a straightforward local model router: it reads rules.json and state.json and prints a JSON decision; it does not call external services or request secrets. Before installing, consider: 1) confirm the small metadata mismatch (SKILL.md declares bash + python3) and ensure python3 is available; 2) note the skill will write state.json inside the skill folder so feedback commands persist and slightly auto-tune thresholds over time; 3) the router only 'suggests' spawning sub-agents — make sure your agent's sessions_spawn or sub-agent mechanism enforces your privacy and does not send sensitive context to external models/services you don't control. If you are comfortable with those points, the skill is coherent and low-risk.

Type: OpenClaw Skill Name: staratheris-arya-model-router Version: 0.1.0 The OpenClaw skill bundle 'arya-model-router' is classified as benign. The `router.py` script locally processes user input and configuration (`rules.json`, `state.json`) to decide on a model level, without making external network calls or executing arbitrary commands. The `brief.py` script is a local, offline text processing utility for context summarization. Neither `SKILL.md` nor `README.md` contain any prompt injection attempts to manipulate the agent into malicious actions; they provide clear usage instructions. All file operations are confined to the skill's own directory, and there is no evidence of data exfiltration, malicious execution, persistence mechanisms, or obfuscation.