Efficiently routes tasks between cheap, default, and pro models using optional sub-agents and briefing to minimize token use and cost.

This skill appears to be what it says: a local router that decides when to escalate to stronger models. Before installing, consider: 1) It writes rules.json and state.json in the skill folder — review and back up those files if you edit them. 2) brief.py will surface URLs, job IDs, errors and similar 'interesting' lines; do not pass sensitive tokens/credentials in context you expect to be briefed and potentially forwarded to an external model. 3) The router only emits decisions (model names like openai/gpt-4.1); actual calls to remote LLMs happen elsewhere — ensure any downstream integration that executes 'use_subagent' is authorized and has appropriate API keys and data-handling policies. 4) Ensure python3 is available (SKILL.md lists bash and python3). 5) Optionally review and customize rules.json thresholds/keywords to match your workload and to avoid unnecessary escalation. If you want a second check, provide how your agent invokes sub-agents (what component accepts 'use_subagent' and whether it will send briefs to remote models).

Type: OpenClaw Skill Name: arya-model-router Version: 0.1.0 The skill bundle is benign. All Python scripts (`brief.py`, `router.py`) operate locally, process text input, and manage configuration/state files (`rules.json`, `state.json`) within the skill's directory. There is no evidence of data exfiltration, malicious execution (e.g., `curl|bash`, remote payloads, `eval/exec` of untrusted input), persistence mechanisms, or obfuscation. The `SKILL.md` and `README.md` files provide instructions for the agent on how to use the skill and interpret its JSON output, including suggesting the execution of the local `brief.py` script or the agent's `sessions_spawn` capability, all of which are aligned with the stated purpose of model routing and token saving without any malicious prompt injection attempts.