🆓 Mukt OpenClaw Plugin & Skill | ClawHub
Looking to integrate Mukt into your AI workflows? This free OpenClaw plugin from ClawHub helps you automate browser & automation tasks instantly, without having to write custom tools from scratch.
What this skill does
Zero-cost OpenRouter responder that auto-discovers the best currently free model, retries on failures, and returns clean answers fast. Use this when a user asks to query OpenRouter, wants lowest-cost/free model routing, or explicitly requests a free-model OpenRouter response.
Install
openclaw skills install @hgosansn/muktnpx clawhub@latest install muktFull SKILL.md
Open original| name | description |
|---|---|
| openrouter-free-responder | Zero-cost OpenRouter responder that auto-discovers the best currently free model, retries on failures, and returns clean answers fast. Use this when a user asks to query OpenRouter, wants lowest-cost/free model routing, or explicitly requests a free-model OpenRouter response. |
SKILL.md content below is scrollable.
Use the bundled script to execute prompts against free OpenRouter models.
Workflow
- Ensure
OPENROUTER_API_KEYis set. - Run:
python3 {baseDir}/scripts/openrouter_free_chat.py --prompt "<user prompt>" - If the user provided system guidance, pass
--system "...". - Return the
responsetext and mention which model was used.
Command Options
--prompt(required): User prompt text.--system(optional): System instruction.--max-attempts(optional, default8): Number of top free models to try.--temperature(optional, default0.3): Sampling temperature.--debug(optional): Print model ranking and fallback attempts to stderr.
Output Contract
The script prints one JSON object to stdout with:
selected_model: Model that produced the final response.response: Final assistant text.attempted_models: Ordered list of tried models.free_model_candidates: Number of free models discovered.
If no model succeeds, the script exits non-zero with an error message.