Task Router Skill
Task Router
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.
Follow the repository instructions for this skill and your agent. Review the files and dependencies before adding it to your workflow.
SkillHub CLI
skillhub install hgosansn/muktInspect the source and compatibility requirements, then follow its installation steps.
Give your agent the source link and ask it to inspect instructions and dependencies before explaining the installation steps.
Use the bundled script to execute prompts against free OpenRouter models.
OPENROUTER_API_KEY is set.python3 {baseDir}/scripts/openrouter_free_chat.py --prompt "<user prompt>"
--system "...".response text and mention which model was used.--prompt (required): User prompt text.--system (optional): System instruction.--max-attempts (optional, default 8): Number of top free models to try.--temperature (optional, default 0.3): Sampling temperature.--debug (optional): Print model ranking and fallback attempts to stderr.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.
These signals come from indexed source analysis and may lag behind changes. Check the current source files.
Use the bundled script to execute prompts against free OpenRouter models.
## Workflow
1. Ensure `OPENROUTER_API_KEY` is set.
2. Run:
```bash
python3 {baseDir}/scripts/openrouter_free_chat.py --prompt "<user prompt>"
```
3. If the user provided system guidance, pass `--system "..."`.
4. Return the `response` text and mention which model was used.
## Command Options
- `--prompt` (required): User prompt text.
- `--system` (optional): System instruction.
- `--max-attempts` (optional, default `8`): Number of top free models to try.
- `--temperature` (optional, default `0.3`): 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.Task Router
Register, communicate, and earn on the x402hub AI agent marketplace. Use when an agent needs to register on x402hub, browse or claim bounties, submit deliverables, send messages to other agents via x402 Relay,...
Real-time event bus for AI agents. Publish, subscribe, and share live signals across a network of agents with Unix-style simplicity.
OpenClaw integration guidance for CAPTCHAS Agent API, including OpenResponses tool schemas and plugin tool registration.