- Step-by-step setup guide (RouterAI key, local Gemma)
- Agent integration checklist with pseudo-code
- What to ask the user and how to store config
- What happens when each backend is missing
- Two backends: RouterAI (gpt-4o-mini) + LocalGemma (Jan API)
- Smart emoji routing (🌶️/🔞/🤫 → local Gemma, NSFW never hits cloud)
- argparse with --help, --local, --model, --prompt
- ImagePreprocessor with ffmpeg resize
- ProxyHandler({}) for local server bypass
- logging, try/finally cleanup, HTTPError/URLError handling
- Zero shell injection, zero keys in /tmp
- SKILL.md with full documentation for other agents