Developer runs a 'ghost' agent to babysit Codex long-running terminal tasks
BLUECOW009 · x · 2026-09-08
A developer shares a lightweight orchestration trick: when running a long Codex session in a new terminal, they spin up a second 'ghost' agent tasked with tracking everything the model says and reporting on it, so they no longer need to watch the session until the task finishes.
More from coding & agent
- Nullheim: an experimental text world built by uncoordinated AI agents — woogal · 2026-09-08
- Dev describes AI-era workflow: spec it, /goal it, repeat until limit resets — tokenbender · 2026-09-08
- WebMCP Is Here: How to Give Browsing Agents Direct Tools on Your Site — localhost9393 · 2026-09-08
- Local MiniMax H3 generates 29 motion clips to build a talking AiTuber avatar — Hailuo_AI · 2026-09-08
- François Fleuret: pre-AI software is awful, coding AI will rebuild what SaaS solves — francoisfleuret · 2026-09-08
- Agent autonomously scrapes and transcribes TikTok, beating anti-bot fingerprinting — gerardsans · 2026-09-08