claude-codex-loop: run Claude Code for days with hourly Codex reviews
daniel_mac8 · x · 2026-10-18
- ajogalekar open-sourced claude-codex-loop, a reusable Codex skill: Claude Code executes a milestone, Codex does an hourly heartbeat review, reconciles UI/artifacts/claims/issues, then sends one bounded follow-up prompt — looping until verified success or a stopping condition.
- The design pushes autonomous task duration from minutes/hours to days, combining Claude's capability with Codex's persistence.
- Includes a persistent ledger, configurable criteria and limits, artifact checkpoints; derived from a working convex-hull research workflow. MIT licensed.
Related event: Codex-driven Claude Code workflow goes viral and gets open-sourced(2 posts)→
More from coding & agent
- Visualizing 10K agent trajectories: LLM-labeled treemaps expose classifier disagreements — enjalot · 2026-10-18
- 'Cuck coding': the savage new nickname for just watching AI write your code — petesena · 2026-10-18
- Agent memory's blind spot: lessons learned in one task silently become rules for the next — blaizedsouza · 2026-10-18
- Huashu-motion open-sourced: coding-agent skill makes product launch videos in 30 min for $0.27 — AlchainHust · 2026-10-18
- XERJ open-sourced: index similar GitHub repos before coding, cuts AI tokens by ~62% vs grep — lxfater · 2026-10-18
- Multi-agent coding is 'the greatest slot machine casinos could never match' — theteknosaur · 2026-10-18