Power user pipes Claude Code plan mode into Codex for cross-review, iterating up to 10 rounds
mikegiannulis · x · 2026-09-24
Reacting to a question about killing plan mode in Claude Code, user mikegiannulis shared his workflow: generate the plan in plan mode, then submit it via CLI tools and webhooks to Codex for a second review that catches bugs and issues.
Claude and Codex iterate back and forth on the plan until it's accepted — sometimes taking up to 10 rounds. A two-model cross-review setup that filters out design flaws before any code gets written.
More from coding & agent
- Stripe launches claimable sandboxes: frictionless payment integrations for AI agents — jeff_weinstein · 2026-11-12
- Databricks launches autonomous AI coworker Genie: 91% on enterprise tasks with half the tokens — Yuchenj_UW · 2026-11-12
- Loom founder launches Roma 2.0, a shared to-do list that orchestrates AI agents — thetripathi58 · 2026-11-12
- Developer proposes a 'blast radius' test for AI agents before building — Few-Garlic2725 · 2026-11-12
- Sosumi Eval: Apple Docs Access Lifts Coding Agent Pass Rates from ~33% to 94-98% — JordanMorgan10 · 2026-11-12
- CypherGuard fixes structurally wrong LLM Cypher queries, hitting 88.5% on CypherBench — JeremyCMorgan · 2026-11-12