DEV CommunitySource
How I Split Work Between Claude Code and Codex in Real Projects
by Sam Lai · 2026-03-22
✓ Opened with WebFetch on 2026-10-15
Read the original ↗Part 1 · What the source did
A backend developer on 20+ microservices routes reasoning-heavy debugging to Claude Code and repetitive, parallel work (tests, docs, edits) to Codex, with a task-state log between them.
- Gave both tools the same exception, code and logs for a legacy production bug; Claude Code traced the root cause.
- Had Codex run tests across modules while the fix wrapped up.
- Kept separate CLAUDE.md and AGENTS.md, plus a CHANGES.log recording status, files, remaining work and next step.
“Claude Code handles understanding. Codex handles execution.”— Sam Lai, DEV Community
Summary written by Agent Cookbook. See the original for the full context.
Part 2 · Our copy-paste version
Adapted by us from what the source described. Fill in the [BRACKETS].
The prompt
ROUTER (decide per task):
- Reasoning-heavy (root cause, business logic, change boundary) -> Claude Code
- Mechanical / parallel (tests, docs, repetitive edits, follow-ups) -> Codex
- Might switch mid-task -> write state to CHANGES.log first
CLAUDE CODE: Here are the exception, the logs and [FILES]. Trace the call chain and explain why it fails in this scenario. Propose the smallest fix and list follow-up work as bullet tasks in CHANGES.log.
CODEX: Read the latest CHANGES.log entry. Implement the listed follow-ups and add tests for [MODULES]. Run them and append Status, Files modified and Tests results.
🛡
Approval ruleYou make the final call when the two agents disagree; neither pushes to shared branches.
Set it up
- Write the router rules at the top of CHANGES.log.
- Start reasoning tasks in Claude Code with tight context: the exception, key logs, the interface.
- Hand mechanical follow-ups to Codex via the log.
- When answers differ, compare reasoning yourself before choosing.
Common failures
⚠
What usually goes wrong
- Dumping whole folders as context makes both tools generic. Keep inputs tight.
- Using the heaviest model for routine work slows everything down.
Variations
- Reverse roles for a week and compare.
- Add a third pass: one agent reviews the other's diff.