Recipes / Dev & code
Multi-agentWorkflowDev & code

Claude Code ↔ Codex hand-off with a shared changes.log

Two agents pass one project back and forth through a single log file each must read before starting and append to after finishing, so the second agent can review the first.

Setup time15 min
CostTwo subscriptions
RunsPer hand-off
NeedsClaude Code, Codex, git
Last updated2026-10-15
SubstackSource

I Used Claude Code And Codex Together, Here’s What Surprised Me

by Wyndo and Dheeraj Sharma · 2026-06-14

✓ Opened with WebFetch on 2026-10-15

Read the original ↗
Part 1 · What the source did

Two agents pass one project back and forth through a single log file each must read before starting and append to after finishing, so the second agent can review the first.

  • Created changes.log that both tools read first and update last.
  • Kept Claude's rules in CLAUDE.md; Codex imported them into AGENTS.md.
  • Ran a live round trip on a small calculator: Claude added a breakdown, Codex turned it into a chart and checked it in the browser, Claude then rebranded it.
“It gives the next agent something to judge.”— Wyndo and Dheeraj Sharma, Substack

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

Before you start: read the LAST entry of changes.log and restate in one line what you're picking up. When you finish, append an entry to changes.log: [YYYY-MM-DD HH:MM] [AGENT NAME] [TASK ID] Status: DONE | PARTIAL | BLOCKED What changed and why: Files touched: Unfinished: Don't undo: Next agent should: (one concrete next step + the command that proves it works) Also review the previous agent's work and list anything you'd push back on.
🛡
Approval ruleNeither agent merges or deploys. You approve each hand-off after reading the new log entry.

Set it up

  1. Pick a low-risk repo both tools can open.
  2. Add changes.log and paste the block above into both CLAUDE.md and AGENTS.md (or import one from the other).
  3. Run one small round trip: agent A builds, agent B reviews and improves, agent A picks back up.
  4. Read each entry before approving the next run.

Common failures

⚠
What usually goes wrong
  • Both agents run at once and overwrite each other's entries. Hand off sequentially or use separate branches.
  • Vague entries ('fixed stuff') give the next agent nothing to judge.
  • Rules drift when CLAUDE.md and AGENTS.md diverge; keep one source and import it.

Variations

  • Swap direction: Codex drafts, Claude Code wires it in.
  • Add a 'reviewer findings' section to every entry.

Related recipes