Running multiple CLI coding agents: plan together, argue when needed, works with any official harness
wavefnx · x · 2026-10-16
Developer wavefnx shares his hands-on recipe for orchestrating multiple CLI coding agents: instruct them to plan together and argue with each other when needed, so they follow specific commands and don't drift from the main goal.
- Works with any number of CLIs, but he warns to be careful sending messages to CLIs you don't trust.
- His point isn't building your own API harness (he already has one), but that this works out of the box with any official harness, with no changes, at any time.
- The thread also includes a screenshot of an agent randomly "getting all philosophical," which he mocks.
Related event: Developer Builds SMS Messaging System for Opus-Codex Agent Collaboration(4 posts)→
More from coding & agent
- Deep Research API showdown: OpenAI, Perplexity, Parallel, Tavily, Gemini, Valyu compared — bar_raiser333 · 2026-10-16
- Geoffrey Huntley open-sources Overalls, a self-hosted AI developer platform under MIT — kieranklaassen · 2026-10-16
- Dev shows 199.7bn tokens over 200 days on OpenAI Codex, peak 8.6bn/day — Dimillian · 2026-10-16
- Ask Claude to open its changes in nvim and scroll to the exact line for review — max__drake · 2026-10-16
- Proof CEO on x401: KYC-compatible agent identity using NIST IAL2 verifiable credentials, composing with x402 payments — csuwildcat · 2026-10-16
- Pydantic's HTTPX2 adds native WebSocket and SSE support — samuelcolvin · 2026-10-16