The Delegate Pattern: Run Claude Code + Codex + Gemini in Parallel — Zero-Cost Rate Limit Bypass for Multi-Agent AI

A developer known as Lux created the 'delegate pattern' to bypass AI rate limits by running Claude Code, Codex CLI, and Gemini CLI in parallel, using Obsidian Markdown files as an asynchronous communication channel. The approach eliminates single-vendor dependency and context pollution by having child agents return results as files, which the parent agent synthesizes upon completion notifications.

The motivation was simple: AI stops. Frequently. When running large tasks with Claude Code, you hit Anthropic's rate limits fast. When you add more sub-agents to run in parallel, Claude's own context gets polluted and performance degrades. I also tried a real-time message bus agmsg . Multiple CLI windows throwing messages caused confusion. SSE connections dropped, losing notifications. Infrastructure maintenance cost was too high. Then it hit me: concentrating everything in one AI vendor is itself the problem. Claude Anthropic , Codex OpenAI , and AGY/Gemini Google each have independent APIs and rate limit pools. Run them in parallel, and when one hits its limit, the others keep going. Use files as the communication channel, and there's no confusion or disconnection. This is the delegate pattern . Single-vendor dependency means hitting ceilings fast. The delegate pattern uses 3 independent API pools, dramatically increasing effective throughput. Dumping all research logs and code output into the parent agent's context makes it forget earlier instructions. In the delegate pattern, child agents run in separate processes and return only their results as files. When you call codex exec / agy --prompt via Bash, Claude Code recognizes them as sub-agents. Claude Code's built-in completion notification infrastructure handles everything automatically — no Monitor tool or custom polling loops needed. Lux / Claude Code parent · orchestrator ├─ Bash → Codex CLI → Tasks/codex xxx.md → Reports/codex xxx.md └─ Bash → Gemini CLI → Tasks/agy xxx.md → Reports/agy xxx.md ↓ Completion notification → Lux reads all results and synthesizes Why Obsidian as the communication channel: | Tool | Role | How to get | |---|---|---| Claude Code | Parent · orchestrator | claude.ai/code | Obsidian | Communication channel · persistent log | obsidian.md free | Codex CLI | Child agent A OpenAI | npm install -g @openai/codex → codex login | AGY / Gemini CLI | Child agent B Google | npm install -g @google/gemini-cli → agy login | Note:Codex requires an OpenAI paid plan. AGY requires a Gemini subscription + CLI install + login no API key needed . Once you're set up, just tell Claude Code: Create a skill called "delegate". Role: I Lux am the parent, Codex CLI and AGY CLI are the children. Tasks are passed via Obsidian Markdown files. Include fire command templates and save to .claude/skills/delegate.md Claude will interactively create the skill file for you. Copy the skill file directly from the repository: git clone https://github.com/melt1007/claude-delegate-pattern.git cp claude-delegate-pattern/skills/delegate.md ~/.claude/skills/ After copying, tell Claude Code "read the delegate skill" and it will be recognized. Write instructions for each agent in separate files: Codex Research Task Objective What you want researched Output destination Obsidian/Reports/codex result 20260726.md Constraints - Read only: this task file and the specified folder - Output: write conclusions, reasoning, and steps separately Tell Claude Code "delegate and summon" and the skill automatically runs: Launch Codex in background codex exec "Read Tasks/task codex.md and write results back" \ --dangerously-bypass-approvals-and-sandbox \ -o "codex out.txt" Launch AGY simultaneously agy --prompt "Read Tasks/task agy.md and do the work" \ --dangerously-skip-permissions Both start in parallel. Claude Code can respond to your next instruction while waiting for completion. When a child agent completes, Claude Code receives a notification. It reads each report file and synthesizes the results. | Criterion | agmsg real-time bus | delegate pattern file-based async | |---|---|---| Reliability | SSE connection errors · complex disconnect handling | File I/O only · simple and robust | Message conflicts | Timing coordination is hard, conflicts happen | Physically separated · zero conflicts | Log persistence | Depends on memory · volatile | Persisted in Obsidian · always accessible | Implementation cost | High bus config · state management required | Low only file ops and CLI calls | Best for | Low-latency interactive processing | "Request → deliverable" tasks: research, implementation, review | The delegate pattern in one sentence: "Run AIs from different companies in parallel and connect them via Obsidian." This alone solves all three problems simultaneously: rate limit distribution, context pollution prevention, and reliable completion notifications. What you need: ✅ Claude Code free tier available ✅ Obsidian free ✅ Codex CLI OpenAI paid plan ✅ AGY / Gemini CLI Google AI Studio ✅ delegate.md get from repo or have Claude create it Simple mechanism. Most reliable and scalable multi-agent approach I've found. Repository skill file · task templates : 👉 https://github.com/melt1007/claude-delegate-pattern https://github.com/melt1007/claude-delegate-pattern This article was written using the delegate pattern itself. Claude Code Lux acted as orchestrator, generating 3 drafts in parallel — Codex, AGY, and Lux — then synthesizing them into this final version.