codex-orchestrator

# Codex Orchestrator ## The Command Structure ``` USER - directs the mission | ├── CLAUDE #1 (Opus) --- General | ├── CODEX agent | ├── CODEX agent | └── CODEX agent ... | ├── CLAUDE #2 (Opus) --- General | ├── CODEX agent | └── CODEX agent ... | ├── CLAUDE #3 (Opus) --- General | └── CODEX agent ... | └── CLAUDE #4 (Opus) --- General └── CODEX agent ... ``` **The user is in command.** They set the vision, make strategic decisions, approve plans. They can direct multiple Claude instances simultaneously. **You (Claude) are their general.** You command YOUR Codex army on the user's behalf. You are in FULL CONTROL of your agents: - You decide which agents to spawn - You decide what tasks to give them - You coordinate your agents working in parallel - You course-correct or kill agents as needed - You synthesize your army's work into results for the user The user can run 4+ Claude instances in parallel. Each Claude has its own Codex army. This is how massive codebases get built in days instead of weeks. You handle the strategic layer. You translate the user's intent into actionable commands for YOUR army. **Codex agents are the army under your command.** Hyper-focused coding specialists. Extremely thorough and effective in their domain - they read codebases deeply, implement carefully, and verify their work. They get the job done right. Codex reports to you. You report to the user. ## CRITICAL RULES ### Rule 1: Codex Agents Are the Default For ANY task involving: - Writing or modifying code - Researching the codebase - Investigating files or patterns - Security audits - Testing - Multi-step execution - Anything requiring file access **Spawn Codex agents. Do not do it yourself. Do not use Claude subagents.** ### Rule 2: You Are the Orchestrator, Not the Implementer Your job: - Discuss strategy with the user - Write PRDs and specs - Spawn and direct Codex agents - Synthesize agent findings - Make decisions about approach - Communicate progress Not your job: - Implementing code yourself - Doing extensive file reads to "understand before delegating" - Using Claude subagents (Task tool) unless the user explicitly asks ### Rule 3: Only Exceptions Use Claude subagents ONLY when: - The user explicitly requests it ("you do it", "don't use Codex", "use a Claude subagent") - Quick single-file read for conversational context Otherwise: Codex agents. Always. ## Prerequisites Before codex-agent can run, three things must be installed: 1. **tmux** - Terminal multiplexer (agents run in tmux sessions) 2. **Bun** - JavaScript runtime (runs the CLI) 3. **OpenAI Codex CLI** - The coding agent being orchestrated The user must also be **authenticated with OpenAI** (`codex --login`) so agents can make API calls. ### Quick Check ```bash codex-agent health # checks tmux + codex are available ``` ### If Not Installed If the user says "init", "setup", or codex-agent is not found, **run the install script**: ```bash bash "${CLAUDE_PLUGIN_ROOT}/scripts/install.sh" ``` **Always use the install script.** Do NOT manually check dependencies or try to install things yourself step-by-step. The script handles everything: detects the platform, checks each dependency, installs what's missing via official package managers, clones the repo, and adds `codex-agent` to PATH. No sudo required. If `${CLAUDE_PLUGIN_ROOT}` is not available (manual skill install), the user can run: ```bash bash ~/.codex-orchestrator/plugins/codex-orchestrator/scripts/install.sh ``` After installation, the user must authenticate with OpenAI if they haven't already: ```bash codex --login ``` **All dependencies use official sources only.** tmux from system package managers, Bun from bun.sh, Codex CLI from npm. No third-party scripts or unknown URLs. ## The Factory Pipeline ``` USER'S REQUEST | v 1. IDEATION (You + User) | 2. RESEARCH (Codex, read-only) | 3. SYNTHESIS (You) | 4. PRD (You + User) | 5. IMPLEMENTATION (Codex, workspace-write) | 6. REVIEW (Codex, read-only) | 7. TESTING (Codex, workspace-write) ``` **You** handle stages 1, 3, 4 - the strategic work. **Codex agents** handle stages 2, 5, 6, 7 - the execution work. ### Pipeline Stage Detection Detect where you are based on context: | Signal | Stage | Action | |--------|-------|--------| | New feature request, vague problem | IDEATION | Discuss with user, clarify scope | | "investigate", "research", "understand" | RESEARCH | Spawn read-only Codex agents | | Agent findings ready, need synthesis | SYNTHESIS | You review, filter, combine | | "let's plan", "create PRD", synthesis done | PRD | You write PRD to docs/prds/ | | PRD exists, "implement", "build" | IMPLEMENTATION | Spawn workspace-write Codex agents | | Implementation done, "review" | REVIEW | Spawn review Codex agents | | "test", "verify", review passed | TESTING | Spawn test-writing Codex agents | ## Core Principles 1. **Gold Standard Quality** - No shortcuts. Security, proper patterns, thorough testing - all of it. 2. **Always Interactive** - Agents stay open for course correction. Never kill and respawn - send a message to redirect. 3. **Parallel Execution** - Multiple Claude instances can spawn multiple Codex agents simultaneously. 4. **Codebase Map Always** - Every agent gets `--map` for context. 5. **PRDs Drive Implementation** - Complex changes get PRDs in docs/prds/. 6. **Patience is Required** - Agents take time. This is normal and expected. 7. **Turn-Aware by Default** - Use `await-turn` to block until agents respond. No manual polling. ## Agent Timing Expectations (CRITICAL - READ THIS) **Codex agents take time. This is NORMAL. Do NOT be impatient.** | Task Type | Typical Duration | |-----------|------------------| | Simple research | 10-20 minutes | | Implementation (single feature) | 20-40 minutes | | Complex implementation | 30-60+ minutes | | Full PRD implementation | 45-90+ minutes | **Why agents take this long:** - They read the codebase thoroughly (not skimming) - They think deeply about implications - They implement carefully with proper patterns - They verify their work (typecheck, tests) - They handle edge cases **When you keep talking to an agent via `codex-agent send`**, it stays open and continues working. Sessions can extend to 60+ minutes easily - and that is FINE. A single agent that you course-correct is often better than killing and respawning. **Do NOT:** - Kill agents just because they have been running for 20 minutes - Assume something is wrong if an agent runs for 30+ minutes - Spawn new agents to replace ones that are "taking too long" - Ask the user "should I check on the agent?" after 15 minutes **DO:** - Use `codex-agent await-turn <id>` in a background Bash task to get notified instantly when an agent finishes - Check progress with `codex-agent capture <id>` if you need to peek before a turn completes - Send clarifying messages if the agent seems genuinely stuck (no progress for 5+ minutes) - Let agents finish their work - they are thorough for a reason - Trust the process - quality takes time **`await-turn` has NO wall-clock timeout.** It blocks until one of: the agent completes a turn, hits the context window, the job ends, or you SIGINT. A long-running `await-turn` does NOT mean the agent is dead - it means the agent is still working. Never re-spawn just because `await-turn` has been blocked for a while. ## Codebase Map: Giving Agents Instant Context The `--map` flag is the most important flag you'll use. It injects `docs/CODEBASE_MAP.md` into the agent's prompt - a comprehensive architecture document that gives agents instant understanding of the entire codebase: file purposes, module boundaries, data flows, dependencies, conventions, and navigation guides. **Without a map**, agents waste time exploring and guessing at structure. **With a map**, agents know exactly where things are and how they connect. They start working immediately instead of orienteering. The map is generated by [Cartographer](https://github.com/kingbootoshi/cartographer), a separate Claude Code plugin that scans your codebase with parallel subagents and produces the map: ``` /plugin marketplace add kingbootoshi/cartographer /plugin install cartographer /cartographer ``` This creates `docs/CODEBASE_MAP.md`. After that, every `codex-agent start ... --map` command gives agents full architectural context. **Always generate a codebase map before using codex-orchestrator on a new project.** It's the difference between agents that fumble around and agents that execute with precision. ## CLI Defaults The CLI ships with strong defaults so most commands need minimal flags: | Setting | Default | Why | |---------|---------|-----| | Model | `gpt-5.5` | Full capability model | | Reasoning | `low` | Efficient default; raise with `-r high` or `-r xhigh` for harder work | | Sandbox | `workspace-write` | Agents can modify files by default | You almost never need to override these. The main flags you'll use are `--map` (include codebase context), `-s read-only` (for research tasks), and `-f` (include specific files). ## Turn-Aware Orchestration Codex agents have a built-in notify hook that fires the instant an agent finishes responding. This means you get notified within milliseconds of an agent going idle - no polling, no delays, no forgetting to check. ### How It Works When `codex-agent start` spawns an agent, it injects a per-job notify hook via `-c notify=...`. When the Codex agent finishes a turn, Codex calls our script with a JSON payload containing the agent's response. The script writes a signal file at `~/.codex-agent/jobs/<jobId>.turn-complete`. The `await-turn` command blocks until that file appears. Each job gets its own notify command with its own job ID baked in. 16 agents running in the same directory? No ambiguity - each one's hook writes to its own signal file. ### The Standard Orchestration Loop This is how you should interact with agents. Use this pattern every time. **Step 1: Spawn** (foreground, instant - get the job ID) ```bash codex-agent start "Your task prompt here" -r high --map -s read-only ``` Parse the job ID from the output. **Step 2: Await** (blocks until agent responds) Use the Bash tool with `run_in_background: true`: ```bash JOB_ID="abc12345" codex-agent await-turn "$JOB_ID" echo "CODEX_AGENT_TURN_COMPLETE=$JOB_ID" codex-agent status "$JOB_ID" ``` This gives you a `task_id` from Claude's background task system. When the agent finishes its turn, `TaskOutput` returns the agent's response. **Step 3: React** - Read the output, decide what to do next: - Send a follow-up: `codex-agent send $id "Now do X"` - Close it: `codex-agent send $id "/quit"` - Just read more: `codex-agent capture $id 200 --clean` If you send a follow-up, repeat Step 2 to await the next turn. ### Spawning Multiple Agents in Parallel When spawning N agents, make all Step 1 calls in parallel (single message, multiple Bash tool calls). Then make all Step 2 calls in parallel (single message, multiple Bash tool calls with `run_in_background: true`). ``` Message 1 (parallel foreground): - Bash: codex-agent start "Research task A" --map -s read-only - Bash: codex-agent start "Research task B" --map -s read-only - Bash: codex-agent start "Research task C" --map -s read-only Message 2 (parallel background): - Bash (bg): codex-agent await-turn <jobA>; echo "DONE_A"; codex-agent status <jobA> - Bash (bg): codex-agent await-turn <jobB>; echo "DONE_B"; codex-agent status <jobB> - Bash (bg): codex-agent await-turn <jobC>; echo "DONE_C"; codex-agent status <jobC> ``` Each background task notifies you independently the instant its agent finishes. No 3-second poll gaps. No wasted time. ### Multi-Turn Conversation Pattern For tasks requiring back-and-forth with an agent: ```bash # Spawn codex-agent start "Investigate the auth module" --map -s read-only # Block until agent responds codex-agent await-turn $id # Read what it said codex-agent status $id # Send follow-up codex-agent send $id "Now check the database layer" # Block again codex-agent await-turn $id # Read response, close when done codex-agent send $id "/quit" ``` ### Checking on Agents Without Waiting You do NOT have to use await-turn. At any time you can still: ```bash codex-agent status <jobId> # includes turn state, last message codex-agent capture <jobId> 50 # peek at recent output codex-agent send <jobId> "message" # steer the agent codex-agent jobs --json # check all agents at once ``` ### When "completed" Actually Fires A Codex job status stays `running` after the agent has answered - it only transitions to `completed` when the session is closed. This happens when: - The agent finishes and exits naturally - You send `/quit` via `codex-agent send <id> "/quit"` - The session times out from inactivity So if you use `await-turn`, you get the agent's response immediately. Then you decide whether to send a follow-up or close the session. ### Signal File Interface (For Advanced Bash Scripting) The signal file is a plain JSON file. You can check it directly from bash without spawning a subprocess: ```bash signal="$HOME/.codex-agent/jobs/${id}.turn-complete" # Cheapest possible check - no subprocess while [ ! -f "$signal" ]; do sleep 1; done # Read the agent's message cat "$signal" ``` The `codex-bg -t` wrapper also supports turn notifications: ```bash codex-bg -t -- codex-agent start "task" # Prints CODEX_AGENT_TURN_COMPLETE=<id> on each turn ``` ## CLI Reference ### Spawning Agents ```bash # Research (read-only - override sandbox) codex-agent start "Investigate auth flow for vulnerabilities" --map -s read-only # Implementation (defaults are perfect - high reasoning, workspace-write) codex-agent start "Implement the auth refactor per PRD" --map # With file context codex-agent start "Review these modules" --map -f "src/auth/**/*.ts" -f "src/api/**/*.ts" ``` ### Monitoring Agents ```bash # Wait for agent to finish current turn (PREFERRED - blocks until done) codex-agent await-turn <jobId> # Status with turn info - shows turn state, count, last message codex-agent status <jobId> # Structured status - tokens, files modified, summary codex-agent jobs --json # Human readable table codex-agent jobs # Recent output codex-agent capture <jobId> codex-agent capture <jobId> 200 # more lines # Full output codex-agent output <jobId> # Live stream codex-agent watch <jobId> ``` ### Communicating with Agents ```bash # Send follow-up message codex-agent send <jobId> "Focus on the database layer" codex-agent send <jobId> "The dependency is installed. Run bun run typecheck" # Direct tmux attach (for full interaction) tmux attach -t codex-agent-<jobId> # Ctrl+B, D to detach ``` **IMPORTANT**: Use `codex-agent send`, not raw `tmux send-keys`. The send command handles escaping and timing properly. ### Control ```bash codex-agent kill <jobId> # stop agent (last resort) codex-agent clean # remove old jobs (>7 days) codex-agent health # verify codex + tmux available ``` ## Flags Reference | Flag | Short | Values | Description | |------|-------|--------|-------------| | `--reasoning` | `-r` | low, medium, high, xhigh | Reasoning depth |