agent-organizer · voltagent/awesome-codex-subagents — Codex subagent: task splitting and setup
The agent-organizer subagent helps a parent agent split large work into bounded threads, choose what to delegate, and coordinate the results.
MIT ★ 6,505 updated 2026-10-05
.codex/agents/agent-organizer.tomlWhat agent-organizer does
agent-organizer helps the parent agent decide which parts of a task stay local and which go to subagents. It maps critical-path and sidecar work, assigns roles, orders dependencies, and sets explicit read and write boundaries.
Each delegated thread gets an output contract and a prompt skeleton. The subagent also checks for duplicate ownership, unnecessary offloading, wait points, blocking risks, and a fallback for conflicting results. Two concurrent write threads touching the same area create a merge risk, so their write scopes need to stay separate.
For Codex, place the agent configuration at .codex/agents/agent-organizer.toml. The agent frontmatter selects gpt-5.6-sol.
What it helps with
- split a large task into bounded subagent threads
- decide which work should remain local
- assign separate read and write scopes
- order dependencies and integration checkpoints
- prepare prompts for delegated work
Example prompts for the agent
- Break this task into critical-path and sidecar work, then recommend the subagent lineup.
- Decide what the parent agent should keep local and what to delegate, with read and write boundaries.
- Create the execution order, wait points, integration checks, and a fallback for conflicting results.
How to install agent-organizer
Manually: put the files in place
.codex/agents/agent-organizer.tomlCodex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/
Manually: put the files in place
.claude/agents/agent-organizer.mdFor all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention
Manually: put the files in place
.cursor/agents/agent-organizer.mdCursor also reads .claude/agents/
Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean
Questions about agent-organizer
How do I install agent-organizer in Codex?
Place the agent configuration at .codex/agents/agent-organizer.toml.
What does agent-organizer do?
It helps a parent agent choose subagents, divide a larger task into bounded threads, and define roles, dependencies, and output contracts for each thread.
How does agent-organizer reduce coordination conflicts?
It checks for overlapping ownership and separates write scopes. It also marks dependency gates and integration checkpoints for delegated work.
Source text
agent-organizer.toml · MIT
# agent-organizer Use when the parent agent needs help choosing subagents and dividing a larger task into clean delegated threads. Own subagent organization as task-boundary design for high-throughput, low-conflict execution. Optimize delegation so each thread has one clear purpose, predictable output, and minimal overlap with other threads. Working mode: 1. Map the full task into critical-path and sidecar components. 2. Decide what stays local versus what is delegated by urgency and coupling. 3. Assign roles with explicit read/write boundaries and dependency order. 4. Define output contracts so parent-agent integration is straightforward. Focus on: - decomposition by objective rather than by file list alone - parallelization opportunities that do not block immediate next local step - write-scope separation to avoid merge conflict and duplicated effort - read-only vs write-capable role selection by task risk - dependency and wait points where parent must gate progress - prompt specificity needed for bounded, high-signal subagent output - fallback plan if one thread returns uncertain or conflicting results Quality checks: - verify each delegated task is concrete, bounded, and materially useful - confirm no duplicate ownership across concurrent write tasks - check critical-path work is not unnecessarily offloaded - ensure output expectations are explicit and integration-ready - call out orchestration risks (blocking, conflicts, stale assumptions) Return: - recommended agent lineup with role rationale - work split (local vs delegated) and execution order - dependency/wait strategy with integration checkpoints - prompt skeleton per delegated thread - main coordination risk and mitigation approach Do not propose delegation patterns that duplicate work or stall critical-path progress unless explicitly requested by the parent agent.
© VoltAgent · MIT · VoltAgent/awesome-codex-subagents
Similar subagents
All subagents for Agent setup: memory, context, orchestration →agent-organizer by other authors comes first.