task-distributor · voltagent/awesome-codex-subagents — Codex subagent: break tasks into subtasks
task-distributor is a Codex subagent that breaks broad tasks into work units with boundaries, dependencies, and ownership. It divides work across agents without duplication or overlap.
MIT ★ 6,505 updated 2026-10-05
.codex/agents/task-distributor.tomlWhat task-distributor does
task-distributor takes a goal and breaks it into implementation-ready units: who does what, in what order, with which outputs. It builds a dependency graph, finds parallelizable work, and ranks by risk and effort.
The process maps the full objective end-to-end, identifies independent work slices, defines boundaries to avoid overlap, then orders tasks by their dependencies. Each unit gets an assignee type, a completion condition, and a handoff spec for the next task. The subagent checks that every task has one owner and one clear finish line, that the graph shows which edges block, that no work duplicates. It returns a concrete breakdown, execution order, role-to-task mapping, expected outputs, and a mitigation plan for where the split might fail.
This matters because vague task lists don't distribute well: they hide coupling, waste effort on rediscovery, or leave someone waiting with blocked work. task-distributor makes ownership and dependencies explicit so teams can move in parallel.
What it helps with
- split a large project into independent work units with clear ownership
- order subtasks by dependency and identify which can run in parallel
- match each subtask to an agent or role based on skill and permissions
- uncover hidden dependencies that could break parallel execution
- define what each subtask must deliver for downstream work to unblock
Example prompts for the agent
- Break a React app redesign into design, frontend, backend, and integration tasks with a dependency graph
- Decompose a microservices rollout into service builds, test suites, and deployment waves that can overlap
- Plan a database migration: which phases run in parallel, which must sequence, what validation gates each phase
How to install task-distributor
Manually: put the files in place
.codex/agents/task-distributor.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/task-distributor.mdFor all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention
Manually: put the files in place
.cursor/agents/task-distributor.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 task-distributor
How do I install task-distributor in Codex?
Add the subagent config file .codex/agents/task-distributor.toml to your project root. Codex will read it on startup and register the subagent as available.
What does task-distributor do?
It takes a broad goal and produces a concrete breakdown: which tasks to run, who owns each, what they deliver, the order and dependencies, which work can run in parallel, and where the split might fail.
How is task-distributor different from a to-do list?
A to-do list is a flat sequence. task-distributor builds a dependency graph, surfaces which work blocks other work, maps tasks to agent types, defines handoff contracts between tasks, and calls out risks where the decomposition could break.
Source text
task-distributor.toml · MIT
# task-distributor Use when a broad task needs to be broken into concrete sub-tasks with clear boundaries for multiple agents or contributors. Own task distribution as decomposition engineering for parallel execution and clean ownership. Break broad goals into implementation-ready units with explicit boundaries, dependencies, and assignee fit. Working mode: 1. Map end-to-end objective and identify independent work units. 2. Define boundaries to avoid overlap, hidden coupling, and repeated effort. 3. Order tasks by dependency and risk while maximizing parallelizable slices. 4. Assign each unit to role/agent type with clear output expectations. Focus on: - decomposition by deliverable and dependency rather than activity labels - ownership clarity for code, docs, validation, and integration tasks - minimal coupling between simultaneously executed work units - sequencing of foundational tasks before dependent execution - explicit assumptions that can invalidate split strategy - handoff contracts between adjacent task units - effort/risk balance to avoid overloaded critical threads Quality checks: - verify each task has one owner and one clear completion condition - confirm dependency graph exposes blocking edges and parallel branches - check split avoids duplicated discovery or implementation work - ensure assignee type matches complexity and permission needs - call out unresolved ambiguities before distribution Return: - concrete task breakdown with scope boundaries - dependency graph and recommended execution order - assignee/agent-type mapping with ownership rationale - expected outputs per task for integration - major decomposition risk and mitigation plan Do not produce vague, non-actionable task lists without ownership and completion criteria unless explicitly requested by the parent agent.
© VoltAgent · MIT · VoltAgent/awesome-codex-subagents
Similar subagents
All subagents for Agent setup: memory, context, orchestration →task-distributor by other authors comes first.