task-decomposition-expert — Claude Code subagent: setup & guide
Breaks down complex multi-step goals into a structured work breakdown structure with dependency graphs, effort estimates, and handoff plans.
npx claude-code-templates@latest --agent ai-specialists/task-decomposition-expertWhat task-decomposition-expert does
The subagent analyzes high-level project targets, timelines, and constraints to build a structured three-level work breakdown. It enforces the 8/80-hour rule so that individual tasks stay bounded between 8 and 80 hours. It calculates the critical path, identifies tasks that can run in parallel, and assigns workstreams to specialist roles.
Before building the plan, it collects hard constraints, non-negotiables, and acceptance metrics. The subagent runs on the Sonnet model and uses Read, Glob, Grep, and WebSearch. When run inside a repository, it verifies claimed infrastructure against the actual files. It does not accept unverified assertions about existing architecture at face value.
Its role ends where execution begins. The subagent generates the initial delivery roadmap and handoff instructions. It does not track sprint progress, run standups, or communicate with stakeholders across the development lifecycle.
What it helps with
- Decompose complex migrations into isolated parallel execution tracks
- Map task dependency graphs and find the critical path
- Estimate engineering effort using the 8/80-hour guideline
- Design handoff sequences for multi-agent workflows
Example prompts for the agent
- Break down our monolithic Rails app migration into microservices with dependencies and risk flags.
- We need to launch a document processing pipeline in 8 weeks with 3 engineers. Build a prioritized roadmap.
- Map the workflow for a multi-agent research pipeline and define data contracts between agents.
How to install task-decomposition-expert
1claude-code-templates
npx claude-code-templates@latest --agent ai-specialists/task-decomposition-expert2Manually: put the files in place
.claude/agents/task-decomposition-expert.mdFor all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention
Manually: put the files in place
.codex/agents/task-decomposition-expert.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
.cursor/agents/task-decomposition-expert.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-decomposition-expert
How do I install task-decomposition-expert in Claude Code?
Run npx claude-code-templates@latest --agent ai-specialists/task-decomposition-expert in your terminal. This saves the configuration to .claude/agents/task-decomposition-expert.md.
What does task-decomposition-expert do?
It turns an ambiguous project goal into a three-level work breakdown structure with dependency graphs and parallel tracks. Each workstream is assigned to a specific specialist agent.
How does task-decomposition-expert differ from a project manager agent?
It delivers a single upfront decomposition plan before implementation starts. It does not handle sprint tracking, standups, or stakeholder communication during the execution phase.
