# task-decomposition-expert

Breaks down complex multi-step goals into a structured work breakdown structure with dependency graphs, effort estimates, and handoff plans.

- subagent · `type=agent` · Claude Code · 6870 installs
- Author: davila7
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/davila7/claude-code-templates/tree/HEAD/cli-tool/components/agents/ai-specialists/task-decomposition-expert.md
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/agents/task-decomposition-expert

## What it 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.

## Install

### Claude Code (native platform)

1. **claude-code-templates**
```bash
npx claude-code-templates@latest --agent ai-specialists/task-decomposition-expert
```

2. **Manually: put the files in place**
- File: `.claude/agents/task-decomposition-expert.md` — For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

### Codex

**Manually: put the files in place**
- File: `.codex/agents/task-decomposition-expert.toml` — Codex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/

### Cursor

**Manually: put the files in place**
- File: `.cursor/agents/task-decomposition-expert.md` — Cursor also reads .claude/agents/

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/davila7/claude-code-templates/tree/HEAD/cli-tool/components/agents/ai-specialists/task-decomposition-expert.md

## When to use it
- 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
- 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.

## Similar
- [frontend-developer](https://affpapa.org/en/nevibecode/agents/voltagent-community-frontend-developer.md) — subagent · 40905 installs
- [dx-optimizer](https://affpapa.org/en/nevibecode/agents/dx-optimizer.md) — subagent · 1198 installs
- [mlops-engineer](https://affpapa.org/en/nevibecode/agents/voltagent-community-mlops-engineer.md) — subagent · 1009 installs
- [postgres-pro](https://affpapa.org/en/nevibecode/agents/postgres-pro.md) — subagent · 897 installs

From the same set: [davila7/claude-code-templates](https://affpapa.org/en/nevibecode/by/davila7/claude-code-templates.md) — 224 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md