Task Preparer — Project Management agent for Claude Code
Reviews and clarifies tasks in Tasks/Next.md for better actionability.
How to install Task Preparer
Installs to ~/.claude/agents/focuscraft-ai-focuscraft-gtd-task-preparer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/focuscraft-ai/focuscraft-gtd/HEAD/.claude/agents/task-preparer.md -o ~/.claude/agents/focuscraft-ai-focuscraft-gtd-task-preparer.md Restart Claude Code, or start a new session, for it to be picked up.
What Task Preparer does
name: task-preparer description: Reviews and clarifies tasks in Tasks/Next.md for better actionability model: claude-sonnet-4-5 color: purple
Task Preparer Agent
You are a specialized agent that reviews tasks in `Tasks/Next.md` and ensures they are clear, actionable, and properly structured for effective execution.
Your Mission
Prepare tasks for execution by:
- Analyzing clarity - Are tasks specific and actionable?
- Checking completeness - Is all metadata present and
Alternatives in Project Management
- Agent Evaluator — Evaluates agent output against 5-axis quality rubric (accuracy, completeness, clarity, actionability, concisen 243.5k ★
- Task Checker — Use this agent to verify that tasks marked as 'review' have been properly implemented according to their speci 267 ★
- Scope Rule Architect NextJS — Use this agent when you need to make architectural decisions about component placement in a Next.js/TypeScript 132 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Execute Plan
Execute PLAN.md tasks one at a time with human oversight. Triggers on "execute", "execute plan", "execute the
Plan Worker
Executes plan-graph tasks: fetches the next ready task, claims it, does the work, verifies it and marks it don
Workhorse Planner
Planning subagent for a Workhorse harness. Clarifies an implementation request and produces the overall plan a
Linear Tracker
Manages Linear issues for the Component Reviews project. Handles CRUD operations for review tracking, finding
Claude Comparator
Blind-compares two outputs for the same task (labeled A and B) and says which is better and why. Use to compar
Eval Agent
Evaluates agent output against 5-axis quality rubric (accuracy, completeness, clarity, actionability, concisen
Related Skills
Prepare Tasks
ACTION REQUIRED: Use the Task tool to invoke the task-preparer agent immediately.
Flow Next
Plan-first AI workflow plugin for Claude Code, OpenAI Codex, and Factory Droid. Zero-dep task tracking, worker
M Next Task
Next Tasks Workflow: Analyze Status & Plan Actions