Parallel Task

This does exactly what it says: you point it at a markdown plan file with sprints and tasks, type /parallel-task, and it spins up multiple Claude subagents to work on independent tasks simultaneously. It parses your plan structure, figures out dependencies, and won't launch agents for tasks that would step on each other's toes. The prompt template it uses is thoughtfully designed with context, acceptance criteria, and validation steps baked in. Worth noting that it keeps looping until the whole plan is done or hits a blocker, so you're not babysitting each task. If you're working from detailed plan files and tired of serializing work that could happen in parallel, this makes that automatic.

GitHub stars: 235
last updated: Jun 10, 2026

View on GitHub

Install

$ npx -y skills add jdrhyne/agent-skills --skill parallel-task --agent claude-code

Installs into .claude/skills of the current project.

Files

Parallel Task Runner

Use Orchestration Mode. Parse plan files and delegate tasks to parallel subagents.

Safety Boundaries

Do not launch subagents for tasks that share write scope until the dependency is resolved.
Do not continue past blockers silently; surface the blocked task and stop that branch of work.
Do not mark tasks complete until validation from the plan has actually been checked.
Do not run this skill unless the user explicitly invoked /parallel-task or clearly asked for parallel agent work.

Process

Step 1: Parse Request

Extract from user request:

Plan file: The markdown plan to read
Sprint/Phase (optional): Which section to run

If sprint not provided, ask user which to run.

Step 2: Read & Parse Plan

Find sprint/phase section (e.g., ## Sprint 1:)
Extract task subsections (e.g., ### Task 1.1:)
For each task, extract:
- Task ID and name
- Full content (description, location, acceptance criteria, validation)
Build task list