tasks

Breaks long-running multi-step tasks into persistent markdown files for resumable agent workflows.

41|2|Updated Feb 28, 2026
One-click install
npx skills add https://github.com/taoeffect/tasks --skill tasks-taoeffect
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: tasks
Source: https://github.com/taoeffect/tasks
Command: npx skills add https://github.com/taoeffect/tasks --skill tasks-taoeffect

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Long-running, multi-step tasks overwhelm AI agents in large projects because context windows fill up and sessions get interrupted, losing all progress. This Skill persists task state in markdown files so work survives session resets and context limits. ## Core Features & Use Cases - Structured Task Files: Creates CURRENT_DESIGN.md, PLAN.md, TODOs.md, STEP-<N>.md, and KNOWLEDGE.md under .agents/tasks/<task name>/ to track design, plans, and progress. - Session Resumption: Pick up exactly where you left off in a brand-new session by reading the step files and notes. - Plan Verification & Pause Handling: Re-evaluate plans mid-task, add TODOs to existing tasks, and formally pause when user intervention (credentials, sudo commands) is required. - Use Case: You need to refactor user creation across a large codebase. Create a task, let the agent plan it into sequential TODOs, then execute one step per session over several days without losing context. ## Quick Start Read the tasks skill and begin task: my-task-name to start executing the planned steps for that task.

Frequently Asked Questions about tasks

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I make an AI agent complete long multi-step tasks?▼

Describe the task and give it a name; the agent creates a .agents/tasks/<task name> folder with a plan, TODO list, and step files. It then works one TODO at a time, recording progress in markdown so later sessions can resume.

How to resume an interrupted agent coding session?▼

Start a new session and tell the agent to read the tasks skill and continue the named task. It reads TODOs.md and the current STEP file's notes to pick up exactly where the previous session stopped.

Should I disable my agent's built-in todos tool when using this?▼

Yes. The skill instructs agents to never use harness todos tools alongside it, since dual tracking causes conflicts. The markdown-based task files are persistent and work across all coding agents.

What happens when the agent hits a blocker needing user action?▼

The agent adds a PAUSED section to the current STEP file describing the blocker and exact commands needed, then stops. After you respond, it records the resolution and continues from where it paused.

Can I verify or adjust a task plan without executing it?▼

Yes. Tell the agent to review only or verify the plan for a task. It compares CURRENT_DESIGN.md, PLAN.md, and TODOs.md against the codebase, updates the documents if needed, and stops without completing TODOs.