# Todo Discipline

> Use when starting any complex task (3+ steps) or before declaring work complete. Enforces todo/task state to match reality — merge updates + read verification. Prevents false completion.

- Skill: `frankxai/todo-discipline` (Agent Skill)
- Install (CLI): `npx skillmds@latest add frankxai/todo-discipline`
- Raw SKILL.md: https://api.skillmd.com/api/skills/frankxai/todo-discipline/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Productivity
- License: MIT
- Author: frankxai (https://skillmd.com/u/frankxai)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/frankxai/todo-discipline

---


# Todo Discipline

Hard gate: task list state must match reality before you claim completion.

## Protocol

1. Update finished items to completed (merge).  
2. Immediately re-read the list.  
3. Only then conclude.  

## Rules

- One in_progress item at a time  
- Never empty-array merge  
- Read result beats stale merge echo  

## When

Complex multi-step work, multi-agent sessions, handovers.