mcpbeat

Todo Write

nexu-io/todo-write

TodoWrite-driven plan that the agent commits to before generation.

411 tokens
context cost
the whole folder, loaded on every use
2
files
instructions only
0
copies elsewhere
how many repositories repackaged it
83386
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository 
npx skills add https://github.com/nexu-io/open-design --skill todo-write

What comes with it

787 bytes besides the instruction
open-design.json

What it tells the agent to use

found in the instruction text
Write writes files

The instruction itself

1 sections, as written by the author

Todo write

Before writing any artifact files, the agent commits to a numbered plan

via the TodoWrite tool. The plan is the audit trail; subsequent turns

either tick items off or rewrite the plan. The atom's prompt fragment

teaches the agent to:

  • Keep todos atomic (one verb per todo).
  • Reorder freely as the picture sharpens.
  • Mark a todo complete only after the matching artifact lands.
  • Surface blockers as todos — never silently skip.

The Open Design daemon does not enforce a particular tool name; the

agent is free to use TodoWrite (Claude Code) or an in-prompt list.

The atom's job is to keep "make a plan first" in the system prompt so

non-trivial workflows don't skip the planning step.

How to use it

Copy the folder

Take nexu-io/todo-write from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.