Open methodology · MIT licensed
About the methodology
A repeatable structure for planning, executing, and verifying deep work with AI coding agents — built in the open and free to use.
What it is
Deep Work Plan (DWP) is a methodology, not a product. It defines how to turn a goal into an agreed plan, break that plan into atomic and independently verifiable tasks, and run each task in a focused loop that ends with a check.<br /><br />It is deliberately agnostic about which AI agent or stack you use — adapters translate the same core loop to Claude, Cursor, Copilot, Codex, Gemini, and more. The plan, the tasks, and the running log are all plain Markdown, so the work stays readable, reviewable, and version-controlled.
Core principles
Plan before execution
No code is written until the plan is agreed. The plan is a contract between you and the agent.
Read the methodology →Tasks are atomic
Each task is scoped so it can be executed and verified on its own, then committed atomically.
Read the methodology →Verify everything
Every task ends with an explicit check before the next one begins, with progress recorded in git.
Read the methodology →At a glance
- Open methodology, MIT licensed
- Framework- and agent-agnostic
- Maintained by Dailybot and the community
- Includes a spec, commands, adapters, presets, and examples
- Markdown-only — no runtime, no lock-in
- Turns any repository into an AI-first, agent-pilotable codebase
Who maintains it
Deep Work Plan grew out of real engineering work at Dailybot and is now maintained by Dailybot together with the open-source community. The methodology, specification, and kit are released under the MIT license — free to use, adapt, and build on.