Step away for lunch. Pick up where you stopped.

whatsnext keeps a plan checklist, check-offs and a short resume note as plain files in your repo. A new session, or a second agent, starts from where the last one stopped, in Claude Code or Codex.

Copy install promptView on GitHub
Experimental (0.1.0, the first public release). whatsnext may have bugs. It is tested on Claude Code 2.1.316 and Codex 0.165.0 only. It writes files in your repo (PLAN.md, a handoff note, progress and journal files) and runs hooks at session start and end. Commit your work first, and review what it writes. Using more than one agent on a plan is experimental. If something breaks, open an issue with what you ran and what you saw.
In Claude Code you say "wrap up", answer one question about an unrecorded decision, and whatsnext saves the handoff. The next morning you start a new session and say "hi", and the agent opens with "Welcome back", the new commits, the open decision and the next step.
A real Claude Code session in a demo project. The waiting time is cut, the agent's wording varies from run to run, and the overnight gap is set up for the recording.

The problem

A coding agent forgets between sessions. So you pay in one of three ways:

A compact does not fix this. It keeps whatever the model thinks matters, which may not be your goal.

What you get

Without whatsnextWith whatsnext
Start of a sessionYou retype the contextA short resume note
Saying "done"A claimA command passed, or it shows done*
Two agents, one planThey may take the same itemThe second is told who has it
CompactKeeps what the model picksKeeps your goal, next action and constraints

How it works

  1. Hooks run. At session start, after /clear and after a compact, a hook prints the resume note. Other hooks record plan-mode plans and add one line per session event to a facts journal. Claude Code and Codex call the same script.
  2. The script saves state as plain files. The plan is PLAN.md. Progress per task and the journal live in docs/project/progress/. The handoff note is docs/project/HANDOFF.md. Read and edit any of them.
  3. The next session reads them. It starts from the files, not from a retelling.

Better with rightsize

whatsnext works alone. With rightsize, it does more: rightsize sends "wrap up" once before a big session's cache goes cold, and its Compact now button runs /compact with whatsnext's text. rightsize decides when. whatsnext decides what to keep. This needs rightsize 0.9.0 or later.

Privacy

Known limits

Install

You need Python 3.9 or later. whatsnext uses only the standard library.

In Claude Code, run these two commands:

/plugin marketplace add archid21/whatsnext
/plugin install whatsnext@whatsnext

Then, in your project, say set up whatsnext. It shows what init would write and waits for your OK. init changes only PLAN.md, .whatsnext/, one line in .gitignore and one marked block in AGENTS.md. init --undo removes the block.

To try it, say wrap up, then start a new session.

Codex

Codex hooks need Codex 0.145.0 or later. Run whatsnext install-hooks, then trust the hooks in Codex's /hooks.

Ask Claude to install it

Paste this into Claude Code.

Install the whatsnext plugin from GitHub for me. Run these two commands in the terminal:
1. claude plugin marketplace add archid21/whatsnext
2. claude plugin install whatsnext@whatsnext --scope user
Tell me if either one fails and why. When both succeed, tell me to start a new session. Then tell me to commit my work in the project I want to use whatsnext in, and to say "set up whatsnext" there. It shows what it will write and waits for my OK.

Claude asks your permission before it runs each command. When it is done, start a new session.

Work in progress

whatsnext is experimental, at version 0.1.0. It may have bugs, and it is tested only on the versions named above. Report problems on GitHub, or email hello@aivalue.blog. This is an independent project, not made or endorsed by Anthropic.