self-clear

by adithepmeekhun · ★ 0 · updated 13 Oct 2026

Status lineCommandsPromptvalidates

0

For long, unattended agent runs: when the conversation reaches a size you set, Claude writes a progress note, the mod checks it and clears the conversation, and (with auto-resume on) Claude carries on, so each step costs less. Off until a project turns it on.

install self-clear

Install

/plugin marketplace add adithepmeekhun/self-clear
/plugin install self-clear@self-clear

Then run /reload-plugins or start a new session. Requires Claude Code 2.1.287+.

View source on GitHub

What it hooks into

From an automated scan with claude plugin validate, not a security review. Mods run with your permissions; read the code before installing.

Events
session.startclassic.Stopagent.spawnprompt.submitturn.completecommand.run
API calls
$.agent.list$.clock.after$.clock.now$.command.register$.command.run$.fs.exists$.fs.list$.fs.read$.fs.stat$.prompt.submit$.session.id$.session.root$.session.usage$.ui.log$.ui.status$.ui.toast
Can see
classic hookssubagent spawnsevery prompt
Reach
level 2 of 3 drives Claudereads filesdraws

Origin

How it got here
Automated scan of public GitHub repos, via the CC0 dataset awesome-claude-code-mods (scan of ).
Repository
github.com/adithepmeekhun/self-clear
Path in repo
plugins/self-clear
Source commit
e5c6888 the exact code the scan read
Author
@adithepmeekhun
License
MIT
First published
Last pushed
First listed here

Name and description come from the mod's own manifest. We link to the code; we don't host it, and it stays under its author's license.