Claude Code mod
self-clear
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
/plugin marketplace add adithepmeekhun/self-clear
/plugin install self-clear@self-clearMods install like plugins. Run /reload-plugins or start a new session to load it.
What it can access
- Reach
- L2Writes or runs: drives Claude, reads files, draws
- Sees
- classic hooks, subagent spawns, every prompt
- Hooks
session.startclassic.Stopagent.spawnprompt.submitturn.completecommand.run
From a static scan of the mod's code by awesome-claude-code-mods. It shows what the code asks for, not a security review.
How Claude Code mods work
- A mod is a plugin with a JavaScript or TypeScript module that runs inside Claude Code (version 2.1.287 or later). It can draw panes beside the transcript, a band above the prompt, buttons and toasts, restyle the spinner and tool rows, and watch or rewrite tool calls and prompts.
- It installs like any plugin: add its marketplace with /plugin marketplace add owner/repo, then /plugin install name@marketplace.
- Check what a mod can reach before installing: it runs with your permissions. Reach goes from drawing only, to reading files, to writing files or running processes, to the network. Run claude plugin validate on a clone to list its hooks and calls without running it.
- Turn one off from the Installed tab in /plugin, or start Claude Code with --safe-mode to skip every customization for a session.
Details
- Repository
- adithepmeekhun/self-clear
- Folder
plugins/self-clear- Marketplace
self-clear- Author
- adithepmeekhun
- License
- MIT
- Last updated
- 13 October 2026
- Listed in
- awesome-claude-code-mods
FAQ
What is self-clear?
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. It is a mod for Claude Code, from adithepmeekhun/self-clear on GitHub.
What can the self-clear mod access?
Its widest reach is "writes or runs" (drives Claude, reads files, draws). It sees classic hooks, subagent spawns, every prompt. Like any mod, it runs with your permissions.
How do I install self-clear?
Inside Claude Code (v2.1.287 or later), run /plugin marketplace add adithepmeekhun/self-clear and then /plugin install self-clear@self-clear.
More memory & instructions mods
segue
sipyourdrink-ltd/segue
Compaction that continues without a break: writes a handoff card before /compact and auto-compact, summarises on Haiku, and tells the agent to carry on from the card. Falls back to the built-in summary on any failure.
session-bookmark
t968rs/operator-straps
Compaction bookmark: git state, last prompts, session notes and /compact instructions kept in session state and appended to the compacted conversation
sage-relay
byShrey/sage-relay
Hands a long Claude Code chat off to a fresh one automatically: saves a full note, clears, carries on. Optional model routing with Deep, Careful and Scout helper agents.
session-handoff
danielgillaspia01-web/claude-mods
Pass work between Claude sessions: /handoff saves a summary, /pickup continues it in another session
rule-keeper
davidparys/claude-mods
When you correct Claude, a band above the prompt offers to save the correction as a permanent rule in CLAUDE.md or a skill.
session-handoff
ptsnac/claude-session-handoff
Band above the prompt with a session timer, a handoff writer and a fresh-start button that loads the handoff
Browse the most popular Claude Code mods, all memory & instructions mods, or the skills and MCP server directories.