Compact Plus

compact-plus

Japanese README | Architecture

A transparent Claude Code and Codex plugin that preserves working state around /compact. It does not replace either runtime's compaction algorithm; it augments compaction through documented hooks.

What It Does

- Backs up the transcript before compaction and writes a 10-section state file with an LLM
- Injects the state file, plan file, and original-source reminder after compaction through additionalContext
- Recovers mechanically observable skills and commands; unobservable Codex skill use is recorded as Not verified
- When context usage crosses a configured threshold, the next user prompt receives a suggestion to run /compact
- Alongside that reminder, the plugin injects a three-line recitation (Active Plan, Current Phase, and the most recent Session Decision from the state file) into additionalContext, so the agent keeps its bearings during the last few turns before compaction actually runs. This does not change the compaction algorithm itself; it is a focus aid that reduces late-session drift between warn and the real /compact
- Provides the /compact-plus skill for manual state capture

Usage

After installation, just run /compact as usual. No additional action is required — the flow is fully transparent.

- Both manual /compact and auto-compaction trigger the same hook path
- Before compaction: the PreCompact hook automatically backs up the transcript and generates the 10-section state file
- After compaction: Claude Code and Codex recover exactly once through SessionStart(source=compact) before the first post-compaction prompt
- The agent does not need to call any specific skill or perform any preparation

Optional enhancements:

- Pass an instruction such as /compact keep the security-related decisions to send…