Reve AI
리소스 마켓
Skill개발무료

project-butler

Project memory system for AI coding assistants (Claude Code, Cursor, Codex): session logs, project wiki, rules, TODOs, and handoff.

156

project-butler

English | 中文

Persistent project memory for AI coding assistants.

project-butler gives Claude Code, Cursor, Codex, and similar AI coding assistants a shared project memory stack: session logs, handoff notes, project wiki, TODOs, rules, file structure, and changelog.

You keep working normally. At the end, say end session. Next time, say continue.

Quick Start

Install as a Claude Code skill:

git clone https://github.com/JamesShi96/project-butler.git ~/.claude/skills/project-butler

Open any project and initialize the memory stack:

/project-butler

At the end of a work session:

end session

Next time:

continue

For Cursor, Codex, and other assistants, see Tool Compatibility.

Why It Exists

AI coding assistants are powerful in one session and forgetful across sessions. If any of these sound familiar, project-butler is for you:

  • "I had to re-explain the architecture again." Each new session starts with missing context.
  • "What did we decide about naming conventions last week?" Decisions disappear into chat history.
  • "The README and TODOs keep drifting from reality." Project state stops matching the files.
  • "The AI keeps violating rules I already explained." Rules live in your head instead of in project memory.
  • "I switch between Claude Code, Cursor, and Codex." Different tools need one shared source of truth.

project-butler turns a project folder into that source of truth.

What It Creates

Run /project-butler once. It creates a file-based project memory stack:

project-root/
├── CLAUDE.md                   <- Project rules / constitution
├── PROJECT.md                  <- Current project wiki
├── STRUCTURE.md                <- File organization rules
├── UPDATE_LOG.md               <- Milestone-level changelog
├── session-handoff.md          <- Cross-session handoff
├── TODO.md                     <- Execution checklist
├── log/                        <- Session logs
└── .claude/
    ├── candidates.md           <- Candidate rules for review
    └── .file-snapshot.json     <- File organization snapshot

The core files are plain Markdown, so other tools can read them even when they do not run the skill natively.

Common Commands

All triggers are natural language. Use slash commands only for first-time setup.

You sayWhat happens
/project-butlerInitialize or upgrade the project memory stack.
end session / we're doneWrite a session log, update handoff, sync wiki, update TODOs, organize new files, and record significant changes.
continue / continue from last timeRecover the previous session and resume without re-explaining context.
continue full contextRebuild the full project trajectory from the latest session plus historical summaries.
review claude / check the rulesReview candidate project rules before they are promoted into the constitution.
sync wiki / update overviewForce-refresh PROJECT.md.
status / where are weRead the current wiki and handoff summary.
organize filesRun file organization based on STRUCTURE.md.
change languageSwitch project management files between English, Chinese, and bilingual mode.

Session recovery (continue / continue full context) is routed through project-butler internally. There is no separate /continue command to install.

Tool Support


GitHub에서 전체 내용 보기