Skip to content
Development
Command

/wrap-up

End the current session with a structured summary and memory update.

From plugin
rohitg00-claude-code-toolkit
2.5k199 skills138 agents199 commands
Install
$ npx -y skills add rohitg00/awesome-claude-code-toolkit --agent claude-code

How it fires

How this command gets triggered: by you, by Claude, or both.

  • Fires itselfClaude auto-loads it when your prompt matches the work.
  • You can call itInvoke it directly when you want it.
  • Slash command/wrap-up

Context preview

What this command does when you run it.

End the current session with a structured summary and memory update.

Command definition

wrap-up.md

End the current session with a structured summary and memory update.

Steps

1. Review all changes made during this session:

  • Run `git diff --stat` for uncommitted changes.
  • Run `git log --oneline --since="4 hours ago"` for recent commits.
  • Scan for TODO/FIXME comments added during the session.

2. Compile a session summary:

  • What was the original goal or task?
  • What was actually accomplished?
  • What is remaining or deferred?

3. Extract learnings to save:

  • New patterns or conventions established.
  • Gotchas or bugs discovered and how they were resolved.
  • Useful commands or techniques discovered.
  • Performance insights or optimization findings.

4. Update project CLAUDE.md with relevant learnings. 5. Commit any outstanding changes if appropriate. 6. Create a brief handoff note for the next session. 7. List any blocking issues that need external resolution.

Format

## Session Wrap-Up (<date>)

### Goal
<what was the objective>

### Accomplished
- <completed item>

### Deferred
- <item not completed and why>

### Learnings
- <insight saved to CLAUDE.md>

### Blockers
- <issue needing resolution>

### Next Session
Start with: <specific instruction for next session>

Rules

  • Always commit or stash changes before wrapping up; do not leave a dirty tree.
  • Keep the summary actionable, not narrative.
  • Save learnings to CLAUDE.md so they persist across sessions.
  • Flag any time-sensitive items (expiring tokens, pending reviews).
  • Do not wrap up with failing tests unless the failure is documented.
Read more
Ships withrohitg00-claude-code-toolkit

The most comprehensive toolkit for Claude Code -- 135 agents, 35 curated skills (+400,000 via SkillKit), 42 commands, 176+ plugins, 20 hooks, 15 rules, 7 templates, 15 MCP configs, 26 companion apps, 53 ecosystem entries, and more.

Get the whole plugin