Menu
Create session handoff document for transferring work to another session
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | util-create-handoff |
| description | Create session handoff document for transferring work to another session |
| metadata | {"source-plugin":"util","source-skill":"create-handoff"} |
${CLAUDE_SESSION_ID}
Create a handoff document for the next session.
Save to: .handoffs/YYYY-MM-DD_HH-MM_<short-description>.yaml
(Example: .handoffs/2026-01-24_14-30_auth-implementation.yaml)
---
date: YYYY-MM-DD
status: complete | partial | stuck | transient
---
goal: |
What was the larger goal of this session?
What were we ultimately trying to achieve?
current_state: |
Where did we end up?
What's the current state of the work?
What skill was used in terms of state - planning, implementing, reviewing etc?
# If stuck
stuck_on: |
What specific problem is blocking progress?
What have we tried that didn't work?
# If goals shifted
transient: false # or true
transient_reason: |
Why did the goals shift? What new direction emerged?
# CRITICAL: Learnings
learned:
- insight: What we discovered
details: Specifics about the learning
worked:
- approach: What worked well
why: Why it worked
didnt_work:
- approach: What we tried that failed
why: Why it failed, what to avoid
# Forward-looking
next_approach: |
Given what we learned, what should we try next?
What's the recommended path forward?
next_steps:
- First concrete action
- Second concrete action
# Auto-populated from git context above
git:
branch: <from context>
recent_commits:
- <from context>
changed_files:
- <from context>
# Optional
questions: [] # Unresolved questions
decisions: [] # Key decisions made
files_to_read: [] # Files next session should read first
Fill this out based on our session. Be honest about stuck points and what didn't work.
Write high-quality session prompts (SESSION_WORKER.md and SESSION_REVIEWER.md) for an agent loop. Reads repo context and follows the loop-author guide to produce targeted, effective prompts. Use when setting up a new loop or rewriting session prompts for an existing one.
Pre-flight checks and launch for agent loops. Validates branch state, session prompts, creates loop directory structure, and launches run.sh in a tmux session. Use when the user wants to start a new agent loop in the current repo.
Cross-repo visibility for agent loops. Lists running, completed, and crashed loops. Reads the registry and per-repo tracking logs. Shows tmux attach commands. Use when checking what loops are active, what ran recently, or loop details.
Capture feedback about wf, util, or vault plugins and file it as a GitHub issue for improvement. Use after any session where the tooling fell short โ wrong agent behavior, missing skill coverage, misleading prompts, workflow friction, or convention gaps. Only for generic plugin improvements that would help ANY project, not repo-specific config. Files to JSai23/claude-tooling with the plugin-feedback label.
Write high-quality session prompts (SESSION_WORKER.md and SESSION_REVIEWER.md) for an agent loop. Reads repo context and follows the loop-author guide to produce targeted, effective prompts. Use when setting up a new loop or rewriting session prompts for an existing one.
Pre-flight checks and launch for agent loops. Validates branch state, session prompts, creates loop directory structure, and launches run.sh in a tmux session. Use when the user wants to start a new agent loop in the current repo.