sharkrebel/everything-everywhere-for-antigravity/handoff

Handoff

Generate a structured HANDOFF.md file that gives a fresh Claude session everything it needs to continue this work without dragging the current degraded context forward.

claude-mem already injects recent observations into every new session, so the fresh agent starts with a timeline of what happened. The handoff adds what that timeline cannot: the goal, the failed attempts and why they failed, the current theory, and exact next steps, plus pointers into memory for deeper recall.

When to Use

• The session is long and Claude feels confused or repetitive
• Claude keeps trying the same failing solution over and over
• The user wants to step away and resume later
• /compact ran but Claude still lacks clear direction
• The user says "handoff", "generate a handoff", "I want to start fresh", or "write a handoff doc"

What to Capture

Think hard about the full arc of this conversation before writing. The handoff must be useful to a Claude instance that has never seen this conversation.

Required Sections

1. Goal — One paragraph. What is the user actually trying to accomplish? State the end state, not the current sub-task. Be specific enough that a fresh agent can orient immediately.

1. Current State — What is working right now? What is broken? What is the exact symptom of the problem? Include error messages verbatim if relevant.

1. Files in Play — List every file that has been read, edited, or created during this session that is relevant to the current task. Use absolute or repo-relative paths. Include a one-line note on why each file matters.

1. What Has Been Tried (and Why It Failed) — This is the most important section. List every approach attempted that did not work, and explain WHY it failed (not just that it failed). A fresh agent that skips this section will repeat the same mistakes.

1. Current Best Theory — What do you currently believe is the right path forward, even if you haven't proven it yet? Include any evidence or reasoning that supports it.

1. Next Steps — Concrete, ordered actions for the fresh agent to take. Be specific: file paths, function names, commands to run. The fresh agent should be able to start on step 1 immediately.

1. Key Constraints and Context — Any non-obvious constraints: environment specifics, user preferences expressed during this session, things the user explicitly said NOT to do, external dependencies, performance requirements, etc.

1. Memory Pointers — If claude-mem's search tools are available, run search for this task's key terms and list the few observation IDs that matter most (a decision, the root cause, a failed approach), so the fresh agent can pull full details with get_observations. Also list one or two search queries worth re-running. Skip this section if the tools are not available.

Writing Rules

• Write the handoff for a fresh Claude, not for the user. The user knows what happened; the fresh Claude does not.
• Be ruthlessly specific. Vague next steps are useless. "Fix the auth" is bad. "In src/auth/middleware.ts:47, the token expiry check uses Date.now() but should use req.timestamp — change the comparison on line 52" is good.
• Include exact error messages, stack traces, or test output that captures the failure mode.
• Do not pad. Every sentence should be load-bearing information for the fresh agent.
• Do not write the handoff from the user's perspective. Write it as a briefing document addressed to the incoming agent.

Output

Write the handoff to HANDOFF.md in the current working directory (the project root).

Use this structure:

# Handoff
 
> Generated: [timestamp]  
> Project: [project name or directory]  
> Session summary: [one sentence describing what this session was about]
 
## Goal
 
[What the user is trying to accomplish — the actual end state]
 
## Current State
 
**Working:**
-[list what is confirmed working]
 
**Broken:**
-[exact symptom, error message, or failure mode]
 
## Files in Play
 
| File | Why It Matters |
|------|---------------|
| `path/to/file.ts` | [one line] |
 
## What Has Been Tried (and Why It Failed)
 
### Attempt 1: [short name]
-**What:** [what was done]
-**Why it failed:** [root cause, not just "it didn't work"]
 
### Attempt 2: [short name]
...
 
## Current Best Theory
 
[What you currently believe is the correct approach and why]
 
## Next Steps
 
1.[Specific, actionable step with file path or command]
2.[Next step]
3....
 
## Key Constraints
 
-[Non-obvious constraint or preference the user expressed]
-[Things explicitly ruled out]
 
## Memory Pointers
 
-Observations: [#ID — one line on why it matters]
-Searches worth re-running: [`search` query]

After Writing

Tell the user:

1. That HANDOFF.md has been written
2. To run /clear or start a new Claude Code session
3. To open the new session and say: "Read HANDOFF.md and continue from where we left off."
4. That claude-mem gives the fresh agent the recent timeline automatically, and HANDOFF.md is its precise briefing on top of that
5. That HANDOFF.md is a scratch file: don't commit it (delete it once the new session has picked up, or add it to .gitignore)

Keep the message short. The user is ready to move — don't make them read a wall of text.