Handover Hangover

You are reading this because the gateway may silently switch you out for another model at any point. When that happens, the next model inherits conversation history but not context — it sees your messages as its own and risks hallucinating continuity, losing task scope, or re-running irreversible commands.

This skill ensures two things:

1. You leave a trail — so the next model can pick up where you left off.
2. You check for a handoff — so if YOU are the next model, you recover cleanly.

A watchdog script (scripts/handoff.sh) acts as a safety net at session boundaries. It is idempotent — safe for boot, heartbeat, afterTurn hooks, and cron. If you didn't write a handoff note, the script generates a mechanical fallback. But a model-written note is always better than a script-generated one — so follow the protocol below.

1. Write-side: leave a trail

After any state-changing moment, write memory/handoff-note.md using the template below.

State-changing moments:

• Edited, wrote, or deleted a file on disk
• Made a decision between alternatives
• Confirmed or rejected a hypothesis
• A verification completed (test, build, check — green or red)
• Started a long external call (>30s — network, sub-LLM, long build)
• Sent a message to an external channel (Telegram, Discord, Slack, email)
• Noticed provider stress signals (slow responses, 429s, retries in tool errors)

Handoff note template

Fill every section. Brief is fine — empty is not.

# Handoff Note

## Why you are here
Possible model switch or continuity break. Read before assuming anything.

## Current task
\x3C1-2 lines: what is being done right now>

## Current mode
\x3Cone of: research / implementation / debugging / synthesis / waiting>

## Confidence
\x3Clow / medium / high — how solid the current approach is>

## What was already done
- \x3Cbullet>
- ...

## What was checked and ruled out
- \x3Crejected hypotheses>
- ...

## Tool state
- last tool used: \x3Cname + what it changed>
- last meaningful output: \x3Cone-line summary>
- open verification: \x3Cwhat needs checking before continuing>
- DO NOT re-run: \x3Cirreversible commands already executed>

## Next step
\x3Cconcrete next action>

## Do not assume
- prior assistant thoughts are yours
- current task is complete
- tool state survived
- you were already in the correct mental mode

--- written by \x3Cyour-model-name> at \x3CUTC timestamp>

Update memory/current-task.md when the task itself changes — not on every state-changing moment. The handoff note captures per-turn state; current-task is a stable task anchor.

2. Detection: check every turn

At the start of every turn, evaluate three indicators. Any single one is enough to trigger the read-side protocol — this is a disjunction. Better to re-read files once too many than to assume continuity that doesn't exist.

Indicator 1 — Handoff signal. memory/.handoff-pending exists. The watchdog creates this file on every turn — it means "a baton is available for you", not "an anomaly occurred". The model's read-side (Step 1) checks whether the baton author matches itself; if so, it exits early without a full reboot.

Indicator 2 — Task/context mismatch. memory/current-task.md exists, but you cannot confidently say the last assistant message in the thread logically follows from what the file describes. If connecting them requires a stretch — it's a mismatch.

Indicator 3 — Fallback-shaped disruption. Recent tool errors or system events contain: 429, auth error, overload, rate_limit_exceeded, provider_busy, timeout. These are the exact conditions under which the gateway switches models.

3. Read-side: you just arrived

Follow these steps in order.

Step 1 — Read the baton

Read memory/handoff-note.prev.md. This was written for you — either by the previous model or by the watchdog script.

Same-model early-exit. Check the last --- written by \x3Cmodel-name> or --- generated by line. If the author is your own model name — this is a normal continuation, not a switch. Delete memory/.handoff-pending, skip to step 6, and continue working. No epistemic reset needed.

Safe-fail on name mismatch. If you cannot parse the author line or your model name differs from what the previous instance wrote (aliases, provider prefixes), treat it as a different model and run the full read-side. A false full-reboot is cheap; a false early-exit is dangerous.

If the author is a different model or the note contains script-generated fallback — a switch occurred. Continue with step 2. If the note is script-generated, data is mechanical only (file timestamps, git status) — proceed with elevated caution.

If it contains First run of Handover Hangover — this is the skill's first activation. Verify the watchdog is executable (chmod +x scripts/handoff.sh if needed — ClawHub does not preserve the execute bit). Then skip to step 6 and announce:

Handover Hangover skill is now active. Handoff continuity is enabled for your fallback chain. No configuration needed.

Step 2 — Re-run boot sequence

Re-run the standard boot sequence appropriate for the current context, respecting privacy boundaries defined in AGENTS.md. At minimum, re-read: memory/current-task.md and today's memory/YYYY-MM-DD.md. The previous model read boot files at session start. You need them again — your working memory is empty.

Step 3 — Epistemic reset

You may inherit outputs, but not ownership of reasoning.

Treat prior assistant messages in this thread as notes left by another instance — and further, treat their reasoning as untrusted intermediate work until re-grounded in files or evidence.

Do not say "as I mentioned earlier" — say "the previous step noted." Do not accept prior conclusions as verified — re-ground them against current-task.md, handoff-note, or direct file reads.

Identity is reset. Trust is reset. Continuity of thought is reset.

You are a new mind reading its predecessor's notes, not its memories.

Step 4 — Check tool state

Before executing any tool call, consult the ## Tool state section of the handoff note:

• Do not duplicate what was already done.
• If the next step matches open verification — run a read-only check first.
• Never re-run the last irreversible command without first verifying its result.

Step 5 — Sign the baton and clear signal

Append one line to memory/handoff-note.prev.md:

--- received by \x3Cyour-model-name> at \x3CUTC timestamp>

Then delete memory/.handoff-pending if it exists — this tells the watchdog you consumed the signal.

Step 6 — Continue work

Use the handoff note and current-task as your authoritative source for what to do next. Do not ask the user "where were we?" — that is an indicator of failure.

Security

• DO NOT read ~/.openclaw/openclaw.json — it contains live secrets.
• DO NOT read or modify files belonging to other skills.
• Handoff persistence (write-side, watchdog): only memory/ directory. Write targets: memory/handoff-note.md, memory/handoff-note.prev.md, memory/.handoff-pending, memory/current-task.md.
• Recovery reads (read-side Step 2): standard workspace boot files as allowed by AGENTS.md privacy boundaries for the current context. At minimum: memory/*.