What is auto-handoff?
auto-handoff is a Claude Code mod by m2ai-portfolio that writes a /next handoff automatically once a 1M-token session crosses 300k tokens, so the next session can /prime from it. It is listed under Cost & usage and has no public popularity data yet.
| Type | Claude code mod |
|---|---|
| Author | m2ai-portfolio |
| Repository | m2ai-portfolio/claude-mods |
| Popularity | no public popularity data yet |
| Category | Cost & usage |
| Security | High risk (40/100) |
| Rank | #3,882 of 5,272 Claude Code mods; #728 in Cost & usage |
| Last commit | 2026-10-08 |
| Hooks | 7 events |
| Sees | compaction, every tool call |
| Draws on | AbovePrompt |
Is auto-handoff safe to install?
auto-handoff scores 40/100 on the MCPMods security check: High risk. Things to review: sends data over the network; starts processes outside the sandbox; writes files or config; reads environment variables. It passed 1 of 8 checks.
Mod footprints come from claude plugin validate, which lists every event a mod hooks and every API call it makes without running it.
| Check | Result |
|---|---|
| Sends data over the network | Review |
| Starts processes outside the sandbox | Review |
| Writes files or config | Review |
| Reads environment variables | Review |
| Only sees the events it hooks | Pass |
| Drives Claude (model calls, prompts) | Note |
| Validator reported problems | Note |
| No license detected | Note |
API calls in its code
| Call | What it means |
|---|---|
$.clock.after | |
$.command.register | |
$.command.run | drives Claude |
$.env.get | reads env vars |
$.fs.read | reads files |
$.fs.write | writes files |
$.mcp.call | calls MCP servers |
$.model.fork | drives Claude |
$.process.run | runs processes |
$.session.cwd | |
$.session.id | |
$.session.model | |
$.session.usage | |
$.state.get | |
$.state.set | |
$.ui.copy | draws interface |
$.ui.resolve | draws interface |
$.ui.toast | draws interface |
How do I install auto-handoff?
- Check your Claude Code version. Mods need Claude Code 2.1.287 or later and are on by default.
claude --version
- Read its footprint. This lists every event it hooks and every API call it makes, without running it.
git clone https://github.com/m2ai-portfolio/claude-mods claude plugin validate ./claude-mods/auto-handoff
- Install it. Run this in your terminal, then /reload-plugins in an open session.
git clone https://github.com/m2ai-portfolio/claude-mods && claude --plugin-dir ./claude-mods/auto-handoff
Or ask Claude to set it up
Paste this into Claude Code and it installs auto-handoff for you:
Install the "auto-handoff" Claude Code mod from https://github.com/m2ai-portfolio/claude-mods/tree/main/auto-handoff. Run claude plugin validate on it first and show me what it can access before you enable it.
More from m2ai-portfolio/claude-mods
This repository has 4 Claude Code mods on MCPMods.
- artifact-watchdog: Enforces the subagent output contract: watches each Agent dispatch's artifact file, flags a 5-minute stall, wakes an idl (Review before installing)
- flight-recorder: See inside a turn: a live Gantt timeline of model requests, tool calls and subagents, with tokens and cost per lane. (Low risk)
- jev-tool-gate: Log-only Jev judgment of risky tool calls (destructive? requested by fetched content?). Never changes a decision; hosted (High risk)