handoff

handoff is a command for Claude Code from joaquinbejar/ai-crew-sync. It costs 14 tokens per session (389 once invoked), scanned A, original, MIT.

A command that passes a task to another teammate after recording what is done, what remains, and where the work is stored.

In plain words
What is it for?
Use it to hand off an active task with its branch, pull request, files, and remaining work documented.
Why use it?
It prevents lost context when work moves between people or agent sessions. The task is released only after its state has been written down.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the ai-crew-sync plugin — 1 skill, 16 commands, 3 hooks shipped together

Good fit Use it to hand off an active task with its branch, pull request, files, and remaining work documented.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/joaquinbejar/ai-crew-sync/handoff
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/joaquinbejar/ai-crew-sync

Made for: Claude Code.

Or install ai-crew-sync, the plugin that ships this one along with the rest of its 1 skill, 16 commands, 3 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for handoff

README.md
[![agentmods](https://agentmods.dev/badge/commands/joaquinbejar/ai-crew-sync/handoff/github.svg)](https://agentmods.dev/commands/joaquinbejar/ai-crew-sync/handoff)
Your own site
<a href="https://agentmods.dev/commands/joaquinbejar/ai-crew-sync/handoff"><img src="https://agentmods.dev/badge/commands/joaquinbejar/ai-crew-sync/handoff/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for handoff

Your own site · 80×15
<a href="https://agentmods.dev/commands/joaquinbejar/ai-crew-sync/handoff"><img src="https://agentmods.dev/badge/commands/joaquinbejar/ai-crew-sync/handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 389 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00014 $0.00389
Opus 5.5 $0.00006 $0.00156
Sonnet 5.5 $0.00003 $0.00078
Haiku 4.5 $0.00001 $0.00039

Measured 23d ago against content hash 1813da9405f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

handoff scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 23d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugin/commands/handoff.md · 18 lines

What it actually says

Pass my task to a teammate so the work continues without a meeting.

Input: $ARGUMENTS

Steps:

  1. The first word is the task key, the second the teammate (agent or agent/session); the rest, if any, is what is left to do. Check the teammate exists with list_agents (and the session with list_sessions when given); if not, ask me instead of guessing.
  2. Call get_task and confirm I hold it. If I do not, say who does and stop.
  3. Write the state down first: call set_note with scope = handoff and key = the task key exactly as it is (a task key keeps its case and may be longer than a note scope allows, so it goes in the note key, never the scope), and a value with three parts: what is done (from this session), what is left (from the input, or ask me), and where things are (branch, PR, files). Show me the value before writing it if anything in it is a guess. If the write fails, stop here and tell me: nothing is released without its state written down.
  4. Then release: release_task with the key.
  5. Then point: post_message with to = the teammate and a body that names the task key, says I released it, and tells them to read the note (get_note with scope handoff and key <task key>) and claim it.

Confirm with the note reference, the release, and the message id. Order matters: note, release, message, so the pointer never arrives before the state.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 23d ago First seen · 18 lines · 14 tokens per session scan A 1813da9405f7

Subscribe to this mod's changes

handoff is a command published in the GitHub repository joaquinbejar/ai-crew-sync (7 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 389 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-23.