handoff

handoff is a command for Claude Code, Codex from thrashr888/AllBeads. It costs 10 tokens per session (1,534 once invoked), scanned A, original, MIT.

A command for giving a tracked work item, called a bead, to an AI coding agent for implementation. It can start new work, queue it for a running agent, or use a separate worktree.

In plain words
What is it for?
Use it to delegate ready beads, choose the agent, isolate changes in a worktree, preview a handoff, or list delegated and available work.
Why use it?
It removes the need to copy task details into another agent manually and lets you hand off work while continuing with something else.

Command for Claude CodeCodex

Written for Claude Code and Codex: a Claude Code plugin manifest, but also runs codex exec. Also seen: mentions Claude Code; mentions Codex; built for aider.

Part of the allbeads plugin — 1 skill, 19 commands, 1 hook shipped together

Good fit Use it to delegate ready beads, choose the agent, isolate changes in a worktree, preview a handoff, or list delegated and available work.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/thrashr888/allbeads/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/thrashr888/AllBeads

Made for: Claude Code, Codex.

Or install allbeads, the plugin that ships this one along with the rest of its 1 skill, 19 commands, 1 hook.

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/thrashr888/allbeads/handoff.svg)](https://agentmods.dev/commands/thrashr888/allbeads/handoff)
Your own site
<a href="https://agentmods.dev/commands/thrashr888/allbeads/handoff"><img src="https://agentmods.dev/badge/commands/thrashr888/allbeads/handoff.svg" alt="Measured on agentmods" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,534 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 $0.00010 $0.01534
Opus 5 $0.00005 $0.00767
Sonnet 5 $0.00002 $0.00307
Haiku 4.5 $0.00001 $0.00153

Measured 7d ago against content hash 34ba39f09331, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 7d 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.

.claude-plugin/commands/handoff.md · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fire-and-forget delegation to AI agents. Launches the agent with full bead context (title, description, dependencies) and moves on.

Usage

# Hand off a specific bead to Claude (default agent)
ab handoff <bead-id>

# Hand off to a specific agent
ab handoff <bead-id> --agent <agent>

# Hand off in an isolated worktree
ab handoff <bead-id> --worktree

# Queue work for a running agent via Agent Mail (instead of spawning new)
ab handoff <bead-id> --queue
ab handoff <bead-id> --queue --agent claude

# Show beads that have been handed off
ab handoff --list

# Show ready beads that could be handed off
ab handoff --ready

# Dry run - see what would happen without launching
ab handoff <bead-id> --dry-run

# Show available agents (detected on system)
ab handoff --agents

Agent Preferences

On first use, you'll be prompted to select your preferred agent from the detected installed agents. Your choice is saved to .beads/config.yaml and used for subsequent handoffs.

To override the saved preference, use --agent:

ab handoff ab-xyz --agent gemini    # Use Gemini instead of preferred

Supported Agents

Terminal Agents (CLI)

  • claude - Claude Code (default)
  • opencode - OpenCode
  • codex - OpenAI Codex
  • gemini - Gemini CLI
  • aider - Aider
  • cody - Sourcegraph Cody

IDE Agents

  • cursor - Cursor
  • kiro - Kiro (AWS)
  • antigravity - Antigravity
  • copilot - VS Code Copilot

Web Agents

  • jules - Jules (Google) - opens browser
  • chatgpt-codex - ChatGPT Codex - opens browser

What Happens

  1. Bead context is loaded (title, description, dependencies, labels)
  2. A prompt is generated from the bead content with workflow instructions
  3. Bead status is updated to in_progress
  4. Handoff is recorded (comment + handed-off label)
  5. If --worktree is used, a git worktree is created in .worktrees/
  6. Agent is launched with the prompt
    • CLI agents: launched with prompt argument (use codex exec --full-auto for non-interactive)
    • IDE agents: launched with chat command
    • Web agents: browser opened with deep-link URL

Read the full file on GitHub · 195 lines

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. 7d ago First seen · 195 lines · 10 tokens per session scan A 34ba39f09331

Subscribe to this mod's changes

handoff is a command published in the GitHub repository thrashr888/AllBeads (8 stars, last pushed 8d ago), licensed MIT. It adds 10 tokens to every session and 1,534 once invoked, about $0.0001 per session on Opus 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 2026-08-31.