A way for one software agent to leave a task or review note for another agent in the same run. The receiving agent can answer with a decision such as approve, request changes, block, or acknowledge.

Use it to pass work between agents, list unresolved handoffs, review subagent results, and record decisions about whether work may continue.

It prevents work passed between agents from being lost and shows which results are still waiting for review. It provides a simple record of what was handed over and what happened next.

handoff — Skill for Claude Code by mubit-ai/claude-plugins

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add mubit-ai/claude-plugins

Claude Code

/plugin install mubit-memory

Made for: Claude Code.

Or install mubit-memory, the plugin that ships this one along with the rest of its 15 skills, 1 agent, 13 hooks, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/mubit-ai/claude-plugins/handoff/github.svg)](https://agentmods.dev/skills/mubit-ai/claude-plugins/handoff)

Your own site

<a href="https://agentmods.dev/skills/mubit-ai/claude-plugins/handoff"><img src="https://agentmods.dev/badge/skills/mubit-ai/claude-plugins/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/mubit-ai/claude-plugins/handoff"><img src="https://agentmods.dev/badge/skills/mubit-ai/claude-plugins/handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,194 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.

Model	Per session	Once invoked
Fable 5.1	$0.00049	$0.01194
Opus 5.5	$0.00020	$0.00478
Sonnet 5.5	$0.00010	$0.00239
Haiku 4.5	$0.00005	$0.00119

Measured 1mo ago against content hash 0669105b50c3, 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 1mo 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.

integrations/claude-code/skills/handoff/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

This skill never installs anything. It runs one Node process from the plugin directory, which writes a handoff or a feedback entry to the user's own Mubit instance under the current run. No packages, no services, no changes to the shell.

What a handoff is

A handoff is a note from one agent to another inside this run — "review this", "continue from here", "approve before I execute" — filed as a handoff entry that the next agent, or the next session, finds. Feedback is the answer: a verdict (approve, request_changes, block, acknowledge) with optional comments, filed against the handoff's id. A handoff with no feedback naming it is open.

Every subagent already files one without being asked. When a subagent finishes, the plugin stores its result as a handoff from that subagent to this session's role, with requested_action: review. So after a fan-out, handoff list --open is the list of subagent results nobody has looked at yet, and answering each one is how the list empties.

Send

node "${CLAUDE_PLUGIN_ROOT}/bin/handoff.mjs" send --to <agent> --action review "<the note>" --data-dir "${MUBIT_CC_DATA_DIR:-${CLAUDE_PLUGIN_DATA}}" --run <run_id> --json

--to is the receiving agent's role — codex for a Codex session in this same directory, claude-code for another Claude Code session, or whatever an orchestrator registered. The note is the argument. --action is one of review, continue, approve, execute; the default is continue. --task <id> ties the note to a task id when the caller has one.

Print the handoff id back. It is what feedback names.

List

node "${CLAUDE_PLUGIN_ROOT}/bin/handoff.mjs" list --open --data-dir "${MUBIT_CC_DATA_DIR:-${CLAUDE_PLUGIN_DATA}}" --run <run_id> --json

Without --open, every handoff in the run, each with the feedback that answered it. "Open" is computed by this command, not by the instance: a handoff is open when no feedback entry names its id. The instance never flips a handoff's active flag, so do not read that field as its state.

Read the full file on GitHub · 88 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.

1mo ago First seen · 88 lines · 49 tokens per session scan A 0669105b50c3

Subscribe to this mod's changes

handoff is a skill published in the GitHub repository mubit-ai/claude-plugins (12 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 49 tokens to every session and 1,194 once invoked, about $0.0002 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 2026-09-10.

Building agents

handoff next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
handoffmubit-ai/claude-plugins	Skill	12	1mo ago	Apache-2.0	A	49	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code