What is create-handoff?

A procedure for sending a defined piece of work to another agent or person. It gathers the recipient, request, scope, sensitivity, priority, and related references, then asks for confirmation before sending.

Use it to delegate a bounded task, such as asking another agent to review code or implement a specific change, with a clear definition of done.

It prevents unclear, unauthorized, or overly broad requests from being passed to someone else. It also checks who the user may contact and what information they may disclose.

create-handoff — Skill for Claude Code and Codex by SarutobiSasuke8

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.

Any agent

npx skills add SarutobiSasuke8/agent-handoff-mcp --skill create-handoff

Clone the repo

git clone --depth 1 https://github.com/SarutobiSasuke8/agent-handoff-mcp

Made for: Claude Code, Codex.

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/sarutobisasuke8/agent-handoff-mcp/create-handoff/github.svg)](https://agentmods.dev/skills/sarutobisasuke8/agent-handoff-mcp/create-handoff)

Your own site

<a href="https://agentmods.dev/skills/sarutobisasuke8/agent-handoff-mcp/create-handoff"><img src="https://agentmods.dev/badge/skills/sarutobisasuke8/agent-handoff-mcp/create-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/sarutobisasuke8/agent-handoff-mcp/create-handoff"><img src="https://agentmods.dev/badge/skills/sarutobisasuke8/agent-handoff-mcp/create-handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 552 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	$0.00036	$0.00552
Opus 5.5	$0.00014	$0.00221
Sonnet 5.5	$0.00007	$0.00110
Haiku 4.5	$0.00004	$0.00055

Measured 6d ago against content hash fad99c908f9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

create-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 6d 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.

plugins/agent-handoff-board/skills/create-handoff/SKILL.md · 32 lines

How it starts

The opening of the file, as written. The whole thing — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create a handoff

Use this when the user wants to pass a piece of work to another agent or person: "hand this off", "ask the reviewer to", "send this to the coder agent".

Steps

Call handoff_whoami once to see who the user is on this board, who they may send to (send_to) and their disclosure ceiling. If the recipient the user names is not in send_to, say so plainly and stop. Do not try other recipients to get round it.
Draft the handoff with the user. It needs:
- recipient: an identity from send_to.
- title: one line, 160 characters at most.
- summary: what the recipient needs to know, in a few sentences.
- request: the bounded piece of work, with a clear definition of done.
- Optional context_refs and artifact_refs: branch names, issue links, file paths or log names as plain strings. The board stores them; nobody fetches or opens them.
- sensitivity: public-safe, internal (default) or restricted, never above the user's ceiling.
- priority: low, normal (default), high or urgent.
- parent_id only when this is a follow-up to an existing handoff.
Show the user the draft and ask them to confirm before sending. A handoff cannot be edited or deleted after it is sent; the sender can only cancel it while it is still queued.
Call handoff_send once. Add an idempotency_key (for example a short slug plus the date) so a retry after a network error does not create a duplicate.
Report the handoff id, recipient, status (queued) and priority.

Rules

Create one bounded handoff per piece of work. Do not split a task into many handoffs to get round size limits.
Never put passwords, tokens, keys or personal data in a handoff. References are labels, not secrets.
If the server returns a policy error (recipient not allowed, sensitivity too high, payload too large, chain too deep), report it in plain words and let the user decide. Do not retry with weaker settings without asking.
This board coordinates work. It cannot run an agent, open a link, read a file or notify anyone outside the board.

Read the full file on GitHub · 32 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.

6d ago First seen · 32 lines · 36 tokens per session scan A fad99c908f9e

Subscribe to this mod's changes

create-handoff is a skill published in the GitHub repository SarutobiSasuke8/agent-handoff-mcp (2 stars, last pushed today), licensed Apache-2.0. It adds 36 tokens to every session and 552 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 2026-10-11.

Multi-Agent Project management TypeScript ai-agents mcp model-context-protocol sqlite

pm

Project Manager skill. One orchestrator session drives eight subagent roles -- planner, plan-reviewer, doer, reviewer, deployer, integ-test-runner, ci-watcher, harvester -- through cycles of Plan, Develop, Test, and Harvest across one or more parallel tracks in isolated git worktrees, running each task on a…

Apra-Labs/apra-fleet · 120 tokens

fleet-sprint-cli

How to launch and supervise apra-fleet's autonomous sprint workflow from the CLI (apra-fleet workflow fleet-sprint) -- the --issue/--members/--branch/--base flag contract, the preconditions to check first, how to launch it as a detached process, and how to watch it via its dashboard. Trigger before running apra-fleet…

Apra-Labs/apra-fleet · 85 tokens

auto-sprint-args

How to construct and pass correct arguments to the auto-sprint workflow -- the required issues+branch fields, optional goal/maxcycles/basebranch/requirementsFile, JSON-object (not string) shape, and common launch mistakes. Trigger when preparing to launch or invoke auto-sprint.

Apra-Labs/apra-fleet · 61 tokens

create-handoff