handoff

handoff is a command for Claude Code from dsifry/metaswarm. It costs 33 tokens per session (572 once invoked), scanned A, original, MIT.

A command that records the current coding session in a self-contained Markdown handoff document for another agent. The document includes the goal, decisions, files, plans, repository state, and remaining work.

In plain words
What is it for?
Use it when pausing or transferring a task, especially when the work has several design decisions, uncommitted changes, plans, or required files to inspect.
Why use it?
It prevents the next agent from having to reconstruct the work from scattered conversation and project files.

Command for Claude Code

Part of the metaswarm plugin — 14 skills, 16 commands, 19 agents, 2 hooks shipped together

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.

agentmods
npx agentmods add commands/dsifry/metaswarm/handoff
Clone the repo
git clone --depth 1 https://github.com/dsifry/metaswarm

Made for: Claude Code.

Or install metaswarm, the plugin that ships this one along with the rest of its 14 skills, 16 commands, 19 agents, 2 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/dsifry/metaswarm/handoff.svg)](https://agentmods.dev/commands/dsifry/metaswarm/handoff)
Your own site
<a href="https://agentmods.dev/commands/dsifry/metaswarm/handoff"><img src="https://agentmods.dev/badge/commands/dsifry/metaswarm/handoff.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 572 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00033 $0.00572
Opus 5 $0.00016 $0.00286
Sonnet 5 $0.00007 $0.00114
Haiku 4.5 $0.00003 $0.00057

Measured 3d ago against content hash 3213526222db, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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/commands/handoff.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Handoff

Analyze the current session and everything we are working on, then write a single comprehensive markdown document containing all the context, files, specs, designs, plans, and decisions a fresh agent with no prior context would need to get fully up to speed and take action. Finish by emitting one unambiguous handoff sentence.

Usage

/handoff

Optionally pass focus hints:

/handoff focus on the auth refactor only

What This Does

Invokes the metaswarm handoff skill, which:

  1. Reconstructs the objective — what the user is trying to accomplish, the Definition of Done, and why.

  2. Loads persisted state — folds in .beads/plans/active-plan.md, .beads/context/*, and bd prime --work-type recovery if present.

  3. Establishes current status — done/verified vs. in-progress vs. not-started, plus the real working-tree state (git status, recent commits, unpushed/uncommitted changes).

  4. Identifies required reading — every spec, design, plan, code file:line, and test the next agent must read, with why and what to look for.

  5. Writes the document to docs/handoffs/handoff-<YYYY-MM-DD-HHmm>.md.

  6. Emits one sentence of the exact form:

    Read docs/handoffs/handoff-2026-06-17-1432.md and do <concrete next action>.
    

Output Contract

  • A self-contained handoff document (so the next agent needs to read only that one file).
  • Exactly one closing sentence: Read <path>.md and do <YYY>. where <YYY> is one concrete, immediately-actionable next step — never "continue the work".

When to Use

  • A session is ending or context is about to be compacted.
  • Switching sessions, machines, or agents mid-task.
  • Pausing complex work you want to resume cleanly later.
  • The user explicitly asks for a handoff.
  • skills/handoff/SKILL.md — the full skill definition (method, document template, anti-patterns).
  • /prime — loads context into a session (the inverse of this command).
  • /self-reflect — captures durable learnings into the knowledge base (vs. this task's transient state).

Read the full file on GitHub · 53 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. 3d ago First seen · 53 lines · 33 tokens per session scan A 3213526222db

Subscribe to this mod's changes

handoff is a command published in the GitHub repository dsifry/metaswarm (407 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 572 once invoked, about $0.0002 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 2026-08-30.