handoff

handoff is a skill for Claude Code, Codex from dsifry/metaswarm. It costs 40 tokens per session (2,188 once invoked), scanned A, original, MIT.

A handoff process that records the current coding session in one self-contained Markdown file for another agent to continue.

In plain words
What is it for?
Use it to create a dated handoff document containing the needed context and a single clear instruction for the next agent.
Why use it?
It prevents important context, decisions, and next steps from being lost when a session ends, changes machine, or runs out of context.

Skill for Claude CodeCodex

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 skills/dsifry/metaswarm/handoff
Any agent
npx skills add dsifry/metaswarm --skill handoff
Clone the repo
git clone --depth 1 https://github.com/dsifry/metaswarm

Made for: Claude Code, Codex.

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/skills/dsifry/metaswarm/handoff.svg)](https://agentmods.dev/skills/dsifry/metaswarm/handoff)
Your own site
<a href="https://agentmods.dev/skills/dsifry/metaswarm/handoff"><img src="https://agentmods.dev/badge/skills/dsifry/metaswarm/handoff.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,188 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 5.1 $0.00040 $0.02188
Opus 5 $0.00020 $0.01094
Sonnet 5 $0.00008 $0.00438
Haiku 4.5 $0.00004 $0.00219

Measured 6d ago against content hash 8d696f1ee2ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 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.

skills/handoff/SKILL.md · 204 lines

How it starts

The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Handoff Skill

Capture everything a fresh agent with zero prior context needs to resume the current work, write it to a single self-contained markdown document, and hand it off with one unambiguous sentence:

Read docs/handoffs/<file>.md and do <the next concrete action>.

Use this when a session is ending, when context is about to be compacted, when you are switching machines or sessions, or when the user explicitly asks for a handoff. The goal is zero context loss: the receiving agent should be able to act correctly after reading exactly one file.


Output Contract

This skill produces exactly two things:

  1. A handoff document at docs/handoffs/handoff-<YYYY-MM-DD-HHmm>.md (created if the directory does not exist). It is comprehensive, self-contained, and links to — or quotes — every artifact the next agent must read.

  2. A single closing sentence, and nothing else after the document is written, of the exact form:

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

    Where <YYY> is one concrete, actionable next step (an imperative, not a vague theme). Good: "implement the parseConfig validation in src/config.ts:84 and make tests/config.test.ts pass". Bad: "continue the work" / "look into the config stuff".

The sentence is the deliverable the user hands to the next agent. The document is what makes that sentence safe to follow.


Method

Step 1 — Reconstruct what we are working on

Review the session to date and answer, concretely:

  • Objective: What is the user actually trying to accomplish? State it in one or two sentences.
  • Definition of Done: What does "finished" look like? Enumerate verifiable acceptance criteria if any exist.
  • Why: The motivation/problem behind the task, so the next agent does not re-litigate settled decisions.

Pull from: the user's original request, any GitHub Issue (gh issue view <n>), the design/plan docs, and the arc of the conversation.

Read the full file on GitHub · 204 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. 6d ago First seen · 204 lines · 40 tokens per session scan A 8d696f1ee2ea

Subscribe to this mod's changes

handoff is a skill published in the GitHub repository dsifry/metaswarm (409 stars, last pushed 2mo ago), licensed MIT. It adds 40 tokens to every session and 2,188 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.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

agent-memory

../../../engineering/agent-memory/skills/agent-memory/SKILL.md.

alirezarezvani/claude-skills · 0 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens