What is agent-handoff?

A structured note for transferring an unfinished coding session to another agent. It records the current state, remaining work, changed files, open questions, and checks to run.

Use it when switching between agents, ending a long task, or asking another coding system to continue the work.

It prevents the next agent from losing important context or repeating work when a session changes hands.

agent-handoff — Skill for Claude Code and Codex by katalalab

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 katalalab/katala-os --skill agent-handoff

Clone the repo

git clone --depth 1 https://github.com/katalalab/katala-os

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/katalalab/katala-os/agent-handoff/github.svg)](https://agentmods.dev/skills/katalalab/katala-os/agent-handoff)

Your own site

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

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 418 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	$0.00055	$0.00418
Opus 5	$0.00028	$0.00209
Sonnet 5	$0.00011	$0.00084
Haiku 4.5	$0.00006	$0.00042

Measured 9d ago against content hash 3b34ecfb9103, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

agent-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 9d 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/agent-handoff/SKILL.md · 55 lines

What it actually says

agent-handoff — structured agent context transfer

Produces a handoff note at ~/work/docs/handoffs/<topic>/<date>-handoff.md that lets any receiving agent resume without reading the full conversation.

When to use

"手を離す前に引き継ぎ書いて"
"Codex に渡したい、ハンドオフして"
"このセッションを Antigravity で続けたい"
End-of-session wrap-up for long tasks

Do not use for:

Simple status summaries (use /session-report instead)
PR descriptions (use commit-commands:commit-push-pr)

Output structure

# Handoff: <topic>
Date: YYYY-MM-DD  Agent: <source>  Target: <destination>

## State
What is done, what is in-progress, what is blocked.

## Minimum Restart Path
Ordered steps for the receiving agent to pick up correctly.

## Open Questions
Decisions deferred to the receiving agent or operator.

## Files Changed
Paths + one-line summaries.

## Verification Commands
Narrowest real commands to confirm health.

How to invoke

Read the current conversation state and any open task lists.
Write the handoff file under ~/work/docs/handoffs/<topic>/.
Print the absolute path and the Minimum Restart Path to the terminal.
If routing to Codex: suggest codex --context <path> invocation.

Hard-rule reminders

Never include secrets, tokens, or credentials in the handoff file.
State verified vs. unverified scope separately.
Include a rollback command for any destructive change performed in the session.

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.

9d ago First seen · 55 lines · 55 tokens per session scan A 3b34ecfb9103

Subscribe to this mod's changes

agent-handoff is a skill published in the GitHub repository katalalab/katala-os (2 stars, last pushed 9d ago), licensed MIT. It adds 55 tokens to every session and 418 once invoked, about $0.0003 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.

Building agents Productivity

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 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

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

agent-handoff