handoff

handoff is a skill for Claude Code, Codex from ykorovko/dotagents. It costs 41 tokens per session (504 once invoked), scanned A, original, MIT.

A short document that records the current goal, progress, decisions, checks, and next step so another coding agent or session can continue the work.

In plain words
What is it for?
Use it when someone explicitly asks for a handoff, continuation brief, or context transfer between coding sessions.
Why use it?
It prevents the next agent from having to reread the entire conversation or guess what remains. It also records missing context and repository state when relevant.

Skill for Claude CodeCodex

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

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.

agentmods badge for handoff

README.md
[![agentmods](https://agentmods.dev/badge/skills/ykorovko/dotagents/handoff.svg)](https://agentmods.dev/skills/ykorovko/dotagents/handoff)
Your own site
<a href="https://agentmods.dev/skills/ykorovko/dotagents/handoff"><img src="https://agentmods.dev/badge/skills/ykorovko/dotagents/handoff.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 504 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 $0.00041 $0.00504
Opus 5 $0.00020 $0.00252
Sonnet 5 $0.00008 $0.00101
Haiku 4.5 $0.00004 $0.00050

Measured 3d ago against content hash 697092a5e525, 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.

skills/handoff/SKILL.md · 25 lines

What it actually says

Handoff

Write a short handoff that lets a fresh agent continue without rereading the current conversation.

Put it somewhere the next session can open. Use a location supplied by the user first. If both sessions share a filesystem, create a unique file in the operating system's temporary directory using the environment's temp facility. Do not hard-code a path. For an isolated or remote harness, use durable artifact storage if the harness provides it. If nothing will persist between sessions, include the full handoff in the response and say that no file was created. Do not write it into the workspace unless the user asks.

Start with the user's goal and where the work stands. Keep the decisions and constraints that still affect the task. Note what is finished, what remains, which checks have run, and anything blocking progress. End with the next concrete action. If earlier parts of the conversation are unavailable, name the missing context instead of guessing.

For repository work, include the repository name or remote, branch, HEAD commit, base or upstream branch when known, and the state of any uncommitted work. Add the workspace root when it helps. Prefer paths relative to the repository so they still work after moving the project to another machine.

Point to existing plans, specifications, ADRs, issues, commits, diffs, and generated files by path or URL. Do not copy their contents into the handoff.

Add a section called Suggested skills. Name only skills known to be available to the next agent, and say briefly why each one would help. Installing or naming a skill does not load it automatically.

Remove secrets, credentials, personal data, and private context unrelated to the task.

If the user describes what the next session will focus on, shape the handoff around that focus. After writing a file, return its absolute path or artifact link with a one-sentence summary. If the handoff is inline, label it so the user can copy it into the next session. Creating the document does not start or message another agent unless the user asks for that separately.

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 25 lines · 41 tokens per session scan A 697092a5e525

Subscribe to this mod's changes

handoff is a skill published in the GitHub repository ykorovko/dotagents (0 stars, last pushed 3d ago), licensed MIT. It adds 41 tokens to every session and 504 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 2026-08-31.

Related

Other skills, from other repositories

skillshare-changelog

Generate CHANGELOG.md entry from recent commits in conventional format. Also syncs the website changelog page. Use this skill whenever the user asks to: generate a changelog, document what changed between tags, or create a new CHANGELOG entry. If you see requests like "write the changelog for v0.17", "what changed…

runkids/skillshare · 134 tokens

skillshare-update-docs

Update website docs to match recent code changes, cross-validating every flag against source. Use this skill whenever the user asks to: update documentation, sync docs with code, document a new flag or command, fix stale docs, or update the README. This skill covers all website/docs/ categories (commands, reference…

runkids/skillshare · 123 tokens

cloudbase-document-database-in-wechat-miniprogram

Use CloudBase document database WeChat MiniProgram SDK to query, create, update, and delete data. Supports complex queries, pagination, aggregation, and geolocation queries.

TencentCloudBase/CloudBase-AI-Toolkit · 46 tokens

ulw-research

Team-first maximum-saturation research orchestration. ALWAYS asks which final format to render (PDF+DOCX default), then stands up a max-size cooperating team (teamcreate): one member per axis plus skeptic/red-team members for ultradebate/hyperdebate cross-critique, explore/librarian lanes, live journaling, an EXPAND…

code-yeongyu/oh-my-openagent · 224 tokens

dashscope

DashScope (Alibaba Cloud Bailian / 阿里云百炼) integration — image generation (qwen-image-2.0-pro), text-to-speech (qwen3-tts-flash), and ASR with word-level timestamps (qwen3-asr-flash-filetrans). Use when generating images via Qwen-Image, narrating via Qwen-TTS, or transcribing with word-level timestamps via Qwen-ASR.

calesthio/OpenMontage · 93 tokens

visual-qa

MUST USE after building/changing any UI or when asked whether a page, component, or TUI looks right. Rigorous visual QA across web/page, terminal, and paginated-document surfaces. Prefer browser:control-in-app-browser for unauthenticated browser/page QA in Codex, then Playwright/agent-browser/dev-browser. Captures…

code-yeongyu/oh-my-openagent · 161 tokens