handoff

handoff is a skill for Claude Code, Codex, Cursor from AI-Learning-Gems/AI-Learning-Gems.github.io. It costs 118 tokens per session (2,419 once invoked), scanned A, original, MIT.

A guide for writing a complete handoff document so another coding agent can continue an unfinished task with the current context and decisions.

In plain words
What is it for?
Creating self-contained handoff instructions for transferring work between agents or to a subagent.
Why use it?
It reduces the chance that a new agent misses important history, reasoning, files, or next steps.

Skill for Claude CodeCodexCursor

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/ai-learning-gems/ai-learning-gems.github.io/handoff
Any agent
npx skills add AI-Learning-Gems/AI-Learning-Gems.github.io --skill handoff
Clone the repo
git clone --depth 1 https://github.com/AI-Learning-Gems/AI-Learning-Gems.github.io

Made for: Claude Code, Codex, Cursor.

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/ai-learning-gems/ai-learning-gems.github.io/handoff.svg)](https://agentmods.dev/skills/ai-learning-gems/ai-learning-gems.github.io/handoff)
Your own site
<a href="https://agentmods.dev/skills/ai-learning-gems/ai-learning-gems.github.io/handoff"><img src="https://agentmods.dev/badge/skills/ai-learning-gems/ai-learning-gems.github.io/handoff.svg" alt="Measured on agentmods" height="20"></a>
Per session 118 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,419 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 $0.00118 $0.02419
Opus 5 $0.00059 $0.01210
Sonnet 5 $0.00024 $0.00484
Haiku 4.5 $0.00012 $0.00242

Measured 5d ago against content hash 41f874cc10a4, 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 5d 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.

.cursor/skills/handoff/SKILL.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Handoff

Purpose

Write a handoff document: a single, self-contained briefing that lets a fresh agent take over an in-progress task with zero loss of context. The successor agent reads the handoff, then reads everything the handoff points it to, and ends up understanding everything the current agent understands — the goal, the history, the reasoning, the dead ends, and the next steps.

This skill produces the handoff in chat unless the user asks to save it to a file.

The handoff is NOT a status update. It is a context-transfer instrument. Its success criterion: a fresh agent that has read only the handoff plus the files/chat sections it names can continue the work without re-asking questions the current agent already answered.


The Two Hard Problems This Skill Solves

  1. Lazy reading. Successor agents skim. They read the first 100 lines of a 2000-line file, assume they understand it, and produce wrong work. The handoff MUST force full reads (see "The Full-Read Mandate" below). This is non-negotiable and must appear prominently in every handoff you write.

  2. Lossy history. A long session contains essential decisions tangled with abandoned threads. The successor needs the outcome and rationale of abandoned threads (so it does not re-propose them or contradict them) but NOT their full blow-by-blow detail. The handoff must compress abandoned threads to "what was tried, why it was dropped" while preserving live threads in full (see "Compressing History" below).


The Full-Read Mandate (Include This Verbatim in Every Handoff)

Every handoff you write MUST contain a block instructing the successor to read in full. Reproduce this block near the top of the handoff, adapted to the project:

READ DISCIPLINE — NON-NEGOTIABLE. You must read every file listed in the "Files to Read" section IN FULL before writing anything. "In full" means: call the Read tool with limit: 2000 (or higher if the file exceeds 2000 lines — check line count first with wc -l and read in 2000-line pages until you reach the end). Do NOT read partial files. Do NOT assume you understand a file from its name, its first screen, or a grep hit. If a file is 1800 lines, you read all 1800. If it is 3500 lines, you read it in two passes. You are not permitted to begin the task until every listed file has been read end to end. Reading is cheap; producing wrong work from a half-read file is expensive.

Read the full file on GitHub · 162 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. 5d ago First seen · 162 lines · 118 tokens per session scan A 41f874cc10a4

Subscribe to this mod's changes

handoff is a skill published in the GitHub repository AI-Learning-Gems/AI-Learning-Gems.github.io (22 stars, last pushed 3mo ago), licensed MIT. It adds 118 tokens to every session and 2,419 once invoked, about $0.0006 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens