handoff

handoff is a skill for Claude Code, Codex from cookys/autopilot. It costs 127 tokens per session (1,312 once invoked), scanned A, original, MIT.

A session handoff document records the current state of unfinished coding work so another session can continue it.

In plain words
What is it for?
It helps save and resume work by recording the branch, recent changes, completed and unfinished tasks, decisions, next commands, and verification steps.
Why use it?
It prevents losing context when a session ends or its context becomes full. It also gives the next session clear decisions and starting steps.

Skill for Claude CodeCodex

Part of the autopilot plugin — 32 skills, 3 agents, 7 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/cookys/autopilot/handoff
Any agent
npx skills add cookys/autopilot --skill handoff
Clone the repo
git clone --depth 1 https://github.com/cookys/autopilot

Made for: Claude Code, Codex.

Or install autopilot, the plugin that ships this one along with the rest of its 32 skills, 3 agents, 7 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/cookys/autopilot/handoff.svg)](https://agentmods.dev/skills/cookys/autopilot/handoff)
Your own site
<a href="https://agentmods.dev/skills/cookys/autopilot/handoff"><img src="https://agentmods.dev/badge/skills/cookys/autopilot/handoff.svg" alt="Measured on agentmods" height="20"></a>
Per session 127 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,312 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 $0.00127 $0.01312
Opus 5 $0.00063 $0.00656
Sonnet 5 $0.00025 $0.00262
Haiku 4.5 $0.00013 $0.00131

Measured 4d ago against content hash c09de03465dd, 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 4d 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.

platforms/codex/plugin/skills/handoff/SKILL.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

handoff

Mid-work session continuation handoff.

Write Mode

Triggered by "寫 handoff", "寫 handover", "ctx 太滿", "context 快滿", "clear session 後繼續", "write a handoff", or "hand off to the next session".

  1. Collect State Mechanically: Run commands to collect context:

    git branch --show-current
    git log --oneline -5
    git status --porcelain | head -20
    git stash list | head -3
    ls docs/projects/ | grep -v _archive | head
    # Also check open task list if the harness shows one
    
  2. Determine Handoff Path:

    • Active project: docs/projects/<project>/HANDOFF.md
    • No project structure: docs/HANDOFF.md
    • Repo not writable or no repo: ~/.autopilot/handoff-manual/<repo-or-cwd-name>.md
  3. Generate Document: If HANDOFF.md already exists, REPLACE it (a handoff is a snapshot, not a log) and note the replacement in the reply. Write verbatim:

    ## 目標
    [One-sentence goal of the interrupted work]
    
    ## 現況
    [Branch, last commit SHA+subject, dirty files, what is DONE vs IN-FLIGHT]
    
    ## 已決事項(不重議)
    - [Decision 1] — [One-line rationale]
    - [Decision 2] — [One-line rationale]
    
    ## 下一步
    1. [CONCRETE command or file edit to start with]
    2. [Subsequent concrete step]
    
    ## 驗證方式
    [Commands and expected output proving work is done]
    
    ## Read-order
    1. /absolute/path/to/file1 — [Why to read first]
    2. /absolute/path/to/file2 — [Why to read second]
    3. /absolute/path/to/file3 — [Why to read third]
    
    ## 陷阱
    - [Gotchas discovered this session that would burn the next session]
    

3.5. Route the durable content out (a handoff is a snapshot and gets deleted — Resume Mode step 5. Anything left only in it is scheduled for destruction):

Walk the document you just wrote 段-by-段 and ask of each one:

「這條超出本次交接嗎?」

A 段 that is only true of this interruption (current branch, in-flight diff, the next command) stays in HANDOFF.md and dies with it — correct. A 段 that would still be worth knowing on a different task is durable content sitting in a temporary file, and must be routed now, per the destination table in references/knowledge-routing.md §3:

Read the full file on GitHub · 111 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. 4d ago First seen · 111 lines · 127 tokens per session scan A c09de03465dd

Subscribe to this mod's changes

handoff is a skill published in the GitHub repository cookys/autopilot (11 stars, last pushed today), licensed MIT. It adds 127 tokens to every session and 1,312 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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens