handoff

A handoff-document tool for passing unfinished work to a fresh coding-agent session. It creates, continues, or closes short-lived files stored under `.ai-sessions/handoffs/`.

In plain words
What is it for?
Use it to prepare a next-session brief, load an existing handoff, or clean up a consumed handoff document.
Why use it?
It preserves the immediate context needed to continue work without relying on the previous conversation. Closing the handoff removes it once it is no longer needed.

Skill for Claude CodeCodex

Part of the bpe plugin — 13 skills, 3 agents 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/masonegger/bpe-claude-code-plugin/handoff
Any agent
npx skills add MasonEgger/bpe-claude-code-plugin --skill handoff
Clone the repo
git clone --depth 1 https://github.com/MasonEgger/bpe-claude-code-plugin

Made for: Claude Code, Codex.

Or install bpe, the plugin that ships this one along with the rest of its 13 skills, 3 agents.

Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,159 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 $0.00017 $0.02159
Opus 5 $0.00009 $0.01079
Sonnet 5 $0.00003 $0.00432
Haiku 4.5 $0.00002 $0.00216

Measured 3d ago against content hash 16d9b1fc6ea1, 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.

bpe/skills/handoff/SKILL.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Handoff Command

Manage forward-looking handoff documents that let a fresh agent pick up where the current conversation left off. Handoffs are short-lived and live under .ai-sessions/handoffs/; they are not session summaries. For durable, backwards-looking session records, use /bpe:session-summary instead.

This command has three subcommands:

  • create [focus]: write a new handoff document. The optional focus describes what the next session will work on; it tailors the handoff toward that thread.
  • continue: read an existing handoff and prime the current conversation with its contents. Does not delete the file.
  • close: delete a consumed handoff file. Run this once the work described in the handoff has been picked up and the file is no longer useful.

Argument Routing

Parse $ARGUMENTS:

  • If the first token is create, run Create Mode. Treat the remainder of the argument string as the optional focus.
  • If the first token is continue, run Continue Mode. Ignore any trailing tokens.
  • If the first token is close, run Close Mode. Ignore any trailing tokens.
  • If $ARGUMENTS is empty, default to Create Mode with no focus.
  • Otherwise, treat the entire argument string as a focus description and run Create Mode. This preserves back-compatibility with the original /bpe:handoff <focus> form.

State the routed mode in user-facing text before proceeding (e.g. "Running handoff in create mode with focus: deck polish.").


Create Mode

Write a handoff document so a fresh agent can continue the current work without starting from scratch. The handoff is forward-looking and short-lived.

Step 1: Generate the Path

Handoffs live alongside session summaries under .ai-sessions/, in a handoffs/ subdirectory. This keeps them in the project tree (so the next agent can find them without being told a path) while keeping them separable from durable summaries.

mkdir -p .ai-sessions/handoffs
date +%Y%m%d-%H%M

Then build the path: .ai-sessions/handoffs/handoff-{timestamp}-{slug}.md.

Read the full file on GitHub · 175 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. 3d ago First seen · 175 lines · 17 tokens per session scan A 16d9b1fc6ea1

Subscribe to this mod's changes

handoff is a skill published in the GitHub repository MasonEgger/bpe-claude-code-plugin (7 stars, last pushed 11d ago), licensed MIT. It adds 17 tokens to every session and 2,159 once invoked, about $0.0001 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

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