handoff

handoff is a command for Claude Code from JobsHwang/skills. It costs 38 tokens per session (305 once invoked), scanned A, original, MIT.

A command that prepares a concise handoff for another coding agent or session. The handoff records the current objective, confirmed decisions, relevant files, unfinished work, risks, and unverified claims.

In plain words
What is it for?
Use it when transferring work, continuing in a new session, or preparing context for review.
Why use it?
It prevents the next agent from having to reconstruct the task from the full conversation.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

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 commands/jobshwang/skills/handoff
Clone the repo
git clone --depth 1 https://github.com/JobsHwang/skills

Made for: Claude Code.

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/commands/jobshwang/skills/handoff.svg)](https://agentmods.dev/commands/jobshwang/skills/handoff)
Your own site
<a href="https://agentmods.dev/commands/jobshwang/skills/handoff"><img src="https://agentmods.dev/badge/commands/jobshwang/skills/handoff.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 305 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 $0.00038 $0.00305
Opus 5 $0.00019 $0.00152
Sonnet 5 $0.00008 $0.00061
Haiku 4.5 $0.00004 $0.00030

Measured 5d ago against content hash e96704c7b02d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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.

adapters/opencode/commands/handoff.md · 27 lines

What it actually says

The user explicitly invoked /handoff.

Invocation arguments: $ARGUMENTS

Handoff

Create one concise handoff that lets a fresh agent continue without reconstructing the conversation.

  1. Treat invocation arguments or accompanying user text as the next agent's objective. If none is provided, infer the immediate next objective from the conversation.
  2. Inspect only the repository state needed to distinguish completed, pending, and unverified work.
  3. Write the handoff to the operating system's temporary directory, never into the workspace. Use a short unique filename ending in .md.
  4. Include:
    • next objective;
    • current state;
    • confirmed decisions and constraints;
    • artifacts to read first, using absolute paths or stable URLs;
    • open work, risks, and unverified claims;
    • suggested explicit Skills, only when they materially help the next step.
  5. Reference existing Specs, PRDs, ADRs, commits, and diffs instead of duplicating their contents.
  6. Do not invent progress, decisions, test results, or repository state. Redact secrets and sensitive personal information.
  7. Do not implement, review, commit, or modify workspace files while handing off.
  8. Return the absolute handoff path and one sentence describing what the next agent should do.
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 · 27 lines · 38 tokens per session scan A e96704c7b02d

Subscribe to this mod's changes

handoff is a command published in the GitHub repository JobsHwang/skills (2 stars, last pushed 3d ago), licensed MIT. It adds 38 tokens to every session and 305 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.