handoff

handoff is a skill for Claude Code from allemaar/open-skills. It costs 116 tokens per session (3,807 once invoked), scanned A, original, Apache-2.0.

A structured brief that gives a new coding-agent session the information needed to continue a task. It combines machine-readable details with notes, sources, and execution guidance.

In plain words
What is it for?
Use it to dispatch a self-contained task, hand work to a fresh agent, move an unfinished task to a new session, or divide a multi-step task into parallel parts.
Why use it?
It avoids losing the task's context when work moves to another session or agent. It can also split a larger task into separate pieces for fresh agents.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions Claude Code; mentions Codex.

Part of the open-skills plugin — 70 skills shipped together

Good fit Use it to dispatch a self-contained task, hand work to a fresh agent, move an unfinished task to a new session, or divide a multi-step task into parallel parts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/allemaar/open-skills/handoff
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.

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

Made for: Claude Code.

Or install open-skills, the plugin that ships this one along with the rest of its 70 skills.

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/allemaar/open-skills/handoff/github.svg)](https://agentmods.dev/skills/allemaar/open-skills/handoff)
Your own site
<a href="https://agentmods.dev/skills/allemaar/open-skills/handoff"><img src="https://agentmods.dev/badge/skills/allemaar/open-skills/handoff/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for handoff

Your own site · 80×15
<a href="https://agentmods.dev/skills/allemaar/open-skills/handoff"><img src="https://agentmods.dev/badge/skills/allemaar/open-skills/handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 116 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,807 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00116 $0.03807
Opus 5 $0.00058 $0.01903
Sonnet 5 $0.00023 $0.00761
Haiku 4.5 $0.00012 $0.00381

Measured 12d ago against content hash b89847abc1a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, 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 12d 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 · 270 lines

How it starts

The opening of the file, as written. The whole thing — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/handoff

Generates a structured handoff brief: YAML frontmatter (Obsidian-readable, vault-schema-compliant) + Obsidian-flavored markdown body containing YON-tagged structured blocks. The brief is the work item a fresh agent in a new session can pick up and execute autonomously.

Structured execution spec: protocol.yon. It carries the workflow steps, the verify and sources gates, and the rules as validatable records; this file is the explanation. Keep the two in sync — edit one, update the other and refresh the @STAMP date.

When to use

  • UC1 — Dispatch a self-contained task to a fresh agent (agent profile)
  • UC4 — Dispatch a multi-step task that needs to be split into parallel sub-tasks (orchestrator profile)
  • UC3 — Switch the current session to a fresh one carrying in-flight state (new-session profile)

For UC2 (turn the current session into pure orchestrator mode), use /orchestrate-mode instead — that's a behavior switch, not a handoff artifact.

Output

Each handoff produces:

  • A vault file (canonical) at $VAULT/Handoffs/{project}/{YYYY-MM-DD}-{slug}.md (set $VAULT to your Obsidian vault root)
  • A chat surface (paste-convenience): full block if file < 500 lines; otherwise summary (first 30 lines) + 📄 Full brief: <path>

For multi-handoff (count=N): N files + a numbered index in chat (no per-brief content in chat).

The cold agent writes its retro to Handoffs/{project}/retros/{YYYY-MM-DD}-{slug}-retro.md (canonical file) AND emits it as a chat block (paste-back surface). Bidirectional brief↔retro linking is automatic via Obsidian's wikilink graph.

Workflow

1. Determine invocation path

Path Trigger Behavior
1. One-shot complete /handoff agent task="..." where="..." evidence="..." acceptance="..." verify="..." Parse, validate required fields present, write file, emit chat surface.
2. One-shot partial /handoff agent task="..." (missing required) Parse, identify gaps, ask ONLY for missing required, then write.
3. Interactive /handoff (no args) Full Q&A from "What kind?" through all required.
4. Multi one-shot /handoff count=3 Each of N briefs runs independent profile-selection + Q&A. Emits N files + numbered index in chat.
5. Multi interactive /handoff then "I have 3 tasks" Detect intent, ask "How many?", then run Path 3 N times independently.
6. Orchestrator subtasks orchestrator profile selected If subtasks field unspecified → LLM auto-decomposes, surfaces for review. If specified → LLM validates 5 checks; pass = proceed; fail = findings + auto-/insight-assess.

Read the full file on GitHub · 270 lines

Files

What ships with it

4 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. 12d ago First seen · 270 lines · 116 tokens per session scan A b89847abc1a6

Subscribe to this mod's changes

handoff is a skill published in the GitHub repository allemaar/open-skills (14 stars, last pushed 2d ago), licensed Apache-2.0. It adds 116 tokens to every session and 3,807 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.