handoff

handoff is a skill for Claude Code from ohm41321/luciazero. It costs 86 tokens per session (923 once invoked), scanned A, original, MIT.

A work-handoff skill that writes a compact state file for unfinished repository work. It records the goal, completed evidence, current files, verification commands, next action, open hypotheses, and discovered risks.

In plain words
What is it for?
Use it when ending an incomplete task, changing coding tools or agents, or asking someone else to continue the work.
Why use it?
It prevents the next session or agent from having to reconstruct context from scratch. It also makes the exact next step and remaining checks explicit when work is interrupted.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code; mentions Codex.

Part of the luciazero plugin — 15 skills, 1 agent, 7 hooks shipped together

Good fit Use it when ending an incomplete task, changing coding tools or agents, or asking someone else to continue the work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ohm41321/luciazero/handoff-v1.5.0
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 ohm41321/luciazero --skill handoff-v1.5.0
Clone the repo
git clone --depth 1 https://github.com/ohm41321/luciazero

Made for: Claude Code.

Or install luciazero, the plugin that ships this one along with the rest of its 15 skills, 1 agent, 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/ohm41321/luciazero/handoff-v1.5.0/github.svg)](https://agentmods.dev/skills/ohm41321/luciazero/handoff-v1.5.0)
Your own site
<a href="https://agentmods.dev/skills/ohm41321/luciazero/handoff-v1.5.0"><img src="https://agentmods.dev/badge/skills/ohm41321/luciazero/handoff-v1.5.0/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/ohm41321/luciazero/handoff-v1.5.0"><img src="https://agentmods.dev/badge/skills/ohm41321/luciazero/handoff-v1.5.0.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 923 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.
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 $0.00086 $0.00923
Opus 5 $0.00043 $0.00462
Sonnet 5 $0.00017 $0.00185
Haiku 4.5 $0.00009 $0.00092

Measured 5d ago against content hash 02dd2c2003f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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.

migrations/handoff-v1.5.0.SKILL.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Handoff — state that survives the session

/retro records permanent lessons; this records transient state. A good capsule lets a stranger (including future-you with zero context) type one command and be productive in two minutes. A stale capsule is worse than none — so capsules are consumed and deleted, never accumulated.

1. Write the capsule

Create HANDOFF.md at the repo root:

# Handoff — <date>

## Goal
<the original request, one paragraph, verbatim enough to re-anchor>

## State
- Done: <what is finished, and the verify evidence: command → decisive line>
- In progress: <the exact piece mid-flight, and which files hold it>
- Verify: <the command(s) to run, fast and full tier>

## Next step
<ONE literal command or edit to do first — not a theme, an action>

## Open hypotheses
- H1: <suspected cause / approach> — status: <untested | supported by X | refuted by Y>

## Landmines
- <thing that looks safe but is not, discovered this session>

## Read first
- docs/lessons.md: <quote the symptom line of each lesson that touches the
  unfinished work — 1-3 entries, not the whole ledger>
- from this machine's cross-repo heuristics (do not travel with the repo):
  <copy the specific entries that apply, verbatim>

Rules:

  • The next step is literal. "Continue the refactor" is not a next step; "run pytest tests/test_auth.py -k refresh — it is the failing one" is.
  • State only what this session knows. No aspirations, no backlog — that belongs in the issue tracker.
  • Refuted hypotheses stay in the capsule — they are exactly what the next session would otherwise waste an hour re-deriving. If a lesson is permanent (true beyond this task), it also goes through /retro.
  • Uncommitted changes: say so explicitly, and name the files. The capsule must not imply a clean tree that is not clean.
  • Read first is a selection, not a copy. The repo's docs/lessons.md travels with the code — quote only the symptom lines relevant to the unfinished work so the reader knows which entries to open before touching it (rule 8, applied for them). Machine-local memory is the exception: entries in this machine's luciazero-heuristics.md (config dir) do not travel, so any that apply get copied verbatim — the capsule is their only ride. Nothing relevant? Say none — an empty section is information too.

Read the full file on GitHub · 64 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 · 64 lines · 86 tokens per session scan A 02dd2c2003f1

Subscribe to this mod's changes

handoff is a skill published in the GitHub repository ohm41321/luciazero (5 stars, last pushed today), licensed MIT. It adds 86 tokens to every session and 923 once invoked, about $0.0004 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 2026-09-05.

Related

Other skills, from other repositories