handoff

handoff is a skill for Claude Code from Tradebaas/Groundwork. It costs 92 tokens per session (952 once invoked), scanned A, original, MIT.

A handoff writer that records the current work state in `docs/state/STATE.md` so another session or person can continue. A handoff summarizes status, checks, the exact next action, and anything blocking progress.

In plain words
What is it for?
Use it at the end of a ticket, before clearing a session, at a milestone, or when someone requests a checkpoint. It can create the state file when the project does not have one and can add extra audit details for a transfer.
Why use it?
It removes the need for the next worker to reconstruct the plan from chat history. It gives a fresh session one trusted place to find what is true and what to do next.

Skill for Claude Code

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

Part of the vibe plugin — 13 skills, 3 agents, 1 hook shipped together

Good fit Use it at the end of a ticket, before clearing a session, at a milestone, or when someone requests a checkpoint. It can create the state file when the project does not have one and can add extra audit details for a transfer.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tradebaas/groundwork/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 Tradebaas/Groundwork --skill handoff
Clone the repo
git clone --depth 1 https://github.com/Tradebaas/Groundwork

Made for: Claude Code.

Or install vibe, the plugin that ships this one along with the rest of its 13 skills, 3 agents, 1 hook.

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/tradebaas/groundwork/handoff/github.svg)](https://agentmods.dev/skills/tradebaas/groundwork/handoff)
Your own site
<a href="https://agentmods.dev/skills/tradebaas/groundwork/handoff"><img src="https://agentmods.dev/badge/skills/tradebaas/groundwork/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/tradebaas/groundwork/handoff"><img src="https://agentmods.dev/badge/skills/tradebaas/groundwork/handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 952 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 $0.00092 $0.00952
Opus 5.5 $0.00037 $0.00381
Sonnet 5.5 $0.00018 $0.00190
Haiku 4.5 $0.00009 $0.00095

Measured 5d ago against content hash 61a1d70a84ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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.

plugins/vibe/skills/handoff/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

handoff: the repo must speak for itself

A fresh session reads docs/state/STATE.md first, so the handoff has one home: STATE.md. Never a second document, never the chat. Two depths, same file:

  • Session handoff, the default: park the current train of work so a fresh, cheap session resumes it. Write from what is already in the conversation; open a file only for a fact that is genuinely missing.
  • Transfer handoff, when a person or tool changes, at a milestone, or on request: the same block, plus the audit below, because the reader has none of your context.

No STATE.md in this project? Say so in one line and write the handoff block into a new docs/state/STATE.md with the shape below; a project without one gets one the first time it needs it.

The block at the top of STATE.md, literally true right now

  • Status / Phase / Branch / HEAD current.
  • Gates: the real state with the number: "checks green, tests 42/42, CI green @ ".
  • Now ▶ the single exact next action, concrete enough to start cold. Not "continue work" but "wire the Stop hook into settings.json per the plan in the log entry below".
  • Blocked on: what waits on the owner or an external thing, else clear it.

Then one dated log entry, newest first, tight and skimmable: Done (a few bullets), Docs touched (links, never restated content), Lessons (only what a fresh session would otherwise rediscover the hard way: a dead end, a non-obvious constraint, a decision with its reason), Stopped at (mirrors Now ▶).

Route facts to their owner, not into the handoff: a decision to docs/decisions/, deferred work to a defer: marker plus docs/state/DEBT.md, new scope to docs/state/INTAKE.md, a correction the owner gave twice to INTAKE.md as an improvement row. Keep STATE.md under 150 lines; overflow moves the oldest log entries to docs/state/log/YYYY-MM.md. Keep secrets, tokens, credential URLs and personal data out: name where a credential lives, never its value. Run node checks/check.mjs if the project has it, so you never hand off a red repo.

Read the full file on GitHub · 67 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 · 67 lines · 92 tokens per session scan A 61a1d70a84ce

Subscribe to this mod's changes

handoff is a skill published in the GitHub repository Tradebaas/Groundwork (2 stars, last pushed 6d ago), licensed MIT. It adds 92 tokens to every session and 952 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-11.

Related

Other skills, from other repositories

autonomous-build

Execute a local task register with requirement tracing, verification, review, and refinement.

bnet47/codexicon · 20 tokens

keel-team

OWNER-only setup wizard for a REAL human team (different people, different machines) — declare the owner (arm owner-guard), register members (@tags), seed lanes + author folders + the comprehension protocol, size the caps, pick the §6 contribution model + host wall. Packages the existing Multi-user playbook into one…

muratsilahtaroglu/claude-code-starter-kit · 77 tokens

sdd-workflow

Guide a project with Spec-Driven Development (SDD) discipline - idea, approved spec, consistent plan, tasks, a gate that verifies approval and consent, implementation, validation, and logbook. Bilingual EN/ES. Use when the user wants to start, spec, plan, implement, or validate work with SDD, or mentions specs, plans…

juanklagos/spec-driven-development-template · 84 tokens

select-build-target

Pull the next source contract to build from the pending backlog, respecting outside-in dependency order.

nullhack/temple8 · 22 tokens

keel-adopt

Adopt Keel's discipline into an EXISTING project (brownfield) — inventory, non-destructive merge, back-fill docs from real code, migrate security. Never overwrites.

muratsilahtaroglu/claude-code-starter-kit · 42 tokens

scaffold

Create, standardize, or audit a Howells project. Covers repo shape, tooling, package boundaries, UI, data, AI, agent workflow, deployment, and launch checks.

howells/scaffold · 39 tokens