sw-handoff

sw-handoff is a skill for Claude Code from anton-abyzov/specweave. It costs 48 tokens per session (1,575 once invoked), scanned A, original, MIT.

A handoff skill that creates a short, portable record of unfinished work, including the relevant task state and uncommitted changes. It removes secrets and includes instructions for resuming on another tool or machine.

In plain words
What is it for?
Use it when switching agents, machines, or sessions, or when running out of context; it releases your task claims and writes a handoff document and diff.
Why use it?
It prevents work from being lost when a session ends or moves elsewhere. The next agent can use the saved summary and diff to continue from the actual project state.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions Claude Code; mentions Codex; mentions OpenCode.

Good fit Use it when switching agents, machines, or sessions, or when running out of context; it releases your task claims and writes a handoff document and diff.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/anton-abyzov/specweave/sw-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 anton-abyzov/specweave --skill sw-handoff
Clone the repo
git clone --depth 1 https://github.com/anton-abyzov/specweave

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 sw-handoff

README.md
[![agentmods](https://agentmods.dev/badge/skills/anton-abyzov/specweave/sw-handoff/github.svg)](https://agentmods.dev/skills/anton-abyzov/specweave/sw-handoff)
Your own site
<a href="https://agentmods.dev/skills/anton-abyzov/specweave/sw-handoff"><img src="https://agentmods.dev/badge/skills/anton-abyzov/specweave/sw-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 sw-handoff

Your own site · 80×15
<a href="https://agentmods.dev/skills/anton-abyzov/specweave/sw-handoff"><img src="https://agentmods.dev/badge/skills/anton-abyzov/specweave/sw-handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,575 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 $0.00048 $0.01575
Opus 5 $0.00024 $0.00788
Sonnet 5 $0.00010 $0.00315
Haiku 4.5 $0.00005 $0.00158

Measured 6d ago against content hash fdb862b32387, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

sw-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 6d 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/sw-handoff/SKILL.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

sw-handoff — resume anywhere

No AI tool can read another's transcript. The portable thing is a ≤1-page document built from durable state: the ledger, the spec ACs, the decisions, and the exact uncommitted diff. This skill writes that document.

Run specweave --version: exit 0 → CLI path. Not found → manual path. Both emit the same sections and the same Doc format v2 footer marker, so a doc from either path is resumable by either.

Before you write

Release your claims so nothing is stuck behind a dead session: specweave task release --all-mine (manual: append one release line per task you hold — see sw-task).

CLI path

specweave handoff [<inc>] [--reason "out of tokens"] [--summary "..."] \
  [--next "..."] [--gotcha "..."] [--decision "..."] [--inline]

Writes .specweave/increments/<inc>/handoff.md + handoff.diff, points .specweave/state/handoff-latest.txt at it, and prints the doc path, the diff path and a copy-paste resume prompt. Surface that output verbatim, in order. --inline embeds the whole body in the prompt (use when moving machines). No workspace or no active increment → a git + notes handoff is still written.

Manual path

  1. Capture git state (free):
git rev-parse --abbrev-ref HEAD; git rev-parse --short HEAD
git status --porcelain; git diff --stat
{ git diff HEAD; git diff --cached; } > handoff.diff

PowerShell — { … } > file writes the scriptblock text in UTF-16, not a diff:

git rev-parse --abbrev-ref HEAD; git rev-parse --short HEAD
git status --porcelain; git diff --stat
$d = (git diff HEAD | Out-String) + (git diff --cached | Out-String)
[IO.File]::WriteAllText('handoff.diff', $d, [Text.UTF8Encoding]::new($false))
  1. Ask the user only what the files cannot know: why you are stopping, where things stand in one line, the exact next step, any gotcha, key decisions.
  2. Scrub secrets in the free text AND the diff before writing: replace sk-…, gh[pos]_…, AKIA…/ASIA…, vsk_…, xox[bap]-…, Bearer …, password=…, api_key=…, -----BEGIN … with [REDACTED-<type>] and count them. Heuristic — say so; an empty list is not a guarantee.
  3. Write the document below to .specweave/increments/<inc>/handoff.md (SpecWeave workspace without an active increment → .specweave/state/handoff-latest.md; outside a workspace → ./HANDOFF.md, or .handoff/HANDOFF.md with .handoff/.gitignore = * when a foreign HANDOFF.md is in the way). UTF-8 without BOM; on PowerShell write with [IO.File]::WriteAllText($p, $body, [Text.UTF8Encoding]::new($false)), never >. If a file is already there without the Doc format v2 (or v1) marker it is somebody else's — do not overwrite it.
  4. Print the absolute doc path first, then the diff path, then the paste prompt.

Read the full file on GitHub · 135 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. 6d ago First seen · 135 lines · 48 tokens per session scan A fdb862b32387

Subscribe to this mod's changes

sw-handoff is a skill published in the GitHub repository anton-abyzov/specweave (160 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 1,575 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 2026-09-03.

Related

Other skills, from other repositories