Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/skills/anton-abyzov/vskill/handoff)<a href="https://agentmods.dev/skills/anton-abyzov/vskill/handoff"><img src="https://agentmods.dev/badge/skills/anton-abyzov/vskill/handoff.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00184 | $0.02811 |
| Opus 5 | $0.00092 | $0.01406 |
| Sonnet 5 | $0.00037 | $0.00562 |
| Haiku 4.5 | $0.00018 | $0.00281 |
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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/handoff — Cross-Tool Work Handoff
No AI coding tool can read another's transcript: Claude Code locks sessions in ~/.claude/projects/<munged-cwd>/<uuid>.jsonl, Codex/OpenCode in their own stores, Antigravity in encrypted .pb. The only thing portable across tools is a self-contained document. This skill writes that document — your current goal, decisions, and the EXACT uncommitted edits — so any other AI agent can pick up where you left off, without you re-explaining anything.
Use this skill when the user is low on tokens, wants to switch tools mid-task, is moving to another machine, or says "handoff" / "continue elsewhere" / "out of tokens".
This skill is self-contained: it works with only git + a shell. It calls specweave handoff as an optional accelerator when that binary is on PATH (high-fidelity, increment-aware) — but it has no hard dependency on SpecWeave being installed.
Decision: which path to take
command -v specweave >/dev/null 2>&1 && echo "ACCELERATOR" || echo "STANDALONE"
- ACCELERATOR (
specweaveon PATH) → run the engine, surface its output. Go to Path A. - STANDALONE (no
specweave) → build the doc yourself fromgit+ a short interview. Go to Path B.
Both paths emit the same doc format and the same paste-prompt (see the canonical template below), so a handoff is continuable in any tool regardless of which path produced it.
Path A — Accelerator (specweave on PATH)
Run the engine, forwarding any short context you can supply cheaply:
specweave handoff [incrementId] [--reason "..."] [--summary "..."] [--next "..."] [--gotcha "..."] [--decision "..."] [--inline]
Then surface its stdout verbatim, in order (do not reorder or paraphrase):
- absolute doc path as plain text (FIRST), 2. clickable markdown link, 3.
.diffpath, - fenced copy-paste resume prompt, 5. per-tool "find your source session" tips.
Done. The engine handled workspace detection, task/AC parsing, git capture, the full-diff dump, secret scrub, and rendering.
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.
- 8d ago First seen · 240 lines · 184 tokens per session scan A 2d222ed579fc
handoff is a skill published in the GitHub repository anton-abyzov/vskill (45 stars, last pushed yesterday), licensed MIT. It adds 184 tokens to every session and 2,811 once invoked, about $0.0009 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.
Other skills, from other repositories
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
init-workspace-flow
Workflow for initializing or upgrading a workspace: context, discovery, documentation, etc.
arrange-workspace-flow
Workflow for arranging a workspace: layout, reference source code, business/technical context, ecosystem setup.
pad
Talk to your project. Natural-language project management — create items, check status, plan work, brainstorm ideas, and more.