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.
npx skills add anton-abyzov/specweave --skill sw-handoffgit clone --depth 1 https://github.com/anton-abyzov/specweaveWrote 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/specweave/sw-handoff)<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.
<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>- NVIDIA SkillSpector pass
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 | $0.00051 | $0.02009 |
| Opus 5.5 | $0.00020 | $0.00804 |
| Sonnet 5.5 | $0.00010 | $0.00402 |
| Haiku 4.5 | $0.00005 | $0.00201 |
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 today.
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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sw-handoff: "hand off" here, "pick up" there
The user should never have to copy a prompt. Two words each way.
Hand off
When the user says "hand off", "handoff", "I'm out of tokens", "switching to Codex" or "switching accounts", run:
specweave handoff --reason "<their words>"
It releases your task claims, records the handoff in the ledger, writes handoff.md
next to the increment, pushes the branch, and pushes a snapshot of your uncommitted
edits to the specweave-handoff branch (and wip/<branch>). Your working tree,
index and branch are untouched. Relay its two or three lines as they are, then tell
the user: say "pick up" in the other tool.
Before handing off, make sure your last task claim / task done carried --line
(the card text) and, for done work, --link (PR, report or artifact); the next agent
reads the checklist, not your transcript.
Add --next "<exact next step>", --gotcha "..." or --decision "..." only for what
the files cannot tell the next agent. No Git remote and another machine:
--inline prints a prompt to paste instead. --no-push keeps it local.
Hand off everything (switching accounts with many threads)
When the user switches accounts or tools with several increments in flight ("hand off all", "switching subscriptions"), run:
specweave handoff --all --reason "<their words>"
It writes .specweave/handoffs/<date>-INDEX.md and index.json: one row per active
increment (tasks done/total, open ACs, last activity, what it waits on, a paste-ready
resume prompt) and every nested checkout (repositories/<org>/<repo> or any folder
up to three levels down with its own .git, and their worktrees) with uncommitted files, unpushed
commits or a branch with no remote, with its open PR when gh is installed. It is
read-only toward everything else: no claims released, nothing committed or pushed in
the umbrella or the nested repos. Commit and push the local-only work it lists, or say
so in your reply. --dry-run prints the index without writing it.
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.
- today Changed · +3 lines 311a42468831
- 3d ago Changed 3e2481b5e347
- 7d ago Changed · +8 lines f7e77db4108a
- 11d ago Changed 3bd59c6e46a3
- 16d ago Changed · +14 lines 4200b9f04f4e
- 17d ago Changed · -1 lines 54894abce553
- 18d ago Changed · +8 lines 9f97b3ef86c7
- 23d ago Changed · +37 lines · +5 tokens per session bc2d671c9f44
- 1mo ago Changed · -60 lines · -2 tokens per session 35c73e35a00c
- 1mo ago First seen · 135 lines · 48 tokens per session scan A fdb862b32387
sw-handoff is a skill published in the GitHub repository anton-abyzov/specweave (169 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 2,009 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
gws-gmail-send
Skill "gws-gmail-send" from googleworkspace/cli, covering gmail +send, usage, flags, examples and tips.
gws-gmail
Gmail: Send, read, and manage email.
obsidian-bases
Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.
recipe-block-focus-time
Create recurring focus time blocks on Google Calendar to protect deep work hours.
recipe-create-vacation-responder
Enable a Gmail out-of-office auto-reply with a custom message and date range.
instagram-skill
How to use Instagram CLI to interact with Instagram from the command line on behalf of a user. Use this skill whenever the user wants to send or read Instagram messages, check their inbox, reply to or unsend messages, or automate any Instagram DM workflow via the CLI. This includes tasks phrased as "message X on…