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 atman-33/workhub --skill handoff-gogit clone --depth 1 https://github.com/atman-33/workhubWrote 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/atman-33/workhub/handoff-go)<a href="https://agentmods.dev/skills/atman-33/workhub/handoff-go"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/handoff-go/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/atman-33/workhub/handoff-go"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/handoff-go.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00043 | $0.00789 |
| Opus 5.5 | $0.00017 | $0.00316 |
| Sonnet 5.5 | $0.00009 | $0.00158 |
| Haiku 4.5 | $0.00004 | $0.00079 |
Grade A, and why
handoff-go 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 1mo 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hand off the current conversation and start the next agent in one go: write the handoff document, then dispatch.mjs launches a fresh claude that reads it and continues. The baton leaves your hand and the next runner is already moving.
You write the document (judgment). dispatch.mjs owns the deterministic rest — environment detection, the initial prompt, the A→B→C fallback, and shell-safe launching.
Step 1 — Write the handoff document
Write a handoff document summarising the current conversation so a fresh agent can continue the work. Save it to the OS temporary directory — not the workspace. Capture its absolute path.
- Include a "suggested skills" section listing skills the next agent should invoke.
- Do not duplicate content already captured in other artifacts (PRDs, plans, ADRs, issues, commits, diffs); reference them by path or URL.
- Redact sensitive information (API keys, passwords, PII).
- Treat the skill arguments as a description of what the next session will focus on, and tailor the document to it.
Done when: the document is saved, its absolute path is captured, secrets are redacted, and a "suggested skills" section is present.
Step 2 — Dispatch
Run the dispatcher using its absolute path — do NOT cd into the skill directory first. Always pass --cwd set to the current session working directory (the project root, not the skill directory):
node "<absolute path to dispatch.mjs>" --doc "<absolute doc path>" --instructions "<the user's supplementary instructions from the arguments>" --cwd "<current session working directory>"
The dispatcher script is located inside the installed skill directory. Construct its absolute path from the known plugin cache location, e.g.:
C:\Users\<user>\.claude\plugins\cache\workhub-marketplace\agent-ops\<version>\skills\handoff-go\dispatch.mjs
Options: --cwd <dir> (required — set to the current working directory of this session), --layout pane|tab (default pane), --dry-run (print what would run without launching).
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 51 lines · 43 tokens per session scan A 763be86ea521
handoff-go is a skill published in the GitHub repository atman-33/workhub (3 stars, last pushed 2d ago), licensed MIT. It adds 43 tokens to every session and 789 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
superbrain-distill
Internal SuperBrain skill — run by the detached capture child to distill a session-event delta into routed Obsidian notes. Not for direct user invocation.
trellis-finish-work
Wrap up the current session: verify quality gate passed, remind user to commit, archive completed tasks, and record session progress to the developer journal. Use when done coding and ready to end the session.
wiki-orchestrate
A coordinator for organizing an Obsidian vault, which is a folder of linked Markdown notes, by first checking its structure and then arranging the notes.
kb-preferences
Use when user wants to view, update, reset, or audit report preferences stored in vault kb.yaml. Triggers on '/kb-preferences', 'update report prefs', 'change report style', 'my preferences', or when a passive reflection step in another skill needs to propose preference updates.
aetox-teach
สอนคนใช้ Aetox — ทำอะไรได้บ้างในคำที่คนเข้าใจ ห้องไหนไว้ทำอะไร ห้าอย่างที่คนใหม่ต้องรู้ และวิธีสอนด้วยการลงมือทำงานจริงของเขาแทนการบรรยาย · อ่านเมื่อผู้ใช้ถามว่าแอปนี้ทำอะไรได้ ถามวิธีใช้ หรือเพิ่งเปิดครั้งแรก.
aetox-orient
ตอนเข้าโปรเจกต์ที่ยังไม่ได้อ่านในบทสนทนานี้ หรือกลับมาสานต่อหลังเว้นไป — ก่อนแตะไฟล์แรก.