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 YuDefine/nuxt-supabase-starter --skill handoffgit clone --depth 1 https://github.com/YuDefine/nuxt-supabase-starterWrote 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/yudefine/nuxt-supabase-starter/handoff)<a href="https://agentmods.dev/skills/yudefine/nuxt-supabase-starter/handoff"><img src="https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/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/yudefine/nuxt-supabase-starter/handoff"><img src="https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 10 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 10 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Agent Snooping · line 286 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00103 | $0.15638 |
| Opus 5 | $0.00051 | $0.07819 |
| Sonnet 5 | $0.00021 | $0.03128 |
| Haiku 4.5 | $0.00010 | $0.01564 |
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 yesterday.
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 — 577 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/handoff
Cursor 主線：
relay與fanout不適用。 命中任一即停這兩格——系統提示自稱 Cursor；Task tool 的 model 清單含claude-opus-5/composer-2.5/gpt-5.6-sol/grok-4.5；env 有CURSOR_SESSION_ID或CURSOR_TRACE_ID。NEVER 開 successor pane 並輸出「目前這裡收工」。裸/handoff若第二層會落到relay／fanout，改為主線自己做完（不收工）。user 顯式打relay／fanout同樣改道，只准主線做完或park（0 pane、只登記）。next的盤點可跑；2B.5 若要開 successor pane 則不開，改主線做或park。Herdr--relay是另一個旗標，效果同為主線收工，同樣不准。park仍適用。本 skill 其餘步驟是 Herdr 內互動式主線（AI Agent 或 Pi/cx）的交接機器；runtime 繼承契約見 dispatch-common.md § 3.1。
Session 交接管理。四個 arg，全部以「本 session 收工」結束；差別只在開幾個 pane。裸 /handoff 自己判該用哪一個——先判當前 session 有沒有未交辦工作，再判其中幾件派得出去。
Step 0 — 解析參數
先解析 invocation args，在 Step 1 之前分流：
| Args | 開幾個 pane | 動作 |
|---|---|---|
| 無參數 | 依判定結果 | 先過 Step 0.5 context 預算 gate，未被 gate 改道才進 Step 1 兩層自動判定，落到 park／relay／fanout／next 其一 |
park / park <一句工作描述> |
0 | 進 § park：只把未完項登記進 HANDOFF／TD／ROADMAP，收工。user 顯式打 park 本身就是允許，不必再問 |
relay / relay <一句工作描述> |
1 successor | MUST Read relay-steps.md 全文並照順序執行 |
fanout / fanout <一句工作描述> |
N worker + 1 successor | MUST Read fanout-steps.md 全文並照順序執行 |
next |
依盤點結果 | 先過 Step 0.5 context 預算 gate；未被改道才進 § next：先跑 health gate／worktree／TD hygiene 盤點，再決定派什麼，收工 |
判準是「手上有幾件可平行的工作」，而預設方向是「派出去」：1 件（含多件但彼此 serial）→ relay；N ≥ 2 件可平行 → fanout；還不知道有幾件 → next（盤點完會落到前三者之一）；0 件才輪到 park，而裸 /handoff 自動判定落到 park 時 MUST 先取得 user 允許（見 Step 1 § park gate）。
relay 與 fanout 是優先選項，判定成立就直接派，NEVER 再回頭問 user「要不要派」——派出去的是互動式 pane，接手的 session 可以直接在那個 pane 問 user，多一次確認只是把決策工作原樣退回。
「可平行」走 dispatch-steps.md § Serial vs Parallel 評估的四條 rubric，四條全成立才算。任一條不成立就是 serial，合併成一份 brief 走 relay。
relay 與 fanout 的共用底座是 dispatch-common.md：preflight、durable thin brief 紀律、--label 要求、runtime cleanup、parent worktree lifecycle、收工訊息契約。兩支 steps 檔只寫各自差異。
What ships with it
6 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.
- yesterday Changed · +5 lines · -17 tokens per session 127fbc64855c
- 2d ago Changed · -1 lines · -2 tokens per session 2aad610a2605
- 5d ago First seen · 573 lines · 122 tokens per session scan A 6f9801ec3be3
handoff is a skill published in the GitHub repository YuDefine/nuxt-supabase-starter (45 stars, last pushed today), licensed MIT. It adds 103 tokens to every session and 15,638 once invoked, about $0.0005 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.
Other skills, from other repositories
cron-manager
A command-line manager for scheduled tasks, which are jobs that run at specified times or intervals. It handles creating, viewing, changing, deleting, enabling, disabling, running, and reviewing the history of those tasks.
daily-digest
Build and deliver the daily activity digest, covering GitHub activity, AI Gateway spend, visitor counts, CLI usage, and a short news section. Load this when the morning digest schedule fires, or when someone asks for a digest, a daily recap, or "what happened" over a recent period, on any channel.
ima-notes
A note-taking tool that uses the IMA service to search, read, list, create, and append notes. IMA is the connected note system it communicates with.
testing-principles
Language-agnostic testing principles including TDD, test quality, coverage standards, and test design patterns. Use when writing tests, designing test strategies, or reviewing test quality.
test-driven-development
Enforces TDD discipline with RED-GREEN-REFACTOR cycle. Use when writing new features, fixing bugs, or refactoring code. Ensures tests genuinely verify behavior.
prd-v07-implementation-loop
Execute implementation within EPICs following test-first development, continuous SoT updates, and code traceability during PRD v0.7 Build Execution. Triggers on requests to start building, implement an epic, begin coding, or when user asks "start building", "implement epic", "coding", "development", "build execution"…