A session handoff workflow for recording unfinished work and transferring it to another coding-agent session. It can also divide several independent tasks among worker sessions.

It is for parking tasks, relaying one task to a successor session, splitting parallel work, or reviewing what should happen next.

It helps preserve progress when a session is ending, the context is getting too large, or work needs to continue elsewhere.

handoff — Skill for Claude Code by YuDefine/nuxt-supabase-starter

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 YuDefine/nuxt-supabase-starter --skill handoff

Clone the repo

git clone --depth 1 https://github.com/YuDefine/nuxt-supabase-starter

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/handoff/github.svg)](https://agentmods.dev/skills/yudefine/nuxt-supabase-starter/handoff)

Your own site

<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.

Your own site · 80×15

<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>

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,114 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 warn 7 Sept 2026

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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00045	$0.01114
Opus 5.5	$0.00018	$0.00446
Sonnet 5.5	$0.00009	$0.00223
Haiku 4.5	$0.00005	$0.00111

Measured 2d ago against content hash 1bfa5fcf510e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 2d 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.

template/.claude/skills/handoff/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/handoff

Runtime host-specific relay/fanout restrictions and launcher/tool bindings are supplied by the selected runtime adapter. The shared rules below define durable handoff semantics and fail-closed boundaries.

Session 交接管理：park／relay／fanout／next 四種模式，判準都在 rules/，照下列 SOP 在命中時讀。

User Input

$ARGUMENTS

SOP

Phase 1 -- 判定 runtime 邊界、延續價值與交接模式（Codex boundary／Step 0.1／Step 0／Step 0.5／Step 1）

READ 每次進入 /handoff，讀取 rules/模式偵測與park閘判準.md：先過 Step 0.1 value-first gate，解析 $ARGUMENTS，裸 /handoff 再過 Step 0.5 context 預算 gate 與 Step 1 兩層判定，落到 park／relay／fanout／next 其一；落到 park 的裸呼叫 MUST 先過 park gate。
READ 若模式是 relay，讀取 relay-steps.md 全文並照順序執行（共用底座 dispatch-common.md）；若是 fanout，讀取 fanout-steps.md 全文照做（同樣先讀 dispatch-common.md）。完成後跳到 Phase 5。

Phase 2 -- 解析 main worktree 的全局寫入路徑（Step 1.5；park／next 共用）

READ 若模式是 park 或 next，讀取 rules/路徑解析判準.md，解析 $MAIN_WT_PATH；之後所有 HANDOFF.md／ROADMAP.md 寫入都用它的絕對路徑。

Phase 3 -- 登記 park 交接（僅 park）

READ 若模式是 park，讀取 rules/park登記與HANDOFF寫回判準.md，照 park 步驟與 HANDOFF 寫回契約登記；之後直接到 Phase 4 的 Step 3。

Phase 4 -- 完成 next 盤點、推薦並收斂 worktree 與 stash（2B.0–2B.5／Step 3）

READ 若模式是 next，讀取 rules/next盤點與推薦判準.md，依 2B.0→2B.1 執行（盤點細節在 scan-steps.md）；走到 2B.1.5 時 MUST 先讀取 rules/worktree與stash收斂判準.md，在此跑完 Step 3（3.1→3.3→3.5；3.5.1 僅 maintenance 才進，查表細節在 worktree-stash-audit.md），再接 2B.1.7→2B.1.8→2B.1.9→2B.2→2B.2.5→2B.3→2B.4→2B.4.5→2B.5（2B.3–2B.5 在 dispatch-steps.md；2B.4.5 用的是 2B.1.5 那次 Step 3.1 的結果）。Step 3 跑過就不在 2B.5 之後重跑。
READ 若模式是 park，Phase 3 完成後讀取 rules/worktree與stash收斂判準.md 跑 Step 3／3.5（細節在 worktree-stash-audit.md；3.5.1 僅 maintenance 才進）。

Phase 5 -- 收工並輸出收工訊息（Output contract）

READ 每種模式收工前，讀取 rules/收工訊息與銜接判準.md，先跑 worktree backlog 檢查，再依模式成功條件輸出完成訊息；失敗或 blocked 明說卡點，不假裝完成。

Runtime adapter: Claude

Claude Code native question handling uses AskUserQuestion; session work inventory uses TaskList. Background successor execution uses the canonical Herdr helper through Task/Agent only for bounded execution, with TaskOutput/TaskStop and the single inert ScheduleWakeup keepalive. These Claude tool names are adapter details; they do not authorize mutation or replace durable handoff receipts.

Read the full file on GitHub · 53 lines

Files

What ships with it

12 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.

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.

2d ago Changed · -518 lines scan C → A 1bfa5fcf510e
6d ago Changed · +6 lines 75d12e24e3f7
8d ago Changed · +2 lines 9e44db069da7
11d ago Changed · -9 lines · -13 tokens per session cd7666fead3e
28d ago Changed · -16 lines 6ea537147e86
29d ago Changed · +11 lines scan A → C abec046cd3f2
1mo ago Changed a894f1acd6bd
1mo ago Changed · +2 lines 8495adf66bb3
1mo ago Changed 7a976be5d4c1
1mo ago First seen · 575 lines · 58 tokens per session scan A 22aad04ca1cf

Subscribe to this mod's changes

handoff is a skill published in the GitHub repository YuDefine/nuxt-supabase-starter (44 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 1,114 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.

Claude Code Planning Productivity TDD ai-assisted nuxt supabase template

handoff next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
handoffYuDefine/nuxt-supabase-starter	Skill	44	yesterday	MIT	A	45	Claude Code
Pair Programmingruvnet/RuView	Skill	103k	yesterday	MIT	A	61	Claude Code
tddvinvcn/mattpocock-skills-zh-CN	Skill	5.6k	9d ago	MIT	A	42	Claude Code, Codex
testing-principlesshinpr/claude-code-workflows	Skill	711	4d ago	MIT	A	50	Claude Code
nw-cross-cutting-context-residencynWave-ai/nWave	Skill	631	yesterday	MIT	A	27	Claude Code
nw-ab-optimize-commandnWave-ai/nWave	Skill	631	yesterday	MIT	A	41	Claude Code
sparc-methodologyfrankxai/claude-skills-library	Skill	47	yesterday	MIT	A	49	Claude Code