agentmods.dev

notion-hub

notion-hub is a skill for Claude Code from YuDefine/nuxt-supabase-starter. It costs 187 tokens per session (2,052 once invoked), scanned A, original, MIT.

A controlled entry point for managing a Notion work hub, which is a shared workspace containing a ticket board and customer-visible delivery items. It coordinates ticket creation, status changes, and delivery progress with repository workflows.

In plain words
What is it for?
Use it to open or update work items, connect non-file work to customer-facing delivery records, and resolve the configured Notion hub for a repository.
Why use it?
It prevents project records from drifting out of sync with the work being done and routes unrestricted Notion operations through the required process.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

not rated 44repo changed 8d ago A scan 187 tokens original MIT

Good fit Use it to open or update work items, connect non-file work to customer-facing delivery records, and resolve the configured Notion hub for a repository.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yudefine/nuxt-supabase-starter/notion-hub
View source ↗ 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 notion-hub
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.

agentmods badge for notion-hub

README.md
[![agentmods](https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/notion-hub/github.svg)](https://agentmods.dev/skills/yudefine/nuxt-supabase-starter/notion-hub)
Your own site
<a href="https://agentmods.dev/skills/yudefine/nuxt-supabase-starter/notion-hub"><img src="https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/notion-hub/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.

agentmods 80×15 button for notion-hub

Your own site · 80×15
<a href="https://agentmods.dev/skills/yudefine/nuxt-supabase-starter/notion-hub"><img src="https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/notion-hub.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 187 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,052 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.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00187 $0.02052
Opus 5.5 $0.00075 $0.00821
Sonnet 5.5 $0.00037 $0.00410
Haiku 4.5 $0.00019 $0.00205

Measured 8d ago against content hash 4cb7f2633f7a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

notion-hub 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.

template/.claude/skills/notion-hub/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

notion-hub

所有 Notion 讀寫的唯一入口：當前 consumer 所屬 hub（ticket board＋客戶看的 交付項目；hub 可省略交付項目、把進度併進 board 進度%）的六個意圖，加上任何 Notion 頁面的查找與更新；生命週期同步由 flow 事件與 notion-sync 自動推進。所有客戶的 hub 共用同一個 workspace，頁面屬於哪個客戶只認 notion-scope.ts 的判定。規約在 [[notion-work-coupling]]，跨 hub 架構與七階段速查見 clade home 的 vendor/snippets/notion-hub/lifecycle.md。

SOP

Phase 1 -- 解析 hub 並選定意圖

  1. DELEGATE 執行 node ~/offline/clade/vendor/scripts/lib/notion-hub.ts resolve --consumer-path .；輸出 configured:false 時只剩 Phase 8 可走（不屬於任何 hub），其餘意圖回報「此 repo 未宣告 notion.hub」並停止，不猜 board。
  2. READ 讀取 resolve 輸出的 hub.ticketStatus、hub.ticketType、hub.fields，後續狀態字、類型字與欄位名一律以它們為準；懷疑欄位或選項被改過時 DELEGATE node ~/offline/clade/scripts/audit-notion-hub-schema.ts --hub <key>。
  3. THINK 先讀取 rules/Notion執行者與ntn呼叫判準.md，再依使用者請求選定意圖：看板（Phase 2）、認領客戶票（Phase 3）、工程師建票（Phase 4）、問客戶（Phase 5）、對帳驗收（Phase 6）、開 hub／加專案（Phase 7）、查找或更新 Notion 頁面（Phase 8）。

Phase 2 -- 看板（唯讀）

  1. DELEGATE 經〔notion-ops〕依 references/ntn-cookbook.md § 讀取 撈本專案票（報告模式另撈交付項目），dump 到檔回傳。
  2. THINK 先讀取 rules/看板分桶與對帳判準.md，逐張分桶、對帳並標 ⚑；報告模式另列逾期。
  3. WRITE 回報分桶結果；有 ⚑ 時結尾首要建議對應意圖。不改任何欄位。

Phase 3 -- 認領客戶票

  1. DELEGATE 經〔notion-ops〕讀票（raw＋客戶 comment），再以 codebase-memory 定位 root cause 與修法草案。
  2. THINK 先讀取 rules/認領分流判準.md，判可直接做／要客戶先拍板（轉 Phase 5）／前提不成立，並區分是否為 coordinator 派來的票。
  3. DELEGATE 可直接做時，先讀取 rules/客戶面證據判準.md 定稿 --title，再執行 flow open <slug> --origin notion:<page-id>（coordinator 派來的票跳過）與 node ~/offline/clade/vendor/scripts/notion-sync.ts open --work <id> --ticket <page-id> --title "<客戶看得懂的一句話>"，交棒 work-route。

Phase 4 -- 工程師建票

  1. DELEGATE 先讀取 rules/客戶面證據判準.md 定稿標題與證據，再執行 node ~/offline/clade/vendor/scripts/notion-sync.ts file --title "<客戶看得懂的一句話>" --kind bug|feature --slug <slug> [--prod-url <prod 頁面>] [--screenshot <png>]…（已有 work item 用 --work <id> 代替 --slug）；照做它印的 export CLADE_WORK_ID=… 後交棒 work-route，拒寫時依已載入判準修正來源。

Phase 5 -- 問客戶（決策題 ticket）

  1. THINK 先讀取 rules/決策題撰寫判準.md，確認符合開決策題的條件（只問一句就改在既有票留 comment），並一次萃取需求標題、拍板題與 code pointer。
  2. WRITE 先讀取 templates/客戶決策題ticket.md 與 templates/客戶決策題ticket.example.md，再讀取 rules/客戶面證據判準.md，依骨架組出 4 段內容與接手 prompt。
  3. DELEGATE 經〔notion-ops〕先以 ntn api "/v1/data_sources/<board>" < /dev/null 重撈 schema，再依 references/ntn-cookbook.md § 建決策題票建頁（類型 用 hub.ticketType.feature，bug 修正類改用 hub.ticketType.bug）；拿到 page id 後回填接手 prompt【第一步】，已有 work item 時再跑 notion-sync.ts open --work <id> --ticket <page>。
  4. WRITE 先讀當前 repo HANDOFF.md 的格式，append 同步條目（ticket URL＋page id、N 題、接手方式），再回報 ticket URL、題數、HANDOFF 位置與接手方式。

Read the full file on GitHub · 58 lines

Files

What ships with it

10 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.

  1. 8d ago Changed · -1 lines 4cb7f2633f7a
  2. 9d ago Changed · -85 lines · +68 tokens per session 938840821a6f
  3. 14d ago Changed · +1 lines 9588db47cf11
  4. 17d ago Changed · +19 lines · +11 tokens per session e821357b403e
  5. 19d ago Changed · -5 tokens per session 17ad3a7ac7e1
  6. 21d ago Changed 34ede41fde65
  7. 22d ago Changed · +2 lines 569cc94042b3
  8. 24d ago First seen · 122 lines · 113 tokens per session scan A f5060510d1c7

Subscribe to this mod's changes

notion-hub is a skill published in the GitHub repository YuDefine/nuxt-supabase-starter (44 stars, last pushed 2d ago), licensed MIT. It adds 187 tokens to every session and 2,052 once invoked, about $0.0007 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 2026-09-23.

Claude CodeProject managementTDDai-assistednuxtsupabasetemplate
Related

Other skills, from other repositories

linear-maintenance

Bi-weekly housekeeping pass over the evlog team's Linear backlog — labels, projects, priorities, stale triage, work that is done but still open, and anything misfiled next to its siblings. Applies the mechanically verifiable fixes and surfaces the rest as decisions. Load this when the linear-maintenance schedule…

HugoRCD/evlog · 89 tokens

product

Consolidated Galyarder Framework Product intelligence bundle.

skillmds/skillmd · 13 tokens

nw-finalize

Archives a completed feature to docs/evolution/, migrates lasting artifacts to permanent directories, and cleans up the temporary workspace. Use after all implementation steps pass and mutation testing completes.

nWave-ai/nWave · 39 tokens

nw-deliver-orchestration

DELIVER wave orchestration workflow -- 9 phases from baseline to finalization. Load when user invokes deliver command. Covers state tracking, smart skip logic, retry, resume, and quality gate enforcement.

nWave-ai/nWave · 48 tokens

issue-tracker-ingestion

Pull issue/PR/ticket details from Jira, GitHub Issues, Linear, or Azure Boards via MCP into 01-spec.md ## Source. Use at the start of /spec whenever the user references an external ticket.

loiane/specs-driven-development-spring-angular · 53 tokens

prd-v07-test-planning

Define test cases BEFORE implementation, ensuring every API, business rule, and user journey has verifiable acceptance criteria during PRD v0.7 Build Execution. Triggers on requests to define tests, plan test coverage, create test cases, or when user asks "define tests", "test planning", "what to test?", "test cases"…

mattgierhart/PRD-driven-context-engineering · 125 tokens