startup

startup is a skill for Claude Code, Codex from mathruffian-dot/cross-device-agent-skills-opencode. It costs 133 tokens per session (2,026 once invoked), scanned A, original, MIT.

A project handoff reader that checks the project plan, handoff notes, and Git status when you resume work.

In plain words
What is it for?
Resuming unfinished work, checking the last recorded progress, spotting outdated files, and identifying the next suggested step.
Why use it?
It reduces the need to remember or re-explain what happened in an earlier session or on another computer.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/mathruffian-dot/cross-device-agent-skills-opencode/startup
Any agent
npx skills add mathruffian-dot/cross-device-agent-skills-opencode --skill startup
Clone the repo
git clone --depth 1 https://github.com/mathruffian-dot/cross-device-agent-skills-opencode

Made for: Claude Code, Codex.

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 startup

README.md
[![agentmods](https://agentmods.dev/badge/skills/mathruffian-dot/cross-device-agent-skills-opencode/startup.svg)](https://agentmods.dev/skills/mathruffian-dot/cross-device-agent-skills-opencode/startup)
Your own site
<a href="https://agentmods.dev/skills/mathruffian-dot/cross-device-agent-skills-opencode/startup"><img src="https://agentmods.dev/badge/skills/mathruffian-dot/cross-device-agent-skills-opencode/startup.svg" alt="Measured on agentmods" height="20"></a>
Per session 133 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,026 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00133 $0.02026
Opus 5 $0.00067 $0.01013
Sonnet 5 $0.00027 $0.00405
Haiku 4.5 $0.00013 $0.00203

Measured 5d ago against content hash 605b1226cdc8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

startup 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 5d 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.

startup/SKILL.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

開工接續助手(三層級)

新對話開始時,幫使用者快速進入「上次做到哪」的脈絡,避免從零開始解釋。

核心原則

  1. 開工是「讀」、收工是「寫」——本技能只讀、只報告,不改任何檔案
  2. 不主動 git pull(避免覆蓋本地未 commit 變動,只提醒「要不要 pull」)
  3. 30 分鐘內 fetch 過就跳過(避免單台多對話冗餘)
  4. Obsidian 有需要才讀——L3 筆記是詳細背景資料,開工預設不讀、只列出路徑
  5. 跟收工(shutdown)技能是對偶關係:收工存進去、開工讀出來

層級偵測(開工看「這個專案」建到哪層)

  • L1:專案有 AGENTS.mdhandoff.md → 讀
  • L2:專案有 .git → 做 git 檢查
  • L3AGENTS.md 同步層級表登記了 Obsidian 路徑,且目前有可用的 Obsidian MCP 工具(例如能列出 vault 目錄、讀寫筆記的工具)→ 列出筆記路徑(不主動讀)

判斷 L3 時請看「你手上實際有哪些工具」,不要假設特定的工具名稱——不同的 Obsidian MCP 名稱不一樣。 注意:偵測依據是「專案有什麼」,不是「電腦有什麼」。低層級電腦打開高層級專案時做得到的照做、做不到的註明(優雅降級)。

開工 SOP(依序執行)

L1:讀藍圖與交接檔(永遠執行)

  1. AGENTS.md:專案目標、路線圖進度、工作約定(摘要,不全文倒出)
  2. handoff.md:上次做到哪、目前狀態、下一步、注意事項
  3. 檢查「最後更新」欄
    • 取得這台電腦的名稱——Windows(PowerShell)用 $env:COMPUTERNAME;Mac/Linux 用 hostname
    • 更新者的電腦名 ≠ 這台電腦 → 特別標示「⚠️ 上次在另一台電腦(名稱)收工」,並確認雲端硬碟同步已完成(看 handoff.md 的檔案時間戳是否與交接檔內寫的時間吻合;若本地檔案明顯過舊,提醒等雲端同步完再開工)
    • handoff.md 的更新時間比 AGENTS.md 舊很多 → 提醒「上次可能沒有正式收工」

Fallback(舊專案相容):若專案沒有 AGENTS.mdhandoff.md

  • 有 Obsidian MCP → 改讀 <你的 vault>/<專案資料夾名>/專案工作流程.md工作筆記.md 的「上次做到哪」段
  • 讀完提議:「這個專案還沒有 AGENTS.md+handoff.md,要不要用『初始化專案』補建?」(提議即可,不主動建)

L2:git 檢查(專案有 .git 才做)

  1. 本地狀態git status --short
    • clean → 「本地工作區乾淨」
    • 有未 commit 變動 → 列出,提醒「上次有未完成的修改,要繼續還是放棄?」
  2. 遠端狀態(30 分鐘規則)
    1. 先看 .git/FETCH_HEAD 的最後修改時間(用你手上的檔案工具讀取時間戳即可,不要用只有某個平台才有的 shell 語法
    2. 檔案不存在,或距離現在超過 30 分鐘 → 執行:
      git fetch origin
      
    3. 再看落後幾個 commit:
      git rev-list --count "HEAD..@{u}"
      

      引號不能省:PowerShell 會把沒加引號的 @{...} 當成 hashtable 語法而報錯。 若回報「沒有上游分支」之類的錯誤 → 視為 0,並在報告註明「尚未設定上游分支」。

    4. 落後 > 0 → 提醒「遠端有 N 個新 commit,要 git pull 嗎?」不主動 pull
  3. 交叉比對防呆:若 handoff.md 寫「Git push:✅」但遠端沒有對應的新 commit → 警告「上次收工可能沒推成功,建議先確認再動工」

L3:Obsidian 筆記(有登記才列,不主動讀)

  1. 在報告中列出筆記路徑(例:<專案資料夾名>/專案工作流程.md),註明「需要詳細背景時我再去讀」
  2. 只有兩種情況才主動讀:handoff.md 的「下一步」明確指向筆記內容,或使用者要求

Read the full file on GitHub · 108 lines

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. 5d ago First seen · 108 lines · 133 tokens per session scan A 605b1226cdc8

Subscribe to this mod's changes

startup is a skill published in the GitHub repository mathruffian-dot/cross-device-agent-skills-opencode (2 stars, last pushed 1mo ago), licensed MIT. It adds 133 tokens to every session and 2,026 once invoked, about $0.0007 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens