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 agentmods add skills/mathruffian-dot/cross-device-agent-skills-opencode/project-initnpx skills add mathruffian-dot/cross-device-agent-skills-opencode --skill project-initgit clone --depth 1 https://github.com/mathruffian-dot/cross-device-agent-skills-opencodeWrote 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/mathruffian-dot/cross-device-agent-skills-opencode/project-init)<a href="https://agentmods.dev/skills/mathruffian-dot/cross-device-agent-skills-opencode/project-init"><img src="https://agentmods.dev/badge/skills/mathruffian-dot/cross-device-agent-skills-opencode/project-init.svg" alt="Measured on agentmods" 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 | $0.00145 | $0.02487 |
| Opus 5 | $0.00072 | $0.01243 |
| Sonnet 5 | $0.00029 | $0.00497 |
| Haiku 4.5 | $0.00015 | $0.00249 |
Grade A, and why
project-init 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 4d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
專案初始化技能(三層級自動偵測)
設計理念
一套技能、三個層級。這台電腦裝了什麼工具,就自動建到哪個層級——不用問使用者「你要第幾層級」。
| 層級 | 平台 | 建立的東西 | 讀取時機 |
|---|---|---|---|
| L1 本地 | 專案資料夾(建議放在你的雲端硬碟資料夾) | AGENTS.md(專案藍圖)+handoff.md(交接檔) |
每個 session 都讀 |
| L2 GitHub | 私有 repo | git 版本控制+雲端備份 | 指定才讀 |
| L3 Obsidian | 第二大腦 vault | 專案工作流程.md(詳細筆記) |
有需要才讀 |
為什麼藍圖叫
AGENTS.md而不是CLAUDE.md?因為 AGENTS.md 是跨 Agent 開放標準——OpenCode、Claude Code、Codex、Gemini CLI 都讀得懂。專案層的檔案刻意用開放格式,任何 Agent 接手都能無縫工作。 檔名必須全大寫AGENTS.md:Windows 不分大小寫所以寫錯也能動,但 Mac/Linux 分大小寫,小寫的agents.md會變成「檔案明明在、Agent 卻讀不到」。
層級偵測(初始化看「這台電腦」有什麼)
依序檢查,決定本次能建到第幾層級:
- L1:無條件可建
- L2:跑
gh auth status,成功(已登入 GitHub CLI)→ 可建 - L3:目前有可用的 Obsidian MCP 工具(能列目錄、建立筆記的工具)→ 可建
- 請依「你手上實際有哪些工具」判斷,不要假設特定的工具名稱
檢查完先告訴使用者:「這台電腦可初始化至第 N 層級」,再開始執行。
初始化 SOP(依序執行)
L1:本地藍圖(永遠執行)
- 掃描資料夾現況:列出既有檔案,若已有
AGENTS.md或handoff.md→ 停下來問使用者是否要覆蓋 - 詢問使用者:專案名稱、一句話目標、關鍵時程(沒有就留白,不要硬編)
- 建立
AGENTS.md:用下方範本為底,填入實際內容;「資料夾結構」區塊由掃描結果自動生成 - 建立
handoff.md:用下方範本為底,「目前做到哪」填「專案初始化完成」,更新者填 Agent 名+電腦名- 電腦名:Windows(PowerShell)用
$env:COMPUTERNAME;Mac/Linux 用hostname
- 電腦名:Windows(PowerShell)用
- 若路徑含「雲端硬碟」「My Drive」「Google Drive」→ 提醒使用者確認雲端硬碟桌面版的同步圖示已打勾(檔案要真的躺在雲端,換電腦才拿得到)
範本:AGENTS.md
# <專案名稱>(專案藍圖)
> 本檔為跨 Agent 通用的專案藍圖(AGENTS.md 開放標準)。任何 Agent 的每個 session 都應先讀本檔+`handoff.md`。
## 專案簡介
<!-- 一段話:這個專案是什麼、目標是什麼 -->
## 關鍵時程
<!-- 格式:- 事件名稱:日期(說明);沒有就留白 -->
## 目標與路線圖
<!-- 用 checklist 追蹤,收工技能會更新這裡 -->
- [ ] 階段一:
- [ ] 階段二:
## 資料夾結構
<!-- 初始化時自動掃描生成,之後新增檔案要更新 -->
## 同步層級(本專案初始化至第 N 層級)
| 層級 | 平台 | 位置 | 讀取時機 |
|------|------|------|---------|
| L1 | 本地(雲端硬碟資料夾) | `AGENTS.md`+`handoff.md` | 每個 session |
| L2 | GitHub | <未啟用|<你的 GitHub 帳號>/repo-name> | 指定時 |
| L3 | Obsidian | <未啟用|專案資料夾名/專案工作流程.md> | 有需要時 |
## 工作約定
- 任何 Agent、任何電腦:**開工先讀 `handoff.md`,收工必更新 `handoff.md`**
- 修改共用檔案前先讀最新內容,避免覆蓋其他 Agent 的變更
- 所有回應與文件使用繁體中文
- 修改前先確認計畫,優先保留原有資料結構
## 安全與隱私(不可違反)
- **不把 API key、密碼、憑證寫進 repo**,也不要貼進 `AGENTS.md`/`handoff.md`;一律放 `.env` 並列入 `.gitignore`
- **學生資料只用座號**,不出現姓名、學號、班級以外的個資、照片或聯絡方式
- 要公開分享前,先確認檔案裡沒有上述兩類內容
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.
- 4d ago First seen · 159 lines · 145 tokens per session scan A 3e1cf931f7d2
project-init 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 145 tokens to every session and 2,487 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…