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 commands/netmindai-open/narranexus/netmind_oauth.rsgit clone --depth 1 https://github.com/NetMindAI-Open/NarraNexusWrote 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/commands/netmindai-open/narranexus/netmind_oauth.rs)<a href="https://agentmods.dev/commands/netmindai-open/narranexus/netmind_oauth.rs"><img src="https://agentmods.dev/badge/commands/netmindai-open/narranexus/netmind_oauth.rs.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 5.1 | $0.00000 | $0.00888 |
| Opus 5 | $0.00000 | $0.00444 |
| Sonnet 5 | $0.00000 | $0.00178 |
| Haiku 4.5 | $0.00000 | $0.00089 |
Grade A, and why
netmind_oauth.rs 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 6d 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.
What it actually says
netmind_oauth.rs — 桌面端 NetMind(Power)OAuth 桥接
Why it exists
Web 版 OAuth([[useNetmindAuth.ts]] startOAuth)靠浏览器弹窗打开 NetMind
auth.html + window.opener.postMessage 回传结果。这套在打包桌面 webview
(WKWebView)里不工作:弹窗被拦、无跨窗 opener 通道。本地桌面在 Power 登录落地前
从没跑过 NetMind OAuth,是新面。
捕获(两条独立路径,双保险)
Rust 建子 webview 加载 auth.html,on_navigation 里两路抓结果:
- URL 匹配(主,零依赖 opener):provider 认证完会把 webview 重定向回
NetMind redirect_uri,带
?code=&state=。只有最终回调同时带这两个参(provider 授权 URL 只有 state 无 code),故要求二者都在才命中,取出后合成{type:'auth',code,state}JSON。return false取消该页加载——服务端换取由 前端handleAuthCallback→/user/userCallBack完成,和 web 版等价。 - opener shim + 哨兵(兜底):初始化脚本合成
window.opener,其 postMessage 跳到哨兵 URLhttps://nmoauth.callback/#<encodeURIComponent(JSON)>,on_navigation 命中后取 fragment。
投递(不依赖事件监听)
命中后 deliver() 把 payload 存进 [[state.rs]] 的 pending_netmind_oauth 槽,
前端启动 OAuth 后轮询 take_netmind_oauth_result(invoke)取走——这条投递不
依赖 window.__TAURI__ 的实时事件(该全局在本项目未开 withGlobalTauri,listen
可能静默失效,正是首个 DMG 测试里"子窗关了但主窗还在登录页"的根因)。同时也
emit("netmind-oauth-callback") 一份作冗余,当前前端不监听。
关键决策 / 踩坑
- payload 双格式统一:URL-match 存纯 JSON,哨兵存 URI-encoded JSON;前端
decodeURIComponent(对纯 JSON 是 no-op)+JSON.parse两者通吃。 - 无 capability 改动:子 webview 只导航,不 invoke、不 emit;缓存/emit 是 Rust 特权。默认 capability 仅覆盖 "main"。
- 窗口/缓存复用:每次开窗前先关旧窗、清空旧缓存,连点不叠、不串。
- 首个 DMG 实测结论:机制(建窗、跳转、关窗)通;Google 内嵌 webview 里 passkey/WebAuthn 用不了(需真浏览器),用"其他方式→密码"可绕过 → 由 URL 匹配路径接住 code/state。若将来要支持 passkey,只能走系统浏览器 + deep-link (需 NetMind 侧支持重定向到 narranexus://)。
未验证(编译需在有 Rust 的打包机)
on_navigation/initialization_script/WebviewUrl 写法在 tauri 2.11 已随首个
DMG 编译通过。运行时的 URL-match 能否在 provider 回调那一跳命中(取决于 NetMind
redirect_uri 把 code/state 放 query 还是 fragment),需实测;放 fragment 的话把
query_pairs() 换成解析 fragment 即可。
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.
- 6d ago First seen · 54 lines · 0 tokens per session scan A f96c2cfea47d
netmind_oauth.rs is a command published in the GitHub repository NetMindAI-Open/NarraNexus (86 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 888 tokens. 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 2026-08-30.
Other commands, from other repositories
init
Initialize configurations for Supabase local development.
http-service
Build, review or debug a Bun HTTP service. Loads the http-service skill, then works the task through its workflow.
start-10-1
Command "start-10-1" from minicoohei/ai-agent-camp, covering 🎓 lesson 10-1: clasp基本・gasプロジェクト管理, 📍 このセッションでやること, 🎯 準備チェック, 🚀 step 1: claspのインストールと apps script api の確認 and 🚀 step 2: google認証.
api-contract-review
Review an API contract (endpoints, request/response shapes, error codes, auth model) BEFORE implementation for naming consistency, versioning, pagination, idempotency, and alignment with existing endpoints. Distinct from review-hard (post-implementation risk) and repo-consistency-sweep (pattern matching on written…
build
Discover an AI Gateway's models and MCP tools, retrieve a credential, and integrate them into your app — call a model, connect MCP tools, or scaffold a runnable agent.
fastapi
FastAPI application design and implementation conventions. Use this skill when building, updating, or reviewing FastAPI services, routers, dependencies, request/response schemas, streaming endpoints, or API tests. Trigger on FastAPI-specific work such as path operation design, dependency injection, response models…