Borrowing it
Nothing to install: this file belongs to jianzhoujz/bilicast. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jianzhoujz/bilicast/main/AGENTS.mdgit clone --depth 1 https://github.com/jianzhoujz/bilicastWrote 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/instructions/jianzhoujz/bilicast/agents-md)<a href="https://agentmods.dev/instructions/jianzhoujz/bilicast/agents-md"><img src="https://agentmods.dev/badge/instructions/jianzhoujz/bilicast/agents-md.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 | $0.07582 | $0.07582 |
| Opus 5 | $0.03791 | $0.03791 |
| Sonnet 5 | $0.01516 | $0.01516 |
| Haiku 4.5 | $0.00758 | $0.00758 |
Grade C, and why
bilicast AGENTS.md scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl http://127.0.0.1:18787/api/bilicast/health | python3 -m json.tool Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl http://127.0.0.1:18787/api/bilicast/health | python3 -m json.tool How it starts
The opening of the file, as written. The whole thing — 513 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
这份文档是给 AI 编程助手（Claude Code、Cursor、Copilot 等）和后续维护者看的工程速查。
用户文档见 README.md；项目原始规划见 BiliCastHelper_PLAN.md。
一句话定位
把 B 站网页视频投到局域网 DLNA 电视的小工具。两部分：
userscript/—— Tampermonkey 用户脚本（B 站页面注入"投屏"按钮、抽流地址）extension/—— 浏览器扩展（Chrome / Edge MV3），复用同一份内容脚本能力，通过 background bridge 做跨域请求与 token 存储macos/—— 纯 Swift 写的 macOS 菜单栏 App（本地 HTTP 控制 API + 流代理 + DLNA 控制）crossplatform/—— Wails2 + Go 跨平台后端路线，支持 Wails 桌面客户端、Go daemon、Docker 部署
没有 Xcode 工程文件、没有外部依赖、纯 SwiftPM + bash。 跟 Projects/demo/input-indicator 同一种工程风格。
仓库结构
bilicast/
├── README.md # 用户向
├── AGENTS.md # 本文档
├── BiliCastHelper_PLAN.md # 原始规划（Go 版，存档参考）
├── userscript/
│ └── bilicast-helper.user.js # 单文件，可直接粘进 Tampermonkey
├── extension/
│ ├── manifest.json # Chrome / Edge MV3 扩展入口
│ ├── background.js # storage + GM_xmlhttpRequest 等价桥接
│ ├── content.js # 与 userscript 内容保持同步
│ ├── popup.html
│ └── popup.js # Token 设置弹窗
├── tests/
│ └── extension-smoke.test.mjs # 浏览器端 smoke tests
├── crossplatform/
│ ├── pkg/backend/ # 跨平台 Go 后端：API、token/config、proxy、DLNA SOAP、candidate pick、SSDP
│ ├── cmd/bilicastd/ # headless daemon / Docker 入口
│ ├── frontend/dist/ # Wails2 内置 UI 静态文件
│ ├── Dockerfile
│ ├── docker-compose.yml
│ └── wails.json
└── macos/
├── Package.swift # SwiftPM，4 个 module，零依赖
├── build.sh # 构建 Go 后端 + Swift 端 → .app bundle → 自签
├── fetch-ffmpeg.sh # ffmpeg 下载脚本（缓存到 lib/）
├── lib/ffmpeg # ffmpeg universal binary（125 MB，Git 管理）
├── .gitignore # 忽略 .build/ build/
├── Sources/
│ ├── BiliCastCore/ # 常量、错误码、token、config、log、网卡
│ ├── BiliCastHTTP/ # BackendClient（HTTP 调用 bilicastd 子进程）+ 流代理
│ ├── BiliCastDLNA/ # SSDP + 描述解析 + AVTransport SOAP（保留，不再被 BiliCastApp 依赖）
│ └── BiliCastApp/ # @main + MenuBarExtra UI + AppState（管理 bilicastd 子进程）
└── build/BiliCast.app # 构建产物
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.
- 8d ago First seen · 513 lines · 7,582 tokens per session scan C 4917905924da
bilicast AGENTS.md is an instructions file published in the GitHub repository jianzhoujz/bilicast (11 stars, last pushed 4mo ago), licensed MIT. It adds 7,582 tokens to every session, about $0.0379 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.