Borrowing it
Nothing to install: this file belongs to fanfan-de/anybox. 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/fanfan-de/anybox/master/.agents/skills/anybox-plugin/SKILL.mdgit clone --depth 1 https://github.com/fanfan-de/anyboxWrote 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/fanfan-de/anybox/anybox-plugin)<a href="https://agentmods.dev/skills/fanfan-de/anybox/anybox-plugin"><img src="https://agentmods.dev/badge/skills/fanfan-de/anybox/anybox-plugin.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00113 | $0.01893 |
| Opus 5 | $0.00056 | $0.00946 |
| Sonnet 5 | $0.00023 | $0.00379 |
| Haiku 4.5 | $0.00011 | $0.00189 |
Grade A, and why
anybox-plugin 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.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Anybox 插件规范
使用当前 Anybox 运行时格式。不要把历史 Fanfande 格式或旧的 fanfande-plugin-structure Skill 当作权威规范。
确定事实来源
做出重要的插件格式判断前,按以下顺序检查目标仓库中的实时内容:
packages/anyboxagent/src/plugin/plugin.tspackages/anyboxagent/Test/plugin.test.tspackages/anyboxagent/src/connector/connector.tspackages/anyboxagent/src/plugin/platform-artifacts.tsplugins/Anybox-Plugins/index.json- 当前内置插件的
.anybox-plugin/plugin.json示例 plugins/Anybox-Plugins/anybox-plugin-development/docs/anybox-third-party-plugin-development.md- 本 Skill 的参考文档
运行代码优先于测试,测试优先于说明文档,目标仓库优先于既有假设。如果实时解析器与本 Skill 不一致,遵循解析器并报告规范漂移。除非用户明确要求修改插件格式本身,否则不要为了让某个插件通过而修改解析器。
按需读取参考文档
- 创建、迁移或完整评审插件时,读取 manifest-format.md。
- 插件声明 MCP Server、自有 Connector、OAuth、API Key 或平台 Connector 依赖时,读取 connectors-and-mcp.md。
- 处理本地来源、安装、Registry 条目、ZIP、GitHub URL、发布或验证时,读取 distribution-and-validation.md。
面对范围很窄的问题时,不要加载无关参考文档。
执行流程
- 判断任务属于包结构、清单编写、运行时接入、分发、迁移还是诊断。
- 找到插件包根目录。把
.anybox-plugin视为元数据目录,而不是包根目录。 - 对每项高级能力检查实时 schema,并至少查看一个当前内置插件示例。
- 在
<plugin-root>/.anybox-plugin/plugin.json创建或更新规范清单。 - 把
scripts、skills、connectors、docs和assets放在.anybox-plugin同级。 - 使用严格 JSON。遇到不支持的顶层字段时应报错,不要假设解析器会忽略。
- 保证所有包内相对路径都留在插件包中。拒绝路径穿越、应使用相对路径处的绝对路径,以及分发包中的符号链接。
- 不要把密钥写入源码。声明 placeholder 和 credential 元数据,由 Anybox 保存并注入真实密钥。
- 按变更风险验证目录加载和安装行为。
- 修改插件系统代码时,在同一项变更中同步更新测试、开发文档和本 Skill。
强制规则
- 为新 Anybox 插件生成
.anybox-plugin/plugin.json。 - 仅把根目录
plugin.json和.codex-plugin/plugin.json当作兼容输入。 - 不要生成
.fanfande-plugin/plugin.json或plugin.meta.json。 - 根据规范化后的 manifest
name生成插件 ID,并让文件夹、manifest 名称和 Registry 路径保持一致。 - 新插件自有 Connector 使用
connectors[].id;把connectorID和appID视为兼容别名。 - 规范 Connector 条目必须同时包含
credential和runtime;configFields只能作为额外配置。 - 优先使用
connectors,不要为新插件使用旧的apps字段。 - 创建新插件时,插件自有
mcpServers和connectors暴露的全部 MCP 工具默认使用auto(Auto allow)。新清单应省略runtime.toolPolicies;只有用户明确要求审批、禁用或逐工具差异时才写非空映射。 runtime.toolPolicies一旦非空,任何未列出的工具都会回退为ask。不要通过“只把部分当前工具列成auto”来表达全工具 Auto allow;若必须启用差异策略并让其余当前工具自动运行,应显式列出全部当前工具,后续新增工具也必须补充策略。- Auto allow 只决定 MCP 工具策略,不绕过工作区外路径授权、规划/只读模式或 critical-risk 阻断等宿主安全边界。
- 把
commands和agents视为保留兼容字段,不要声称当前运行时会执行它们。 - 完整 App 使用
views提供用户入口;只有需要宿主启动本地 HTTP 后端时才声明独立的appRuntime,不要把它与mcpServers[].runtime混用。 - App Web 构建产物应放在插件包内并使用相对资源路径。
appRuntime中带${PLUGIN_ROOT}的 command、arg 和 cwd 必须解析到真实的包内文件或目录,不能使用其他 Runtime placeholder。 appPermissions当前会进入高风险安装审查;workspace: "request"只提供过渡性的项目上下文,network和system不能被描述成已经具有 OS 级强制隔离或完整 Host SDK 授权。- 自定义 Provider 地址使用
appPermissions.network[].kind = "user-configured-origin";仅声明权限不等于网络隔离,Runtime 必须验证 HTTPS/loopback、DNS 结果与同源重定向。 - 系统钥匙串或原生选择器使用通用
platformArtifacts.type = "app-runtime-helper"。每个平台文件必须绑定 SHA-256,Runtime 只从ANYBOX_APP_ARTIFACTS_JSON读取安装后的路径,不得在 Core 添加插件 ID 分支。 - App Runtime 只能依赖通用
ANYBOX_APP_*启动环境与最小 OS 环境,不得依赖ANYBOX_AGENT_*、插件专用兼容变量或宿主共享工具路径。 - Plugin View 通过宿主同源 Gateway 播放 Runtime 音视频时,桌面端自定义协议必须启用
stream: true,并用测试同时覆盖协议权限、Range 请求和206 Partial Content响应。 - Local App Runtime 是真实本机代码。未实现 OS 级进程 Sandbox、签名与信任链前,必须明确告知风险,不得把声明式网络或文件权限宣传为安全边界。
- 桌面开发版与正式版默认共享仓库内稳定的
.catalog/anybox-plugin-registry.json,且默认不扫描本地仓库源码包;只有显式设置ANYBOX_PLUGIN_INCLUDE_SOURCE_PACKAGES=1才进入源码插件开发模式。插件目录不跟随桌面版本,所有 Registry 和版本化 ZIP 都在本地生成、验证后作为普通 Git 文件提交;不得依赖 GitHub Actions、Release 或 API。 - 除非确实希望阻止安装,否则不要把风险标记为
critical。 - 迁移或验证期间保留用户文件和工作区中的无关改动。
- OAuth Credential 的实时字段包括
refreshURL、tokenRequestFormat和可选dialect;当前方言为standard、bilibili和tiktok。使用非标准方言前必须核对 Provider 官方文档并补覆盖授权码交换与刷新行为的测试。
What ships with it
4 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.
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 · 83 lines · 113 tokens per session scan A a6ca299e4ca2
anybox-plugin is a skill published in the GitHub repository fanfan-de/anybox (57 stars, last pushed 25d ago), licensed MIT. It adds 113 tokens to every session and 1,893 once invoked, about $0.0006 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 2026-08-30.
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…
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…
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…
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…