cyrene-plugin-dev

cyrene-plugin-dev is a skill for Claude Code, Codex from Playa-0v0/Cyrene-Agent. It costs 61 tokens per session (2,349 once invoked), scanned A, original, MIT.

A guide for developing runtime plugins for Cyrene, including plugins that add tools, windows, events, live context, or connections to services. Cyrene is the host application that runs these plugins.

In plain words
What is it for?
Use it to build installable Cyrene plugins, add tools or interfaces, connect services, respond to application events, or diagnose plugin failures.
Why use it?
It gives developers the required references and workflow for creating, troubleshooting, and packaging Cyrene plugins correctly.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to build installable Cyrene plugins, add tools or interfaces, connect services, respond to application events, or diagnose plugin failures.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/playa-0v0/cyrene-agent/cyrene-plugin-dev
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.

Any agent
npx skills add Playa-0v0/Cyrene-Agent --skill cyrene-plugin-dev
Clone the repo
git clone --depth 1 https://github.com/Playa-0v0/Cyrene-Agent

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 cyrene-plugin-dev

README.md
[![agentmods](https://agentmods.dev/badge/skills/playa-0v0/cyrene-agent/cyrene-plugin-dev.svg)](https://agentmods.dev/skills/playa-0v0/cyrene-agent/cyrene-plugin-dev)
Your own site
<a href="https://agentmods.dev/skills/playa-0v0/cyrene-agent/cyrene-plugin-dev"><img src="https://agentmods.dev/badge/skills/playa-0v0/cyrene-agent/cyrene-plugin-dev.svg" alt="Measured on agentmods" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,349 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00061 $0.02349
Opus 5 $0.00030 $0.01175
Sonnet 5 $0.00012 $0.00470
Haiku 4.5 $0.00006 $0.00235

Measured 4d ago against content hash 44261c9e1d17, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

cyrene-plugin-dev 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.

skills/cyrene-plugin-dev/SKILL.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cyrene 插件开发

本 Skill 指导如何为 Cyrene 开发运行时插件:从需求到可安装的 zip 包,一次做对。

何时使用

  • 用户想给 Cyrene 加新能力,且明确走插件形式(而不是改本体源码)
  • 用户拿来的插件报错,需要排查(启用失败、工具不生效、弹窗异常)
  • 用户询问插件怎么写、能做什么

不使用:改 Cyrene 本体源码的普通开发任务;只是使用已装插件。

前置知识:先读再写

动手前必须先读本 Skill 目录下的参考文件(自包含,打包版也可用):

  1. references/getting-started.md —— 快速上手教程,含最小可用模板和常见坑速查
  2. references/api-spec.md —— 完整接口规范(manifest 字段表、ctx API、生命周期、zip 导入限制)
  3. references/example-walkthrough.md —— 官方示例插件 system-status 走读,覆盖工具 + 弹窗 + IPC 全部知识点;写新插件前通读一遍

开发版仓库中另有 docs/plugins/ 文档和 examples/ 官方示例(system-status 为 JS 全功能走读;weather-toollong-term-memoryscheduled-automationlocal-asr-contract 为 TypeScript + SDK 示例,分别覆盖 Secrets/轮次事件冻结分页/调度任务/语音租约契约),以 references/ 为准。

开发流程

1. 明确插件形态

先和用户确认要做的是哪类能力,通常是一种或多种组合:

形态 特征
纯工具插件 只注册 registerTool,AI 对话中自动调用(最常见)
带界面插件 额外实现 open() 弹独立窗口
事件驱动插件 ctx.events.on/emit:监听宿主生命周期(如关机前收尾)、与其他插件互通
动态上下文插件 ctx.registerPromptProvider:让昔涟主动感知实时状态(天气/日程/番茄钟),无需用户开口问
调用 LLM 的插件 manifest 声明 "deps": ["llm"]
渠道插件 ctx.registerChannelAdapter(进阶,先确认用户真的需要)
数据服务插件 deps 声明后经 ctx.deps 使用:secrets(密钥保管)、conversations(只读对话分页)、workspace(工作区只读绑定)、scheduler(自有定时任务)
语音输入插件 deps: ["speech-input"]:自带 ASR 模型,取独占语音租约后把识别文本提交进正常对话

2. 搭骨架

在一个独立目录(如 examples/<plugin-id>/ 或用户指定目录)创建:

<plugin-id>/
  manifest.json
  index.cjs

manifest 必填字段:apiVersion: 1idnameversion(严格三段式 SemVer)、descriptionauthorentryauthor 填开发者或团队名称,会展示在聊天窗口的插件卡片中;id 全小写连字符,它决定工具 id 前缀和安装目录名。可选字段 icon(裸文件名,png/jpg/webp/svg,≤2MiB)在插件卡片左侧展示图标,不合法时静默忽略不影响加载。

3. 实现

铁律(违反会直接启用失败或行为异常):

  • 工具 id 必须以 <插件id>_ 开头,如插件 my-plugin 的工具叫 my-plugin_hello
  • 工具的 description 是写给 AI 看的:写清"什么场景该用",含参数说明
  • 只读工具 risk: "safe" + effectKind: "read";有副作用的用 effectKind: "write"
  • 弹窗用 BrowserWindow 加载插件目录内的 HTML,nodeIntegration: true + contextIsolation: false
  • 窗口实例、定时器、子进程必须在 unregister() 里清理,且该函数要能重复调用不崩;后台资源优先用 ctx.onDispose(() => ...) 登记兜底清理、ctx.signal 传给后台任务,交给框架托管停止时机
  • 渲染进程与插件通信:IPC 通道名是 plugin:<插件id>:<channel>
  • 事件发布只能用短名(框架自动补 plugin:<插件id>: 前缀),不能伪造 host:* 或其他插件的事件;监听器单个最多 5 秒
  • 提示词 Provider 只写本轮有用的实时事实、短而精;单项配额 2 秒 / 16000 字符,超时或失败只跳过自身
  • 数据采集优先 Node 原生(osfs),不够再用 PowerShell / nvidia-smi 等子进程;子进程要设超时并处理失败降级

Read the full file on GitHub · 144 lines

Files

What ships with it

3 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.

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. 4d ago First seen · 144 lines · 61 tokens per session scan A 44261c9e1d17

Subscribe to this mod's changes

cyrene-plugin-dev is a skill published in the GitHub repository Playa-0v0/Cyrene-Agent (554 stars, last pushed today), licensed MIT. It adds 61 tokens to every session and 2,349 once invoked, about $0.0003 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 2026-09-03.