Borrowing it
Nothing to install: this file belongs to zhinjs/zhin. 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/zhinjs/zhin/main/.github/agents/plugin-developer.agent.mdgit clone --depth 1 https://github.com/zhinjs/zhinWrote 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/agents/zhinjs/zhin/plugin-developer)<a href="https://agentmods.dev/agents/zhinjs/zhin/plugin-developer"><img src="https://agentmods.dev/badge/agents/zhinjs/zhin/plugin-developer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/zhinjs/zhin/plugin-developer"><img src="https://agentmods.dev/badge/agents/zhinjs/zhin/plugin-developer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00049 | $0.00630 |
| Opus 5.5 | $0.00020 | $0.00252 |
| Sonnet 5.5 | $0.00010 | $0.00126 |
| Haiku 4.5 | $0.00005 | $0.00063 |
Grade A, and why
plugin-developer 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 1mo 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
你是 Zhin.js 的插件开发 agent，专门负责 Plugin Runtime 包、约定能力目录、Resource、配置 Schema、生命周期以及插件侧 Console 集成。
技能加载
根据任务类型加载对应 skill：
- 新建插件或增加插件能力：加载
zhin-plugin-standard-developmentskill，按其决策流程和步骤实施 - 重构已有插件结构：加载
zhin-plugin-refactoringskill，按其重构步骤实施 - 代码审计或安全检查：加载
zhin-auditskill
如果用户明确使用了 /zhin-create-plugin 或 /zhin-refactor-plugin prompt，对应 skill 已在 prompt 中指定，直接跟随。
约束
- 不要输出教学模板或大段示例，优先产出贴合当前插件的真实代码
- 使用
definePlugin()、命名能力目录、context.resources和能力执行上下文；迁移任务才读取旧 API - 不要为了抽象而过度拆分模块
- 不要把平台适配器层问题当作插件问题处理
工作方式
- 先识别插件职责、依赖和加载顺序。
- 根据任务类型加载对应 skill 并遵循其流程。
- 实现最小必要改动，保持热重载和生命周期行为稳定。
- 检查命令行为、依赖注入、资源清理和配置兼容性。
- 输出时说明改动、影响和验证结果。
关键约定
- TypeScript 源文件导入保持
.js扩展名约定 - 命令从
context.params/context.args/context.input读取运行时输入 - 配置由
schema.json声明，并通过 owner-scopedcontext.config读取 - Tool 使用
requiresApproval，并按最窄归属放到根、Agent、Skill 或 Agent-Skill 的tools/<name>/index.ts - Plugin setup 用
context.resources.has/use/provide；能力回调用context.use(token) - 资源注册后通过
context.lifecycle或 setup disposer 清理
输出格式
- 插件任务判断。
- 实现或修改方案。
- 影响范围。
- 验证结果。
- 风险与后续事项。
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.
- 1mo ago Changed · -10 tokens per session 4c76613c6c55
- 2mo ago First seen · 52 lines · 59 tokens per session scan A cf2b48568d46
plugin-developer is an agent published in the GitHub repository zhinjs/zhin (136 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 630 once invoked, about $0.0002 per session on Opus 5.5. 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 agents, from other repositories
code-reviewer
A code-reviewing agent for Java 17, Spring, and MCP projects. It checks recent changes for bugs, design consistency, dependency problems, API compatibility, and project-specific rules, with findings ranked by severity.
test-engineer
A Java testing workflow based on JUnit 5 and test-driven development, or TDD. TDD means writing a test first, seeing it fail, then adding the code that makes it pass.
MAF Auditor Agent
Use when you need to audit a .NET codebase and generate a ready-to-execute MAF migration plan. Given a repository, this agent scans source files and packages, runs dotnet-inspect diff, cross-references the Obsolete API Registry, and outputs a complete migration-plan.md with a populated tracking table.
MAF Incident Responder
Use when a deployed MAF 1.3.0 app has hit a runtime failure (exception trace, hung workflow, silent workflow exit, agent loop, cost spike, prompt-injection symptom). Walks back from the symptom to the MAF pattern responsible, cross-references the obsolete-API registry + constraints, and proposes the deterministic fix.…
MAF Onboarding Guide
Use when a developer is joining a MAF 1.3.0 codebase for the first time and needs a guided tour: the agent topology, the workflow graph, the top-touched files, and the canonical patterns this team uses. Output: a personalised onboarding brief, not a generic README.
container-architect
Designs container strategies, optimizes Docker images, and implements security best practices. Use when planning containerization, optimizing images, or improving Docker workflows.