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 agents/zhinjs/zhin/plugin-developergit clone --depth 1 https://github.com/zhinjs/zhinWhat 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 | $0.00059 | $0.00579 |
| Opus 5 | $0.00030 | $0.00290 |
| Sonnet 5 | $0.00012 | $0.00116 |
| Haiku 4.5 | $0.00006 | $0.00058 |
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 2d 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，专门负责实现和修改插件代码，包括插件入口、命令、中间件、Context、配置 Schema 以及插件侧的 Web 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
- 不要脱离 Zhin.js 现有插件模式，尤其是 usePlugin、provide、useContext、inject 的使用约定
- 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 - 命令参数读取优先使用
result.params - 配置声明优先使用
declareConfig() - 类型扩展使用
declare module 'zhin.js' - 资源注册后要有对应清理路径
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.
- 2d ago First seen · 52 lines · 59 tokens per session scan A cf2b48568d46
plugin-developer is an agent published in the GitHub repository zhinjs/zhin (135 stars, last pushed 5d ago), licensed MIT. It adds 59 tokens to every session and 579 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 2026-08-30.
Other agents, from other repositories
code-reviewer
代码审查官·严重性分级 🔴🟡🟢。Java/Spring/MCP 语境下审查逻辑缺陷、设计模式一致性、依赖方向、阿里规范。聚焦最近改动，证据先于断言。.
git-commit-assistant
Git 提交官·原子提交/Conventional Commits/契约顺序。按模块分批提交，精确 git add，中文 message，遵循重构契约提供者先行的提交顺序。.
AgentEval Dev
AI agent for AgentEval development tasks - code implementation, review, and debugging.
test-engineer
测试工程师·JUnit5/TDD 双 commit（[RED]→[GREEN]）。先于实现按规格写测试、锁定 API 签名 stub，覆盖解析器链/Schema 生成/扫描器/回调。三方制衡的测试方。.
agent-developer
元·Agent 体系维护者。维护 .claude/agents/ 定义与 agent-groups.json 注册表的双向一致，新增/修改/删除 agent 后跑 verify。守护本项目 Java/MCP 语境，杜绝前端污染。.
agent
The foundation class for all agents in AgentFly.