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 instructions/ohh-889/skyroc/agents-mdgit clone --depth 1 https://github.com/Ohh-889/skyrocWrote 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/ohh-889/skyroc/agents-md)<a href="https://agentmods.dev/instructions/ohh-889/skyroc/agents-md"><img src="https://agentmods.dev/badge/instructions/ohh-889/skyroc/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 | $0.02868 | $0.02868 |
| Opus 5 | $0.01434 | $0.01434 |
| Sonnet 5 | $0.00574 | $0.00574 |
| Haiku 4.5 | $0.00287 | $0.00287 |
Grade A, and why
skyroc AGENTS.md 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.
How it starts
The opening of the file, as written. The whole thing — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
本文件为编码智能体(Claude Code、Codex 等)在本仓库工作时提供指导。
CLAUDE.md是指向本文件的符号链接,全仓库只有一份事实来源。 修改本文件,永远不要直接编辑CLAUDE.md。
规范索引
本文件只包含跨端通用、随时可能被违反的规则。平台专属规范放在对应子树, 工作涉及该子树时才需要阅读:
| 范围 | 文件 |
|---|---|
| Native 样式(Uniwind / 语义色 / 安全区) | packages/native/AGENTS.md |
| Web 样式(UnoCSS / 色阶 / antd) | packages/web/AGENTS.md |
| 包布局与命名(平台优先分层) | packages/ARCHITECTURE.md |
Skills 调用规则(关键)
技能位于 .agents/skills/(.claude/skills/ 为镜像)。
权威清单以该目录为准,此处不做枚举——手工维护的列表必然过期。
思考顺序
你是一位经验丰富的软件架构师与工程师。回应任何任务时,严格遵循以下顺序:
- 功能开发:先分析架构 → 描述系统结构、职责与交互 → 架构明确后才动手实现。
- 代码重构:先定义代码的理想终态 → 描述目标结构、抽象与边界 → 朝终态增量重构。
- 调试修复:先梳理已知信息 → 明确区分「事实 vs 假设」「症状 vs 根因」 → 问题空间厘清前不提修复方案。
信息不完整时请求澄清。不要急于写代码。行动前审慎且透明地推理。
React 组件规范
以下规则定义的是强制开发工作流,不是建议、不是偏好、不是「最佳实践」。 违反这些规则的代码即视为缺陷,即使功能正常也必须修正。
组件定义
必须使用箭头函数
// ✅ 正确
const Portal = (props: PortalProps) => { ... };
// ❌ 禁止 function 声明式组件
function Portal(props: PortalProps) { ... }
必须有独立的 Props 接口
用 interface,禁止在函数签名里内联。每个字段必须有 JSDoc 注释说明意图(不是重复类型):
interface PortalProps {
/** 是否在容器不存在时自动创建 */
autoCreate?: boolean;
/** 传送门内容 */
children: ReactNode;
}
Props 在函数体内解构
禁止在参数位置解构,解构必须是函数体第一行:
// ✅ 正确
const Portal = (props: PortalProps) => {
const { autoCreate = false, children, container } = props;
...
};
// ❌ 禁止
const Portal = ({ autoCreate, children }: PortalProps) => { ... };
理由:保持单一可预测的入口、便于调试重构、防止 prop 意外遮蔽。
Hooks 规则
useCallback — 禁止使用
useCallback 不得出现在组件代码中。以下用法一律禁止:
- 为传给子组件的函数「稳定」引用
- 配合
React.memo阻止子组件重渲染 - 用来消除
exhaustive-deps告警 - 任何预防性 / 防御性优化
若某处看起来「必须」用它,说明设计有问题,改设计而不是加 hook:
- 函数不闭包任何东西 → 提到组件外
- 命令式且不应影响渲染 → 改用
ref - 其余 → 重划组件边界,让该函数不再跨界
Web 端另有一层理由:
packages/web/admin-vite默认启用 React Compiler, 手动 memo 不仅多余,还可能干扰编译器优化。Native 端(Expo)未启用编译器, 但禁令同样成立——理由见文末「核心理念」。
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.
- 4d ago First seen · 298 lines · 2,868 tokens per session scan A 6d662d426a5b
skyroc AGENTS.md is an instructions file published in the GitHub repository Ohh-889/skyroc (787 stars, last pushed 4d ago), licensed MIT. It adds 2,868 tokens to every session, about $0.0143 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 instructions, from other repositories
ant-design-pro CLAUDE.md
Claude Code instructions for ant-design/ant-design-pro, covering claude.md, project, commands, critical rules and architecture essentials.
south-admin-react CLAUDE.md
Instructions for southliu/south-admin-react, covering claude.md, commands, development, code quality and package management.
south-admin-react AGENTS.md
Instructions for southliu/south-admin-react, covering agents.md, 常用命令, 新建页面(重要约定), 目录结构 and 路由(自动生成).
ant-design-pro AGENTS.md
AGENTS.md instructions for ant-design/ant-design-pro, a project described as: 👨🏻💻👩🏻💻 Use Ant Design like a Pro!
catch-admin AGENTS.md
Instructions for JaguarJack/catch-admin, covering catchadmin v5 - ai agent guidelines, role, 规则, 技术栈 and project 目录说明.
ant-design-cli CLAUDE.md
Instructions for ant-design/ant-design-cli, covering claude.md, coding principles, 1. think before coding, 2. simplicity first and 3. surgical changes.