skyroc AGENTS.md

skyroc AGENTS.md is an instructions file for Codex, OpenCode from Ohh-889/skyroc. It costs 2,868 tokens per session, scanned A, original, MIT.

Repository instructions for the Ohh-889/skyroc project. They explain where shared and platform-specific rules live, how coding skills are selected, and conventions for React components.

In plain words
What is it for?
They help agents find the right instruction files, follow the project's architecture and workflow, and write React components with the required props and definition patterns.
Why use it?
They give coding agents a consistent source of project rules, reducing changes that conflict with the repository's architecture or component standards.

Instructions file for CodexOpenCode

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.

agentmods
npx agentmods add instructions/ohh-889/skyroc/agents-md
Clone the repo
git clone --depth 1 https://github.com/Ohh-889/skyroc

Made for: Codex, OpenCode.

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 skyroc AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ohh-889/skyroc/agents-md.svg)](https://agentmods.dev/instructions/ohh-889/skyroc/agents-md)
Your own site
<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>
Per session 2,868 This file is loaded in full into every session.
When invoked 2,868 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.02868 $0.02868
Opus 5 $0.01434 $0.01434
Sonnet 5 $0.00574 $0.00574
Haiku 4.5 $0.00287 $0.00287

Measured 4d ago against content hash 6d662d426a5b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

AGENTS.md · 298 lines

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:

  1. 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。
  2. 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。
  3. 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

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」。

Read the full file on GitHub · 298 lines

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 · 298 lines · 2,868 tokens per session scan A 6d662d426a5b

Subscribe to this mod's changes

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.