What is AwesomeClaudeCode CLAUDE.md?

Repository instructions for AwesomeClaudeCode, a Chinese-language catalogue of Claude Code resources. Its CSV file is the single source used to generate the README and related assets.

Use them when adding or changing catalogue entries, categories, links, generation scripts, or validation tests.

They prevent manual edits to generated files and keep resource data, categories, validation, and output in sync.

AwesomeClaudeCode CLAUDE.md — Instructions file by yiancode

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/yiancode/awesomeclaudecode/claude-md

Clone the repo

git clone --depth 1 https://github.com/yiancode/AwesomeClaudeCode

Per session 2,475 This file is loaded in full into every session.

When invoked 2,475 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.

Model	Per session	Once invoked
Fable 5	$0.02475	$0.02475
Opus 5	$0.01238	$0.01238
Sonnet 5	$0.00495	$0.00495
Haiku 4.5	$0.00248	$0.00248

Measured 2d ago against content hash 0a4b65b72132, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

AwesomeClaudeCode CLAUDE.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 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.

CLAUDE.md · 313 lines

How it starts

The opening of the file, as written. The whole thing — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

AwesomeClaudeCode 是一个采用 单一数据源（SSOT） 架构的 Claude Code 资源汇聚项目。所有资源数据存储在 THE_RESOURCES_TABLE.csv 中，通过 Python 脚本自动生成 README.md。内容以简体中文为主，英文为辅。

Architecture

Data Flow

数据变更 → CSV 更新 → 脚本处理 → README 生成

Core Components

数据层 (Data Layer):

THE_RESOURCES_TABLE.csv - 资源数据的唯一数据源（SSOT）。包含所有资源的元数据
templates/categories.yaml - 分类定义的唯一数据源。定义13个主分类及其子分类
templates/resource-overrides.yaml - 资源手动覆盖配置。用于特殊情况的数据覆盖

生成层 (Generation Layer):

scripts/generate_readme.py - 核心生成脚本，从 CSV 生成 README.md
scripts/generate_logo_svgs.py - 生成 SVG 图标和动画
scripts/generate_ticker_svg.py - 生成滚动条 SVG

验证层 (Validation Layer):

scripts/validate_csv.py - CSV 数据完整性验证
scripts/validate_links.py - 链接有效性检查
tests/ - 单元测试和集成测试

输出层 (Output Layer):

README.md - 自动生成的项目主页，不要手动编辑
assets/ - 生成的 SVG 图标和动画文件

Critical Rules

README.md 是只读的: 所有内容变更必须通过修改 CSV 或模板文件实现
CSV 是数据源: 直接修改 CSV 文件添加、更新或删除资源
categories.yaml 定义结构: 添加新分类时必须更新此文件
先验证后生成: 修改后先运行 make validate 再运行 make generate

Common Commands

# 设置开发环境
make dev-setup

# 生成 README.md（从 CSV 数据）
make generate

# 验证 CSV 数据完整性
make validate

# 运行所有测试
make test

# 自动填充 GitHub 元数据
make auto-fill

# 快速生成并验证
make quick

# 查看所有可用命令
make help

Working with Resources

Adding a New Resource

打开 CSV 文件: 编辑 THE_RESOURCES_TABLE.csv
生成唯一 ID: 使用格式 {category_prefix}-{hash8}
- 从 templates/categories.yaml 找到分类的 prefix
- 生成 8 位哈希值（基于资源 URL 或名称）
填写所有必填字段（见下方 CSV 字段参考）
设置状态: IsActive=TRUE, IsPinned=FALSE (除非是特别重要的资源)
运行验证: make validate
生成 README: make generate
提交变更: 提交 CSV 和生成的 README.md

Updating an Existing Resource

在 THE_RESOURCES_TABLE.csv 中找到对应的行
修改需要更新的字段
如果需要覆盖某些验证规则，编辑 templates/resource-overrides.yaml
运行 make validate && make generate
提交变更

Read the full file on GitHub · 313 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.

2d ago First seen · 313 lines · 2,475 tokens per session scan A 0a4b65b72132

Subscribe to this mod's changes

AwesomeClaudeCode CLAUDE.md is an instructions file published in the GitHub repository yiancode/AwesomeClaudeCode (7 stars, last pushed 8d ago), licensed MIT. It adds 2,475 tokens to every session, about $0.0124 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 2026-08-31.

Documents Testing Writing and docs

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

AwesomeClaudeCode CLAUDE.md