What is code-reader-skills CLAUDE.md?

A project instruction file for a bilingual collection of Claude Skills, which are reusable instructions for understanding source code. It explains the repository layout and the YAML-and-Markdown format used to define skills.

Use it when developing, packaging, documenting, or reviewing the repository's code-understanding skills.

It gives contributors the project structure and the expected format for adding or updating English and Chinese code-reading tools.

How notlate-cn/code-reader-skills configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to notlate-cn/code-reader-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/notlate-cn/code-reader-skills/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/notlate-cn/code-reader-skills

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/notlate-cn/code-reader-skills/claude-md/github.svg)](https://agentmods.dev/instructions/notlate-cn/code-reader-skills/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/notlate-cn/code-reader-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/notlate-cn/code-reader-skills/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/notlate-cn/code-reader-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/notlate-cn/code-reader-skills/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,118 This file is loaded in full into every session.

When invoked 1,118 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.01118	$0.01118
Opus 5.5	$0.00447	$0.00447
Sonnet 5.5	$0.00224	$0.00224
Haiku 4.5	$0.00112	$0.00112

Measured 2mo ago against content hash 165f75ed764f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

code-reader-skills 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 2mo 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 · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 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

This is a Claude Skills repository containing bilingual (Chinese/English) code analysis tools based on cognitive science research. The skills help developers achieve deep understanding of source code through elaborative interrogation, self-explanation testing, and retrieval practice.

Core Philosophy: Understanding WHY > Knowing WHAT

Repository Structure

deep-code-understanding-skill/
├── code-reader-zh/          # Chinese version skill
│   ├── SKILL.md             # Source skill definition (primary)
│   └── code-reader-zh.skill # Packaged skill file
├── code-reader-en/          # English version skill
│   ├── SKILL.md             # Source skill definition (primary)
│   └── code-reader-en.skill # Packaged skill file
├── README.md                # Bilingual project documentation
├── LICENSE                  # MIT License
└── CLAUDE.md                # This file

Key Architecture

Skill Definition Format

Skills use YAML frontmatter followed by Markdown content:

---
name: code-reader-v2-cn
description: [Trigger words and brief description]
---

# [Content follows...]

Three Analysis Modes

Mode	Duration	Use Case	Key Features
Quick	5-10 min	Code review, quick browse	Overview, dependencies, key segments
Standard	15-20 min	Learning, research	WHY analysis, design patterns, algorithm deep dive
Deep	30+ min	Mastery, interview prep	Application transfer, quality verification, progressive generation

Core Analysis Framework

The skills implement a 9-step research-driven workflow:

Quick Overview - Language, scale, dependencies, code type
Elaborative Interrogation - 3 WHYs for background/motivation
Concept Network Construction - Concept relationships with WHYs
Algorithm & Theory Analysis - Complexity, rationale, references
Design Pattern Recognition - WHY used, alternatives, implications
Line-by-Line Analysis - Scenario-based comments with execution tracking
Application Transfer Testing - At least 2 different scenarios
Dependencies & Usage - WHY for each dependency
Quality Verification - Self-assessment checklist

Read the full file on GitHub · 137 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.

2mo ago First seen · 137 lines · 1,118 tokens per session scan A 165f75ed764f

Subscribe to this mod's changes

code-reader-skills CLAUDE.md is an instructions file published in the GitHub repository notlate-cn/code-reader-skills (181 stars, last pushed 7mo ago), licensed MIT. It adds 1,118 tokens to every session, about $0.0045 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.

code-reader-skills CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
code-reader-skills CLAUDE.mdnotlate-cn/code-reader-skills	Instructions file	181	7mo ago	MIT	A	1,118	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

code-reader-skills: Instructions file for Claude Code