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 skills/notlate-cn/code-reader-skills/code-reader-zhnpx skills add notlate-cn/code-reader-skills --skill code-reader-zhgit clone --depth 1 https://github.com/notlate-cn/code-reader-skillsWhat 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 | $0.00080 | $0.07908 |
| Opus 5 | $0.00040 | $0.03954 |
| Sonnet 5 | $0.00016 | $0.01582 |
| Haiku 4.5 | $0.00008 | $0.00791 |
Grade A, and why
code-reader-v2-cn 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.
How it starts
The opening of the file, as written. The whole thing — 729 lines — stays where its author put it; the contents beside it link to each section on GitHub.
源代码深度理解分析器 v2.3 (中文版)
基于认知科学研究的专业代码分析工具，支持三种分析深度，确保真正理解代码，而非产生流畅幻觉。
核心原则：理解 WHY，而非只知道 WHAT。像有经验的工程师给朋友讲解，而非照本宣科堆砌术语。
研究支撑：Dunlosky et al. · Chi et al. · Karpicke & Roediger
三种分析模式
| 用户意图 | 模式 | 触发词示例 | 分析时长 |
|---|---|---|---|
| 快速浏览/代码审查 | Quick | "快速看一下"、"这段代码干嘛的"、"简单扫一眼" | 5-10 分钟 |
| 学习理解/技术调研 | Standard ⭐ | "分析一下"、"帮我理解"、"解释一下"、"什么原理" | 15-20 分钟 |
| 深度掌握/大型项目 | Deep 🚀 | "彻底分析"、"完全掌握"、"深入研究"、"面试准备"、"项目整体分析" | 30+ 分钟 |
默认使用 Standard Mode。系统根据代码规模和用户意图自动选择模式。
Deep Mode 内部策略选择：
if 代码行数 <= 2000:
策略 A：渐进式生成（顺序填充章节）
elif 代码行数 <= 10000 且 文件数 <= 20:
策略 B：并行处理（子 Agent 章节级并行）
else: # 行数 > 10000 或 文件数 > 20
策略 C：分层并行（模块级扫描 → 章节级并行）
分析输出结构
Quick Mode（5-10 分钟）
# [代码名称] 快速分析
## 1. 快速概览
- 编程语言和版本 / 代码规模和类型 / 核心依赖
## 2. 功能说明
- 主要功能是什么 (WHAT) + 简要 WHY
## 3. 核心算法/设计
- 复杂度（如有）+ 设计模式（如有）+ WHY 选择
## 4. 关键代码段
- 3-5 个核心代码段，每段简要说明作用
## 5. 依赖关系
- 外部库列表及用途
## 6. 快速使用示例
Standard Mode（15-20 分钟）⭐
# [代码名称] 深度理解分析
## 理解验证状态
| 核心概念 | 自我解释 | 理解"为什么" | 应用迁移 | 状态 |
|---------|---------|-------------|---------|------|
| [概念] | ✅/❌ | ✅/⚠️/❌ | ✅/❌ | [状态] |
## 1. 快速概览
## 2. 背景与动机（3 个 WHY）
## 3. 核心概念说明（每个概念 2-3 个 WHY）
## 4. 算法与理论（复杂度 + WHY + 参考）
## 5. 设计模式（WHY 使用 + 不用会怎样）
## 6. 关键代码深度解析（见第 6 步）
## 7. 依赖关系与使用示例（含 WHY 注释）
Deep Mode（30+ 分钟）
完整章节结构（严格按此编号，禁止引入 Phase/Part/Section 等额外层级）：
# [代码名称] 深度理解分析
## 理解验证状态
## 项目完整地图（文件数 > 5 时）
## 1. 快速概览
## 2. 背景与动机（3 个 WHY）
## 3. 核心概念网络（每个概念 3 WHY + 概念关系矩阵）
## 4. 算法与理论（复杂度 + WHY + 参考）
## 5. 设计模式（WHY 使用 + 不用会怎样）
## 6. 关键代码深度解析
### 核心片段清单（6A）
### 片段 #1：[名称]
#### 1.1 代码整体作用
#### 1.2 核心逻辑分析
#### 1.3 逐行代码解释
#### 1.4 关键设计点
#### 1.5 完整示例（三组对比）
#### 1.6 使用注意与改进建议
### 片段 #2：[名称]
[同上 6 节结构，每片段编号与片段编号一致]
...
## 7. 测试用例分析（检测到测试文件时）
## 8. 应用迁移场景（至少 2 个）
## 9. 依赖关系与使用示例
## 10. 质量验证清单
## 覆盖率摘要（并行模式时）
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 729 lines · 80 tokens per session scan A 26eca5238373
code-reader-v2-cn is a skill published in the GitHub repository notlate-cn/code-reader-skills (148 stars, last pushed 5mo ago), licensed MIT. It adds 80 tokens to every session and 7,908 once invoked, about $0.0004 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.