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 skills add TashanGKD/tashan-cursor-skills --skill codebase-explorergit clone --depth 1 https://github.com/TashanGKD/tashan-cursor-skillsWrote 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/skills/tashangkd/tashan-cursor-skills/codebase-explorer)<a href="https://agentmods.dev/skills/tashangkd/tashan-cursor-skills/codebase-explorer"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-cursor-skills/codebase-explorer/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.
<a href="https://agentmods.dev/skills/tashangkd/tashan-cursor-skills/codebase-explorer"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-cursor-skills/codebase-explorer.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00099 | $0.02443 |
| Opus 5 | $0.00049 | $0.01222 |
| Sonnet 5 | $0.00020 | $0.00489 |
| Haiku 4.5 | $0.00010 | $0.00244 |
Grade A, and why
codebase-explorer 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 6d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
代码库探索(codebase-explorer)
在提出任何架构改建议之前,必须先有可信赖的全局图景。 基于 closure-orchestration-package 的 repo-system-cartographer 模式本地化。
知识导航表(执行前必须理解的概念根)
| 层级 | 文档 | 需要理解的概念 |
|---|---|---|
| D0 认知根(必读) | _内部总控/认知结构/L1_系统性文档/技术架构思维维度/技术架构方案.md |
整体技术体系框架:各项目的技术选型/架构模式/层次划分(接手代码库时的全局视角) |
| D3 规范参考 | _内部总控/开发规范/公共模块注册表.md |
已有公共模块清单(探索时识别代码库对公共模块的使用情况) |
| D4 运行时数据 | 目标项目 技术架构.md(若存在)+ 项目代码根目录 |
已有架构文档(对比预期 vs 实际)+ 实际代码目录结构 |
核心概念速查: ① 探索顺序:有文档→先读文档了解预期,再看代码了解实际;无文档→先扫描再输出 ② 差距 = 代码与文档不一致的地方(是 issue-tracker 的候选输入) ③ 输出架构理解文档 = K-object.create(K4项目规格):写入 _内部总控/开发规范/架构理解/
激活后立即执行
Step 1 确认探索目标
询问(如未说明):
「要探索的代码库路径是什么?探索目的是:
① 快速理解(输出架构概览)
② 深度分析(含差距分析和建议)
③ 接手开发(含与产品定义的对比)」
Step 2 用内置 explore 子智能体并行扫描(不占主对话 context)
- 扫描顶层目录结构(文件树)
- 读取 README.md / 开发规范.md / 产品定义.md(若存在)
- 识别主要配置文件(package.json / requirements.txt / docker-compose.yml 等)
Step 3 识别技术栈与架构层次
从扫描结果提取:
- 前端技术(框架/构建工具/状态管理)
- 后端技术(语言/框架/API 风格)
- 数据层(数据库/ORM/迁移工具)
- AI/ML 层(若有,LLM/向量库/调用方式)
- 基础设施(部署/CI/CD/容器)
Step 4 读取核心文件(最多 5-8 个,聚焦最关键的)
优先级:主入口文件 > 核心业务逻辑 > 数据模型 > API 定义
Step 5 提取架构模式与源真相
识别:
- 哪些文件是「真源」(source of truth)
- 模块边界在哪里
- 前后端如何通信
- 数据流向是什么
- 有哪些明显的技术债或架构风险
Step 5.5【浅层模块识别(improve-my-codebase)】
对已识别的核心模块,评估「深度」:
浅层模块(shallow module)特征——接口复杂但实现简单,认知成本高于价值贡献:
□ 接口臃肿:调用方需要了解≥5个参数才能调用,或需要了解实现细节才能正确传参
□ 实现轻薄:函数体≤10行,只做简单的格式转换/转发,没有真正的业务逻辑
□ 多层传递:参数从A穿透B传到C,B不使用该参数(B是「中间人」)
改进方向:将多个浅层模块的功能内聚到一个接口更简单的深层模块
→ 接口应该隐藏复杂度,而非暴露复杂度
输出格式:
| 模块 | 类型 | 问题描述 | 改进建议 |
|---|---|---|---|
| [模块名] | 浅层/深层 | [具体问题] | [合并/重构方向] |
Step 5.6【可测试性扫描(improve-my-codebase)】
识别以下阻碍测试的代码模式:
□ 隐式依赖:函数内部直接实例化依赖(new DatabaseClient()、硬编码 URL)
→ 改为:依赖注入(参数传入 / 配置注入)
□ 无接口抽象:业务逻辑直接调用外部服务(DB、AI API、文件系统、时间函数)
→ 改为:引入接口/协议层(定义抽象,测试时可替换为 mock)
□ 全局副作用:函数修改全局状态 / 写文件 / 发网络请求而不在签名中声明
→ 改为:纯函数提取(将副作用边界化,核心逻辑变纯函数)
□ 超长函数:单个函数超过50行,难以独立测试各逻辑分支
→ 改为:提取子函数,每个子函数单独可测
输出格式:
| 文件/函数 | 问题类型 | 具体描述 | 改进优先级 |
|---|---|---|---|
| [路径] | 隐式依赖/无抽象/全局副作用/超长 | [描述] | P0/P1/P2 |
Step 6 与产品定义/需求对比(若存在)
Read: 产品经理/产品定义.md(若存在)
输出:
- 已实现的功能
- 架构就绪但未完全实现的功能
- 产品要求但代码中完全缺失的功能
- 与需求存在偏差的实现
Step 7 输出架构理解文档
写入:技术架构师/[项目名]_架构理解_YYYYMMDD.md
结构:
- 一句话定位(这个系统是什么)
- 技术栈全景
- 分层架构图(文本形式)
- 核心模块与职责
- 真源声明(哪个文件/模块负责哪类数据)
- 已发现的风险和模糊点
- 与产品定义的差距(若做了 Step 6)
What ships with it
2 files 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.
- 6d ago First seen · 196 lines · 99 tokens per session scan A f9846e38577b
codebase-explorer is a skill published in the GitHub repository TashanGKD/tashan-cursor-skills (20 stars, last pushed 5mo ago), licensed MIT. It adds 99 tokens to every session and 2,443 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
template-helpers
Catalog of the reusable building blocks shipped with this Android template — BaseActivity/BaseFragment, the helpers/ extension files (navigation, lifecycle, toast, snackbar, dialogs, images, permissions, theme, locale, settings intents, date, delay), common/ (Firebase, network, observers), and…
android-feature
Workflow for implementing a new Android feature, screen, fragment, activity, dialog, adapter, or enhancement in this XML/MVVM template. Use whenever the user asks to add, build, implement, or extend functionality — before writing any code. Covers planning, the MVVM/MVI skeleton, the Android configuration checklist…
android-new-project
Workflow for turning a fresh copy of this Android template into a new app — renaming the package/namespace/applicationId, branding (icons, splash, palette, fonts), Firebase setup, signing config, stripping unused sample screens, and verifying the foundation. Use when the user says they are starting a new app…
android-upgrade
Workflow for changing an existing working Android project — upgrading dependencies, AGP/Gradle or SDK levels, migrating deprecated APIs, refactoring, and fixing bugs, without breaking what already works. Covers baseline verification, scoping the diff, targetSdk behaviour changes, SharedPreferences/Room data…
android-build-config
Gradle and build configuration rules for this template — AGP 9 / Gradle 9 DSL (built-in Kotlin, compileSdk block, optimization block instead of minify/proguard), the gradle/libs.versions.toml version catalog, R8 keep rules in keepRules/.keep, gradle.properties defaults, and manifest registration. Use when editing…
android-preflight
Final verification checklist to run before declaring Android work finished — build, both themes, string resources, lifecycle and leak risks, registered permissions and components, resource parity between values and values-night, and honest reporting of what was and was not verified. Use at the end of any feature, fix…