Borrowing it
Nothing to install: this file belongs to Asheng008/unifiles-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Asheng008/unifiles-mcp/main/.cursor/commands/explain.mdgit clone --depth 1 https://github.com/Asheng008/unifiles-mcpWrote 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/commands/asheng008/unifiles-mcp/explain)<a href="https://agentmods.dev/commands/asheng008/unifiles-mcp/explain"><img src="https://agentmods.dev/badge/commands/asheng008/unifiles-mcp/explain.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.02770 |
| Opus 5 | $0.00000 | $0.01385 |
| Sonnet 5 | $0.00000 | $0.00554 |
| Haiku 4.5 | $0.00000 | $0.00277 |
Grade A, and why
explain 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 7d 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 — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
解释代码/文字/文件
解释用户选择的代码、文字或文件内容,提供清晰、详细的中文说明。
目标
- 分析并解释用户选择的代码片段、文字内容、文件或终端输出
- 提供清晰、结构化的中文解释
- 根据内容类型(代码、文档、配置、终端输出等)采用相应的解释方式
- 帮助用户理解代码逻辑、设计意图、配置含义、命令/错误输出等
处理流程
1. 识别输入类型
根据用户选择的内容,判断类型:
- 代码片段:Python、配置文件、Markdown 等代码
- 文档文字:README、技术文档、注释等
- 文件路径:用户选择或提及的文件
- 终端输出:命令执行结果、错误日志、测试输出、构建/安装输出等(来自终端、控制台或 IDE 的终端面板)
- 混合内容:代码 + 注释、多文件、命令与输出组合等
2. 分析内容
根据内容类型进行相应分析:
代码分析:
- 功能说明:这段代码做什么
- 逻辑流程:代码执行流程
- 关键概念:使用的技术、库、模式
- 参数/返回值:函数签名、类型注解
- 依赖关系:与其他代码/模块的关系
- 潜在问题:可能的错误、边界情况
文档分析:
- 主要内容:文档的核心信息
- 结构组织:章节、层次结构
- 关键要点:重要概念、规则、约定
- 使用场景:适用情况、示例
配置文件分析:
- 配置项说明:每个配置的含义
- 默认值:默认设置及其影响
- 依赖关系:配置之间的关联
- 最佳实践:推荐的配置方式
终端输出分析:
- 输出类型:正常输出、错误信息、警告、测试结果、构建/安装日志等
- 结构解析:命令提示符、标准输出、标准错误、退出码(如有)
- 关键信息:成功/失败标志、错误堆栈、行号、路径、建议或 hint
- 原因推断:可能触发该输出的命令或操作、环境或配置因素
- 解决建议:若是错误/警告,给出排查步骤或修复方向
2.1 查询工具使用(当遇到不确定内容时)
当遇到以下情况时,必须使用查询工具:
- 不熟悉的库、框架、API 用法
- 不确定的配置项含义
- 需要最新文档或最佳实践
- 代码中使用了不常见的模式或技术
- 需要验证某个概念或实现方式
工具使用优先级:
-
Context7(MCP 工具) - 优先使用
- 适用场景:查询库的官方文档、API 用法、代码示例
- 使用方法:
- 先使用
mcp_context7_resolve-library-id解析库名称 - 再使用
mcp_context7_query-docs查询具体文档
- 先使用
- 示例:
- 代码中使用了
pandas.ExcelWriter→ 查询 pandas 官方文档 - 配置中有
[tool.mypy]→ 查询 mypy 配置文档 - 代码使用了
pathlib.Path→ 查询 Python 标准库文档
- 代码中使用了
-
联网搜索(Web Search) - 备选方案
- 适用场景:
- Context7 无法找到相关文档
- 需要查找最新信息、博客文章、Stack Overflow 解答
- 查询特定错误信息或解决方案
- 使用方法:使用
web_search工具 - 示例:
- 查询 "pandas ExcelWriter 多工作表写入最佳实践"
- 查询 "mypy python_version 3.10 配置说明"
- 查询特定错误信息或警告
- 适用场景:
-
RefTools(MCP 工具) - 补充查询
- 适用场景:搜索通用技术文档、GitHub 文档、PDF 文档
- 使用方法:使用
mcp_RefTools_ref_search_documentation和mcp_RefTools_ref_read_url
查询后的处理:
- 将查询结果整合到解释中
- 明确标注信息来源(如"根据 pandas 官方文档...")
- 如果查询结果与代码中的用法不一致,说明可能的问题
- 如果查询无结果,说明情况并基于现有知识提供解释
3. 提供解释
解释格式:
- 概述:一句话总结内容的核心
- 详细说明:
- 代码:逐行或逐块解释
- 文档:按章节或要点说明
- 配置:逐项说明
- 终端输出:输出类型、各部分含义、错误/警告解读、退出码含义
- 关键点:重要概念、设计决策、注意事项
- 相关上下文:与项目其他部分的关联
- 示例/用法(如适用):如何使用、示例代码;若为错误输出,补充排查或修复建议
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.
- 7d ago First seen · 271 lines · 0 tokens per session scan A e6f89c1ca98c
explain is a command published in the GitHub repository Asheng008/unifiles-mcp (0 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,770 tokens. 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.