ros/claude-code-router
1
0
Fork 0
mirror of https://github.com/musistudio/claude-code-router.git synced 2026-01-30 06:12:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

add posts

Browse Source
This commit is contained in:
musistudio
2026-01-10 21:42:01 +08:00
parent 4afa571934
commit c73fe0d49d
4 changed files with 308 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

154
blog/en/progressive-disclosure-of-agent-tools-from-the-perspective-of-cli-tool-style.md Normal file
View File

@@ -0,0 +1,154 @@
# Progressive Disclosure of Agent Tools from the Perspective of CLI Tool Style
It has been nearly two months since Anthropic released [Skills](https://www.anthropic.com/engineering/equipping-agents-for-the-real-world-with-agent-skills). In this release, Anthropic mentioned a term: Progressive Disclosure. What exactly is this? What problem does it solve?
Actually, in my Vibe Coding workflow, I rarely use MCP. The reason is that I find the implementation quality of MCP to be inconsistent. At its core, it’s about context injection (the essence of tools is also context injection), and I’m not sure if prompts written by others might affect my workflow, so I simply avoid using it altogether. The current implementation of MCP essentially wraps all functionalities as tools exposed to the Agent (one functionality wrapped as one tool, given a detailed description, telling the agent when to call it and what the parameter format is). This has led to the current explosion of prompts.
It wasn’t until Anthropic released Skills and I looked into it that I realized its essence is still prompt injection. If MCP provides a specification for injecting tools, then what Skills advocates is somewhat "unconventional." Skills provides a Markdown document to describe the purpose and best practices of the skill, along with some attached scripts (different from MCP).
![image](https://www.anthropic.com/_next/image?url=https%3A%2F%2Fwww-cdn.anthropic.com%2Fimages%2F4zrzovbb%2Fwebsite%2F6f22d8913dbc6228e7f11a41e0b3c124d817b6d2-1650x929.jpg&w=3840&q=75)
Since these scripts run directly on the user’s local machine, there are significant security risks. If users cannot review the script code, it can easily lead to serious security issues such as data leakage or virus infections. Compared to MCP, which provides a standardized interface, Skills offer a series of script files. Different skills may have different types of script files—for example, some scripts are implemented in Node.js, while others use Python. To use these scripts, users also need to install the corresponding runtime and dependencies. This is why I describe it as "unconventional."
Is this really the best practice?
Regarding Progressive Disclosure, here is how Anthropic describes it:
> Progressive disclosure is the core design principle that makes Agent Skills flexible and scalable. Like a well-organized manual that starts with a table of contents, then specific chapters, and finally a detailed appendix, skills let Claude load information only as needed:
> ![image](https://www.anthropic.com/_next/image?url=https%3A%2F%2Fwww-cdn.anthropic.com%2Fimages%2F4zrzovbb%2Fwebsite%2Fa3bca2763d7892982a59c28aa4df7993aaae55ae-2292x673.jpg&w=3840&q=75)
> Agents with a filesystem and code execution tools don’t need to read the entirety of a skill into their context window when working on a particular task. This means that the amount of context that can be bundled into a skill is effectively unbounded.
The following diagram shows how the context window changes when a skill is triggered by a user’s message.
![image](https://www.anthropic.com/_next/image?url=https%3A%2F%2Fwww-cdn.anthropic.com%2Fimages%2F4zrzovbb%2Fwebsite%2F441b9f6cc0d2337913c1f41b05357f16f51f702e-1650x929.jpg&w=3840&q=75)
Do we really need to implement it this way?
In our daily use of CLI tools, most CLI tools come with a `--help` parameter for viewing the tool's usage and instructions. Isn't that essentially the tool's user manual? For example:
```shell
> npm --help
npm <command>
Usage:
npm install install all the dependencies in your project
npm install <foo> add the <foo> dependency to your project
npm test run this project's tests
npm run <foo> run the script named <foo>
npm <command> -h quick help on <command>
npm -l display usage info for all commands
npm help <term> search for help on <term>
npm help npm more involved overview
All commands:
access, adduser, audit, bugs, cache, ci, completion,
config, dedupe, deprecate, diff, dist-tag, docs, doctor,
edit, exec, explain, explore, find-dupes, fund, get, help,
help-search, hook, init, install, install-ci-test,
install-test, link, ll, login, logout, ls, org, outdated,
owner, pack, ping, pkg, prefix, profile, prune, publish,
query, rebuild, repo, restart, root, run-script, sbom,
search, set, shrinkwrap, star, stars, start, stop, team,
test, token, uninstall, unpublish, unstar, update, version,
view, whoami
Specify configs in the ini-formatted file:
/Users/xxx/.npmrc
or on the command line via: npm <command> --key=value
More configuration info: npm help config
Configuration fields: npm help 7 config
```
This manual doesn't return every possible usage of every command either. It only lists which commands are available and what functions they can perform. For the specific usage of a command, you can still obtain it by using the `--help` parameter:
```shell
> npm install --help
Install a package
Usage:
npm install [<package-spec> ...]
Options:
[-S|--save|--no-save|--save-prod|--save-dev|--save-optional|--save-peer|--save-bundle]
[-E|--save-exact] [-g|--global]
[--install-strategy <hoisted|nested|shallow|linked>] [--legacy-bundling]
[--global-style] [--omit <dev|optional|peer> [--omit <dev|optional|peer> ...]]
[--include <prod|dev|optional|peer> [--include <prod|dev|optional|peer> ...]]
[--strict-peer-deps] [--prefer-dedupe] [--no-package-lock] [--package-lock-only]
[--foreground-scripts] [--ignore-scripts] [--no-audit] [--no-bin-links]
[--no-fund] [--dry-run] [--cpu <cpu>] [--os <os>] [--libc <libc>]
[-w|--workspace <workspace-name> [-w|--workspace <workspace-name> ...]]
[-ws|--workspaces] [--include-workspace-root] [--install-links]
aliases: add, i, in, ins, inst, insta, instal, isnt, isnta, isntal, isntall
Run "npm help install" for more info
```
Doesn't this resemble the definition of progressive disclosure mentioned above?
Can we implement an MCP in this style to achieve progressive disclosure of tools without needing skills? I used Codex to convert the official PDF Skill into an MCP, exposing only a single tool:
```json
{
"name": "mcp__pdf__pdf",
"description": "Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.You need to pass in the --help parameter to obtain the usage of this tool first.",
"input_schema": {
"type": "object",
"properties": {
"params": {
"$ref": "#/$defs/PdfCommandInput"
}
},
"required": [
"params"
],
"$defs": {
"PdfCommandInput": {
"additionalProperties": false,
"properties": {
"argv": {
"description": "Command tokens excluding the leading 'pdf' executable name",
"items": {
"type": "string"
},
"title": "Argv",
"type": "array"
},
"command": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional command string; if set, it will be split like a shell",
"title": "Command"
}
},
"title": "PdfCommandInput",
"type": "object"
}
},
"title": "pdfArguments"
}
}
```
Below is the change in the context window when using this MCP:
```json
User: Extract all the text from test.pdf and write it into result.txt
Agent: Tool(name="pdf", args=["--help"])
Tool: pdf - Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale在使用之前你需要先传入--help参数以获取该工具的用法\n\nUsage:\n pdf [--help] <domain> <command> [options]\n\nDomains:\n forms Fill, extract, and validate PDF form fields.\n documents Create, merge, and split PDFs.\n text Extract text content from PDFs.\n tables Extract tables (heuristic, whitespace-based).\n images Render PDF pages to PNG images.\n\nRun `pdf <domain> --help` for domain help.\nRun `pdf <domain> <command> --help` for command help.
Agent: Tool(name="pdf", args=["text", "--help"])
Tool: text - Extract text content from PDFs.\n\nUsage:\n pdf text <command> [options]\n\nCommands:\n extract Extract text content from a PDF.\n\nRun `pdf text <command> --help` for details.
Agent: Tool(name="pdf", args=["text", "extract", "--help"])
Tool: usage: pdf text extract --pdf PDF_PATH [--pages PAGES] [--out OUTPUT_PATH]\n [--format {text,json}] [--overwrite]\n\nExtract text content from a PDF.\n\noptions:\n --pdf PDF_PATH Input PDF\n --pages PAGES Page selection like 1,3-5 or 'all' (default: all)\n --out OUTPUT_PATH Write extracted text to a file\n --format {text,json} Output format (default: text)\n --overwrite Overwrite output file if it exists\n
Agent: Tool(name="pdf", args=["text", "extract", "--pdf", "test.pdf", "--out", "result.txt", "--overwrite"])
Tool: {"result": {"stdout": "xx","data": {"pdf_path": "test.pdf","page_count": 6,"pages": [xxx],"format": "text","output_path": "result.txt"}}}
Agent: xxx
```
From the perspective of context changes, progressive disclosure has been fully realized. This MCP code is open-source (entirely written by Codex, serving only to validate the idea without any review): https://github.com/musistudio/pdf-skill-mcp
If you have any thoughts or ideas, I’d also welcome the opportunity to discuss them with you. email: [m@musiiot.top](mailto://m@musiiot.top )

150
blog/zh/从CLI工具风格看工具渐进式披露.md Normal file
View File

@@ -0,0 +1,150 @@
# 从CLI工具风格看Agent工具渐进式披露
距离Anthropic发布[Skills](https://www.anthropic.com/engineering/equipping-agents-for-the-real-world-with-agent-skills)也过去将近两个月的时间了，其中Anthropic提到了一个术语渐进式披露(Progressive Disclosure)，这到底是什么东西？解决了什么问题？
其实在我的Vibe Coding流程中，我很少使用MCP。因为我觉得MCP实现质量层次不齐，本质是上下文注入(工具的本质也是上下文注入)，我不确定别人写的提示词会不会影响到我的工作流，干脆直接不用。现在的MCP实现基本上就是把所有的功能全都包装成工具暴露给Agent(一个功能包装成一个工具，给定详细的描述，告诉agent在什么时候进行调用，参数格式是什么)，这就导致了现在的提示词爆炸。
直到Anthropic发布了Skills，研究了一下发现本质仍然是提示词注入。如果说MCP是提供了一套注入工具的规范，那么Skills所提倡的则是“离经叛道”。Skills给了一个Markdown文档用于描述该skill的用途和最佳用法，附带提供了一些脚本(与MCP不同)。
![image](https://www.anthropic.com/_next/image?url=https%3A%2F%2Fwww-cdn.anthropic.com%2Fimages%2F4zrzovbb%2Fwebsite%2F6f22d8913dbc6228e7f11a41e0b3c124d817b6d2-1650x929.jpg&w=3840&q=75)
由于这些脚本直接在用户本地运行，存在极大的安全风险。如果用户不能对脚本代码进行review，很容易造成数据泄露、感染病毒等严重安全性问题。相比于MCP提供一个标准化的接口，Skill提供一系列的脚本文件，不同的skill可能拥有不同类型的脚本文件，比如有些脚本使用node.js实现，有些脚本使用Python实现，要使用这些脚本还需要用户安装对应的运行时和脚本所需要的依赖。这也是我说“离经叛道”的原因所在。
这真的是最佳实践吗？
关于渐进式披露，Anthropic是这样描述的：
> 渐进式披露是使代理技能灵活且可扩展的核心设计原则。就像一本组织良好的手册，从目录开始，然后是具体章节，最后是详细的附录一样，技能允许 Claude 仅在需要时加载信息：
> ![image](https://www.anthropic.com/_next/image?url=https%3A%2F%2Fwww-cdn.anthropic.com%2Fimages%2F4zrzovbb%2Fwebsite%2Fa3bca2763d7892982a59c28aa4df7993aaae55ae-2292x673.jpg&w=3840&q=75)
> 拥有文件系统和代码执行工具的智能体在执行特定任务时，无需将技能的全部内容读取到上下文窗口中。这意味着技能中可以包含的上下文信息量实际上是无限的。
下图是使用Skill的上下文窗口变化
![image](https://www.anthropic.com/_next/image?url=https%3A%2F%2Fwww-cdn.anthropic.com%2Fimages%2F4zrzovbb%2Fwebsite%2F441b9f6cc0d2337913c1f41b05357f16f51f702e-1650x929.jpg&w=3840&q=75)
我们真的需要这样去实现吗？
在我们平时使用CLI工具时，一般的CLI工具都会带有一个`--help`参数，用于查看该工具的用法和说明，这不就是该工具的使用手册吗？比如：
```shell
> npm --help
npm <command>
Usage:
npm install install all the dependencies in your project
npm install <foo> add the <foo> dependency to your project
npm test run this project's tests
npm run <foo> run the script named <foo>
npm <command> -h quick help on <command>
npm -l display usage info for all commands
npm help <term> search for help on <term>
npm help npm more involved overview
All commands:
access, adduser, audit, bugs, cache, ci, completion,
config, dedupe, deprecate, diff, dist-tag, docs, doctor,
edit, exec, explain, explore, find-dupes, fund, get, help,
help-search, hook, init, install, install-ci-test,
install-test, link, ll, login, logout, ls, org, outdated,
owner, pack, ping, pkg, prefix, profile, prune, publish,
query, rebuild, repo, restart, root, run-script, sbom,
search, set, shrinkwrap, star, stars, start, stop, team,
test, token, uninstall, unpublish, unstar, update, version,
view, whoami
Specify configs in the ini-formatted file:
/Users/xxx/.npmrc
or on the command line via: npm <command> --key=value
More configuration info: npm help config
Configuration fields: npm help 7 config
```
这份手册也不会返回所有的命令所有的用法，它只会返回它有哪些命令可以实现什么功能，对于命令的具体用法你仍然可以通过`--help`参数获得：
```shell
> npm install --help
Install a package
Usage:
npm install [<package-spec> ...]
Options:
[-S|--save|--no-save|--save-prod|--save-dev|--save-optional|--save-peer|--save-bundle]
[-E|--save-exact] [-g|--global]
[--install-strategy <hoisted|nested|shallow|linked>] [--legacy-bundling]
[--global-style] [--omit <dev|optional|peer> [--omit <dev|optional|peer> ...]]
[--include <prod|dev|optional|peer> [--include <prod|dev|optional|peer> ...]]
[--strict-peer-deps] [--prefer-dedupe] [--no-package-lock] [--package-lock-only]
[--foreground-scripts] [--ignore-scripts] [--no-audit] [--no-bin-links]
[--no-fund] [--dry-run] [--cpu <cpu>] [--os <os>] [--libc <libc>]
[-w|--workspace <workspace-name> [-w|--workspace <workspace-name> ...]]
[-ws|--workspaces] [--include-workspace-root] [--install-links]
aliases: add, i, in, ins, inst, insta, instal, isnt, isnta, isntal, isntall
Run "npm help install" for more info
```
这是不是很像上面的渐进式披露的定义？
我们是不是可以按照这种风格去实现一个MCP来实现无需skill的工具渐进式披露？我使用Codex将官方的PDF Skill转换成了一个MCP，只暴露一个工具：
```json
{
"name": "mcp__pdf__pdf",
"description": "Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.You need to pass in the --help parameter to obtain the usage of this tool first.",
"input_schema": {
"type": "object",
"properties": {
"params": {
"$ref": "#/$defs/PdfCommandInput"
}
},
"required": [
"params"
],
"$defs": {
"PdfCommandInput": {
"additionalProperties": false,
"properties": {
"argv": {
"description": "Command tokens excluding the leading 'pdf' executable name",
"items": {
"type": "string"
},
"title": "Argv",
"type": "array"
},
"command": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional command string; if set, it will be split like a shell",
"title": "Command"
}
},
"title": "PdfCommandInput",
"type": "object"
}
},
"title": "pdfArguments"
}
}
```
下面是使用该MCP的上下文窗口变化
```json
User: Extract all the text from test.pdf and write it into result.txt
Agent: Tool(name="pdf", args=["--help"])
Tool: pdf - Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale在使用之前你需要先传入--help参数以获取该工具的用法\n\nUsage:\n pdf [--help] <domain> <command> [options]\n\nDomains:\n forms Fill, extract, and validate PDF form fields.\n documents Create, merge, and split PDFs.\n text Extract text content from PDFs.\n tables Extract tables (heuristic, whitespace-based).\n images Render PDF pages to PNG images.\n\nRun `pdf <domain> --help` for domain help.\nRun `pdf <domain> <command> --help` for command help.
Agent: Tool(name="pdf", args=["text", "--help"])
Tool: text - Extract text content from PDFs.\n\nUsage:\n pdf text <command> [options]\n\nCommands:\n extract Extract text content from a PDF.\n\nRun `pdf text <command> --help` for details.
Agent: Tool(name="pdf", args=["text", "extract", "--help"])
Tool: usage: pdf text extract --pdf PDF_PATH [--pages PAGES] [--out OUTPUT_PATH]\n [--format {text,json}] [--overwrite]\n\nExtract text content from a PDF.\n\noptions:\n --pdf PDF_PATH Input PDF\n --pages PAGES Page selection like 1,3-5 or 'all' (default: all)\n --out OUTPUT_PATH Write extracted text to a file\n --format {text,json} Output format (default: text)\n --overwrite Overwrite output file if it exists\n
Agent: Tool(name="pdf", args=["text", "extract", "--pdf", "test.pdf", "--out", "result.txt", "--overwrite"])
Tool: {"result": {"stdout": "xx","data": {"pdf_path": "test.pdf","page_count": 6,"pages": [xxx],"format": "text","output_path": "result.txt"}}}
Agent: xxx
```
从上下文变化情况来看，完全实现了渐进式披露，该MCP代码开源(代码完全由codex编写，只验证想法，未做任何审查): https://github.com/musistudio/pdf-skill-mcp
如果你有什么想法也欢迎与我进行交流 email: [m@musiiot.top](mailto://m@musiiot.top )