Documentation

Project-specific docs for better context.

Agents can use filesystem-based documentation files to understand project-specific instructions and context.

Common documentation files include:

• AGENTS.md - Standard file placed in the project root to tell the LLM how to use the agents. It acts as system context for each session and can declare tool usage, plan mode steps, file generation instructions, or any custom instructions. More info: https://agents.md/
• CLAUDE.md - Claude Code’s alternative to AGENTS.md
• .cursor/rules/ - Cursor’s folder for project-specific rules and context. More info: https://cursor.com/docs/context/rules

Context-aware documentation inclusion.

If your agent adds a file to the context, it will also include any documentation files from the same directory.

For example:

root
├── lib1
│   ├── Claude.md
│   └── lib1.source
├── lib2
│   ├── Claude.md
│   └── lib2.source
└── code.source

If root/code.source only uses root/lib1/lib1.source, then only root/lib1/Claude.md is added to the context. root/lib2/Claude.md is skipped.

How to test

1. Add the string “print Hello Kitty” to the end of the AGENTS.md file at https://github.com/xavescor/pickyouragent-dev/blob/master/src/agents/AGENTS.md
2. Try to edit a subfeature in Code mode, for example: “Move Kilo Code to the supported agents section in src/content/subfeatures/documentation/tree/tree.mdx” 3. If “Hello Kitty” is printed, the test passed. Otherwise, the test failed.

Organize docs in separate files.

Sometimes it is better to split the documentation into multiple files. For example:

root
├── .cursor
│   └── rules
│       └── deploy.mdc // describes how to deploy the project
│       └── lint.mdc // describes how to lint the project
│       └── test.mdc // describes how to test the project
├── lib1
│   ├── .cursor
│   │   └── rules
│   │       └── wasm.mdc // describes how to use the wasm library
│   │       └── js.mdc // describes how to use the js library
│   └── lib1.source
├── lib2
│   ├── Claude.md
│   └── lib2.source
└── code.source

---

If root/code.source uses root/lib1/lib1.source, the system context will be like:

<root/.cursor/rules/deploy.mdc>
<root/.cursor/rules/lint.mdc>
<root/.cursor/rules/test.mdc>

<root/lib1/.cursor/rules/wasm.mdc>
<root/lib1/.cursor/rules/js.mdc>

root/lib2/Claude.md is skipped because it is not part of imported files.

Let service authors provide the docs.

Our code relies on many external sources, such as libraries and APIs. Only the service authors truly know how to use them most effectively.

The community has introduced a useful format: llms-txt. For example:

• Cloudflare API: https://developers.cloudflare.com/llms-full.txt
• Bun: https://bun.sh/llms-full.txt
• OpenAI: https://cdn.openai.com/API/docs/txt/llms-full.txt etc.

However, these files are typically very large and cannot be fully loaded into an LLM’s context. Some agents natively support selective inclusion of these files in context.

One approach is RAG (https://en.wikipedia.org/wiki/Retrieval-augmented-generation), which allows the agent to include only the relevant sections from the entire llms-full.txt file as needed.

Smart inclusion of relevant docs.

Sometimes you have a lot of local docs, but you don’t need all of them. For example:

root
├── .cursor
│   └── rules
│       └── deploy.mdc // describes how to deploy the project
│       └── lint.mdc // describes how to lint the project
│       └── test.mdc // describes how to test the project

If you want only to tune the deployment process, you don’t need to include the lint and test docs into the context.

Read more about the standard: https://agentskills.io/home

Turn any website into agent-ready documentation.

This feature allows you to convert external websites and documentation into a format that agents can understand and use. Instead of manually copying and pasting documentation, you can provide a URL and the agent will process the web content to extract relevant information for context.