docs: clarify memory bank status indicators#1
Conversation
Summary of ChangesHello @jeremylongshore, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request, titled "docs: clarify memory bank status indicators," intended to update the Highlights
Changelog
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
📝 WalkthroughWalkthroughA documentation file containing guidance on AGENTS.md configuration has been completely removed from the kilocode-docs repository. The 169-line file is deleted with no replacement or alternative content introduced. Changes
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~3 minutes Poem
🚥 Pre-merge checks | ✅ 4 | ❌ 2❌ Failed checks (1 warning, 1 inconclusive)
✅ Passed checks (4 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing touches🧪 Generate unit tests (beta)
No actionable comments were generated in the recent review. 🎉 Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
There was a problem hiding this comment.
Code Review
This pull request is intended to add a clarifying sentence to the documentation regarding memory bank status indicators. However, the current change accidentally deletes the entire agents-md.md file. This is a critical error that will remove an important documentation page and cause broken links throughout the site. The file should be restored, and the intended clarification should be applied.
|
|
||
| # agents.md | ||
|
|
||
| AGENTS.md files provide a standardized way to configure AI agent behavior across different AI coding tools. They allow you to define project-specific instructions, coding standards, and guidelines that AI agents should follow when working with your codebase. | ||
|
|
||
| {% callout type="note" title="Memory Bank Deprecation" %} | ||
| The Kilo Code **memory bank** feature has been deprecated in favor of AGENTS.md. | ||
|
|
||
| **Existing memory bank rules will continue to work.** | ||
|
|
||
| If you'd like to migrate your memory bank content to AGENTS.md: | ||
|
|
||
| 1. Examine the contents in `.kilocode/rules/memory-bank/` | ||
| 2. Move that content into your project's `AGENTS.md` file (or ask Kilo to do it for you) | ||
| {% /callout %} | ||
|
|
||
| ## What is AGENTS.md? | ||
|
|
||
| AGENTS.md is an open standard for configuring AI agent behavior in software projects. It's a simple Markdown file placed at the root of your project that contains instructions for AI coding assistants. The standard is supported by multiple AI coding tools, including Kilo Code, Cursor, and Windsurf. | ||
|
|
||
| Think of AGENTS.md as a "README for AI agents" - it tells the AI how to work with your specific project, what conventions to follow, and what constraints to respect. | ||
|
|
||
| ## Why Use AGENTS.md? | ||
|
|
||
| - **Portability**: Works across multiple AI coding tools without modification | ||
| - **Version Control**: Lives in your repository alongside your code | ||
| - **Team Consistency**: Ensures all team members' AI assistants follow the same guidelines | ||
| - **Project-Specific**: Tailored to your project's unique requirements and conventions | ||
| - **Simple Format**: Plain Markdown - no special syntax or configuration required | ||
|
|
||
| ## File Location and Naming | ||
|
|
||
| ### Project-Level AGENTS.md | ||
|
|
||
| Place your AGENTS.md file at the **root of your project**: | ||
|
|
||
| ``` | ||
| my-project/ | ||
| ├── AGENTS.md # Primary filename (recommended) | ||
| ├── src/ | ||
| ├── package.json | ||
| └── README.md | ||
| ``` | ||
|
|
||
| **Supported filenames** (in order of precedence): | ||
|
|
||
| 1. `AGENTS.md` (uppercase, plural - recommended) | ||
| 2. `AGENT.md` (uppercase, singular - fallback) | ||
|
|
||
| {% callout type="warning" title="Case Sensitivity" %} | ||
| The filename must be uppercase (`AGENTS.md`), not lowercase (`agents.md`). This ensures consistency across different operating systems and tools. | ||
| {% /callout %} | ||
|
|
||
| ### Subdirectory AGENTS.md Files | ||
|
|
||
| You can also place AGENTS.md files in subdirectories to provide context-specific instructions: | ||
|
|
||
| ``` | ||
| my-project/ | ||
| ├── AGENTS.md # Root-level instructions | ||
| ├── src/ | ||
| │ └── backend/ | ||
| │ └── AGENTS.md # Backend-specific instructions | ||
| └── docs/ | ||
| └── AGENTS.md # Documentation-specific instructions | ||
| ``` | ||
|
|
||
| When working in a subdirectory, Kilo Code will load both the root AGENTS.md and any subdirectory AGENTS.md files, with subdirectory files taking precedence for conflicting instructions. | ||
|
|
||
| ## File Protection | ||
|
|
||
| Both `AGENTS.md` and `AGENT.md` are **write-protected files** in Kilo Code. This means: | ||
|
|
||
| - The AI agent cannot modify these files without explicit user approval | ||
| - You'll be prompted to confirm any changes to these files | ||
| - This prevents accidental modifications to your project's AI configuration | ||
|
|
||
| ## Basic Syntax and Structure | ||
|
|
||
| AGENTS.md files use standard Markdown syntax. There's no required structure, but organizing your content with headers and lists makes it easier for AI models to parse and understand. | ||
|
|
||
| ### Recommended Structure | ||
|
|
||
| ```markdown | ||
| # Project Name | ||
|
|
||
| Brief description of the project and its purpose. | ||
|
|
||
| ## Code Style | ||
|
|
||
| - Use TypeScript for all new files | ||
| - Follow ESLint configuration | ||
| - Use 2 spaces for indentation | ||
|
|
||
| ## Architecture | ||
|
|
||
| - Follow MVC pattern | ||
| - Keep components under 200 lines | ||
| - Use dependency injection | ||
|
|
||
| ## Testing | ||
|
|
||
| - Write unit tests for all business logic | ||
| - Maintain >80% code coverage | ||
| - Use Jest for testing | ||
|
|
||
| ## Security | ||
|
|
||
| - Never commit API keys or secrets | ||
| - Validate all user inputs | ||
| - Use parameterized queries for database access | ||
| ``` | ||
|
|
||
| ## Best Practices | ||
|
|
||
| - **Be specific and clear** - Use concrete rules like "limit cyclomatic complexity to < 10" instead of vague guidance like "write good code" | ||
| - **Include code examples** - Show patterns for error handling, naming conventions, or architecture decisions | ||
| - **Organize by category** - Group related guidelines under clear headers (Code Style, Architecture, Testing, Security) | ||
| - **Keep it concise** - Use bullet points and direct language; avoid long paragraphs | ||
| - **Update regularly** - Review and revise as your project's conventions evolve | ||
|
|
||
| ## How AGENTS.md Works in Kilo Code | ||
|
|
||
| ### Loading Behavior | ||
|
|
||
| When you start a task in Kilo Code: | ||
|
|
||
| 1. Kilo Code checks for `AGENTS.md` or `AGENT.md` at the project root | ||
| 2. If found, the content is loaded and included in the AI's context | ||
| 3. The AI follows these instructions throughout the conversation | ||
| 4. Changes to AGENTS.md take effect in new tasks (reload may be required) | ||
|
|
||
| ### Interaction with Other Rules | ||
|
|
||
| AGENTS.md works alongside Kilo Code's other configuration systems: | ||
|
|
||
| | Feature | Scope | Location | Purpose | Priority | | ||
| | -------------------------------------------------------------- | ------- | ------------------------- | ----------------------------------------- | ----------- | | ||
| | **[Mode-specific Custom Rules](/docs/customize/custom-rules)** | Project | `.kilocode/rules-{mode}/` | Mode-specific rules and constraints | 1 (Highest) | | ||
| | **[Custom Rules](/docs/customize/custom-rules)** | Project | `.kilocode/rules/` | Kilo Code-specific rules and constraints | 2 | | ||
| | **[AGENTS.md](/docs/customize/agents-md)** | Project | `AGENTS.md` | Universal standard for any AI coding tool | 3 | | ||
| | **[Global Custom Rules](/docs/customize/custom-rules)** | Global | `~/.kilocode/rules/` | Global Kilo Code rules | 4 | | ||
| | **[Custom Instructions](/docs/customize/custom-instructions)** | Global | IDE settings | Personal preferences across all projects | 5 (Lowest) | | ||
|
|
||
| ### Enabling/Disabling AGENTS.md | ||
|
|
||
| AGENTS.md support is **enabled by default** in Kilo Code. To disable it, edit `settings.json`: | ||
|
|
||
| ```json | ||
| { | ||
| "kilocode.useAgentRules": false | ||
| } | ||
| ``` | ||
|
|
||
| ## Related Features | ||
|
|
||
| - **[Custom Rules](/docs/customize/custom-rules)** - Kilo Code-specific rules with more control | ||
| - **[Custom Modes](/docs/customize/custom-modes)** - Specialized workflows with specific permissions | ||
| - **[Custom Instructions](/docs/customize/custom-instructions)** - Personal preferences across all projects | ||
| - **[Migrating from Cursor or Windsurf](/docs/getting-started/migrating)** - Migration guide for other tools | ||
|
|
||
| ## External Resources | ||
|
|
||
| - [AGENTS.md Specification](https://agents.md) - Official standard documentation | ||
| - [dotagent](https://github.com/johnlindquist/dotagent) - Universal converter tool for agent configuration files | ||
| - [awesome-cursorrules](https://github.com/PatrickJS/awesome-cursorrules) - 700+ example rules you can adapt |
There was a problem hiding this comment.
This change deletes the entire content of the agents-md.md documentation file, which contradicts the pull request's goal of adding a single sentence for clarification. This appears to be a mistake and will result in a broken documentation page and broken links from other parts of the documentation. Please restore the file's content and apply the intended clarification.
|
@coderabbitai review |
|
/gemini review |
✅ Actions performedReview triggered.
|
There was a problem hiding this comment.
Code Review
This pull request is intended to add a clarifying sentence to the agents-md.md documentation regarding memory bank status indicators. However, the current changes completely remove the agents-md.md file instead. This action contradicts the pull request's description and will result in the loss of important documentation and broken navigation links. It appears the wrong changes have been committed and this should be rectified.
|
|
||
| # agents.md | ||
|
|
||
| AGENTS.md files provide a standardized way to configure AI agent behavior across different AI coding tools. They allow you to define project-specific instructions, coding standards, and guidelines that AI agents should follow when working with your codebase. | ||
|
|
||
| {% callout type="note" title="Memory Bank Deprecation" %} | ||
| The Kilo Code **memory bank** feature has been deprecated in favor of AGENTS.md. | ||
|
|
||
| **Existing memory bank rules will continue to work.** | ||
|
|
||
| If you'd like to migrate your memory bank content to AGENTS.md: | ||
|
|
||
| 1. Examine the contents in `.kilocode/rules/memory-bank/` | ||
| 2. Move that content into your project's `AGENTS.md` file (or ask Kilo to do it for you) | ||
| {% /callout %} | ||
|
|
||
| ## What is AGENTS.md? | ||
|
|
||
| AGENTS.md is an open standard for configuring AI agent behavior in software projects. It's a simple Markdown file placed at the root of your project that contains instructions for AI coding assistants. The standard is supported by multiple AI coding tools, including Kilo Code, Cursor, and Windsurf. | ||
|
|
||
| Think of AGENTS.md as a "README for AI agents" - it tells the AI how to work with your specific project, what conventions to follow, and what constraints to respect. | ||
|
|
||
| ## Why Use AGENTS.md? | ||
|
|
||
| - **Portability**: Works across multiple AI coding tools without modification | ||
| - **Version Control**: Lives in your repository alongside your code | ||
| - **Team Consistency**: Ensures all team members' AI assistants follow the same guidelines | ||
| - **Project-Specific**: Tailored to your project's unique requirements and conventions | ||
| - **Simple Format**: Plain Markdown - no special syntax or configuration required | ||
|
|
||
| ## File Location and Naming | ||
|
|
||
| ### Project-Level AGENTS.md | ||
|
|
||
| Place your AGENTS.md file at the **root of your project**: | ||
|
|
||
| ``` | ||
| my-project/ | ||
| ├── AGENTS.md # Primary filename (recommended) | ||
| ├── src/ | ||
| ├── package.json | ||
| └── README.md | ||
| ``` | ||
|
|
||
| **Supported filenames** (in order of precedence): | ||
|
|
||
| 1. `AGENTS.md` (uppercase, plural - recommended) | ||
| 2. `AGENT.md` (uppercase, singular - fallback) | ||
|
|
||
| {% callout type="warning" title="Case Sensitivity" %} | ||
| The filename must be uppercase (`AGENTS.md`), not lowercase (`agents.md`). This ensures consistency across different operating systems and tools. | ||
| {% /callout %} | ||
|
|
||
| ### Subdirectory AGENTS.md Files | ||
|
|
||
| You can also place AGENTS.md files in subdirectories to provide context-specific instructions: | ||
|
|
||
| ``` | ||
| my-project/ | ||
| ├── AGENTS.md # Root-level instructions | ||
| ├── src/ | ||
| │ └── backend/ | ||
| │ └── AGENTS.md # Backend-specific instructions | ||
| └── docs/ | ||
| └── AGENTS.md # Documentation-specific instructions | ||
| ``` | ||
|
|
||
| When working in a subdirectory, Kilo Code will load both the root AGENTS.md and any subdirectory AGENTS.md files, with subdirectory files taking precedence for conflicting instructions. | ||
|
|
||
| ## File Protection | ||
|
|
||
| Both `AGENTS.md` and `AGENT.md` are **write-protected files** in Kilo Code. This means: | ||
|
|
||
| - The AI agent cannot modify these files without explicit user approval | ||
| - You'll be prompted to confirm any changes to these files | ||
| - This prevents accidental modifications to your project's AI configuration | ||
|
|
||
| ## Basic Syntax and Structure | ||
|
|
||
| AGENTS.md files use standard Markdown syntax. There's no required structure, but organizing your content with headers and lists makes it easier for AI models to parse and understand. | ||
|
|
||
| ### Recommended Structure | ||
|
|
||
| ```markdown | ||
| # Project Name | ||
|
|
||
| Brief description of the project and its purpose. | ||
|
|
||
| ## Code Style | ||
|
|
||
| - Use TypeScript for all new files | ||
| - Follow ESLint configuration | ||
| - Use 2 spaces for indentation | ||
|
|
||
| ## Architecture | ||
|
|
||
| - Follow MVC pattern | ||
| - Keep components under 200 lines | ||
| - Use dependency injection | ||
|
|
||
| ## Testing | ||
|
|
||
| - Write unit tests for all business logic | ||
| - Maintain >80% code coverage | ||
| - Use Jest for testing | ||
|
|
||
| ## Security | ||
|
|
||
| - Never commit API keys or secrets | ||
| - Validate all user inputs | ||
| - Use parameterized queries for database access | ||
| ``` | ||
|
|
||
| ## Best Practices | ||
|
|
||
| - **Be specific and clear** - Use concrete rules like "limit cyclomatic complexity to < 10" instead of vague guidance like "write good code" | ||
| - **Include code examples** - Show patterns for error handling, naming conventions, or architecture decisions | ||
| - **Organize by category** - Group related guidelines under clear headers (Code Style, Architecture, Testing, Security) | ||
| - **Keep it concise** - Use bullet points and direct language; avoid long paragraphs | ||
| - **Update regularly** - Review and revise as your project's conventions evolve | ||
|
|
||
| ## How AGENTS.md Works in Kilo Code | ||
|
|
||
| ### Loading Behavior | ||
|
|
||
| When you start a task in Kilo Code: | ||
|
|
||
| 1. Kilo Code checks for `AGENTS.md` or `AGENT.md` at the project root | ||
| 2. If found, the content is loaded and included in the AI's context | ||
| 3. The AI follows these instructions throughout the conversation | ||
| 4. Changes to AGENTS.md take effect in new tasks (reload may be required) | ||
|
|
||
| ### Interaction with Other Rules | ||
|
|
||
| AGENTS.md works alongside Kilo Code's other configuration systems: | ||
|
|
||
| | Feature | Scope | Location | Purpose | Priority | | ||
| | -------------------------------------------------------------- | ------- | ------------------------- | ----------------------------------------- | ----------- | | ||
| | **[Mode-specific Custom Rules](/docs/customize/custom-rules)** | Project | `.kilocode/rules-{mode}/` | Mode-specific rules and constraints | 1 (Highest) | | ||
| | **[Custom Rules](/docs/customize/custom-rules)** | Project | `.kilocode/rules/` | Kilo Code-specific rules and constraints | 2 | | ||
| | **[AGENTS.md](/docs/customize/agents-md)** | Project | `AGENTS.md` | Universal standard for any AI coding tool | 3 | | ||
| | **[Global Custom Rules](/docs/customize/custom-rules)** | Global | `~/.kilocode/rules/` | Global Kilo Code rules | 4 | | ||
| | **[Custom Instructions](/docs/customize/custom-instructions)** | Global | IDE settings | Personal preferences across all projects | 5 (Lowest) | | ||
|
|
||
| ### Enabling/Disabling AGENTS.md | ||
|
|
||
| AGENTS.md support is **enabled by default** in Kilo Code. To disable it, edit `settings.json`: | ||
|
|
||
| ```json | ||
| { | ||
| "kilocode.useAgentRules": false | ||
| } | ||
| ``` | ||
|
|
||
| ## Related Features | ||
|
|
||
| - **[Custom Rules](/docs/customize/custom-rules)** - Kilo Code-specific rules with more control | ||
| - **[Custom Modes](/docs/customize/custom-modes)** - Specialized workflows with specific permissions | ||
| - **[Custom Instructions](/docs/customize/custom-instructions)** - Personal preferences across all projects | ||
| - **[Migrating from Cursor or Windsurf](/docs/getting-started/migrating)** - Migration guide for other tools | ||
|
|
||
| ## External Resources | ||
|
|
||
| - [AGENTS.md Specification](https://agents.md) - Official standard documentation | ||
| - [dotagent](https://github.com/johnlindquist/dotagent) - Universal converter tool for agent configuration files | ||
| - [awesome-cursorrules](https://github.com/PatrickJS/awesome-cursorrules) - 700+ example rules you can adapt |
There was a problem hiding this comment.
The pull request's description states that a single sentence should be added to this file for clarification. However, the entire file is being deleted. This appears to be an error, as it removes crucial documentation for the AGENTS.md feature and will lead to broken links on the documentation site. Please revert this deletion and apply the intended change as described in the pull request.
|
Closing: diff artifact from API commit. Recreating with proper cherry-pick. |
Reviews #1-22 covering PRs across tiers 1-3. Includes review.md (machine-parseable), journal.md (human narrative), and status.json for each PR. Combined integration test: PRs Kilo-Org#5370 + Kilo-Org#5660 + Kilo-Org#5704 merged and tested together — 7,932 tests passed, 4 pre-existing failures (mistral-fim mocks). Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Context
Clarify that Memory Bank status indicators may not appear in all clients. Softens guarantees to align with observed behavior.
Mirrors Kilo-Org/kilocode#5667 for multi-AI review testing.
Implementation
Adds one sentence to the deprecation callout in agents-md.md explaining that legacy indicators can still appear but aren't guaranteed across all clients or modes.
How to Test
Closes Kilo-Org#3837
Summary by CodeRabbit