agents-md-guide
Guide for using and supporting the AGENTS.md standard in VS Code. Use this when asked about AGENTS.md, custom instructions, or repo-level AI agent configuration.
Best use case
agents-md-guide is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Guide for using and supporting the AGENTS.md standard in VS Code. Use this when asked about AGENTS.md, custom instructions, or repo-level AI agent configuration.
Teams using agents-md-guide should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/agents-md-guide/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How agents-md-guide Compares
| Feature / Agent | agents-md-guide | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Guide for using and supporting the AGENTS.md standard in VS Code. Use this when asked about AGENTS.md, custom instructions, or repo-level AI agent configuration.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# AGENTS.md Guide for VS Code
This skill provides guidance on implementing and using the `AGENTS.md` standard to provide custom instructions for AI coding agents in VS Code.
## Why AGENTS.md?
- **Standardization**: Reduces fragmentation from proprietary files like `.cursorrules`.
- **Interoperability**: Works across different AI tools (GitHub Copilot, Cursor, etc.).
- **Efficiency**: Saves time by providing structured context (build steps, coding conventions).
- **Consistency**: Ensures AI agents follow project-specific protocols.
- **Open Standard**: Governed by the Agentic AI Foundation (Linux Foundation).
## Mental Model
`AGENTS.md` acts as a centralized **instruction manual** for AI coding agents at the repo root.
- **Flow**: Repo clone → agent scans for `AGENTS.md` → parses sections → applies rules during tasks → outputs aligned code.
## VS Code Configuration
To enable `AGENTS.md` support in VS Code:
1. **Enable Setting**: Set `chat.useAgentsMdFile` to `true`.
2. **Nested Files (Experimental)**: Set `chat.useNestedAgentsMdFiles` to `true` for subfolder instructions.
## How to Implement AGENTS.md
1. **Location**: Place `AGENTS.md` at the root of your repository.
2. **Structure**: Use clear sections:
- `## Environment`: Setup and build instructions.
- `## Coding Style`: Linting, formatting, and architectural rules.
- `## Testing`: How to run and write tests.
3. **Keep it Concise**: Avoid overly verbose rules.
## Real-World Scenarios
- **Open-source Maintenance**: AI agents auto-generate PRs following style guides.
- **Enterprise Code Reviews**: Teams use repo-level rules during Copilot-assisted edits.
- **Indie Dev Prototyping**: Automate build and test cycles with tools like Cursor or Codex.
## Survival Kit
- **Day 0**: Clone a repo with `AGENTS.md`; ensure `chat.useAgentsMdFile` is enabled in VS Code.
- **Week 1**: Create a basic `AGENTS.md` in a test repo and iterate on sections.
- **Week 2**: Add nested files if needed using experimental settings.
## Security & Risks
- **No Secrets**: Never include API keys or credentials.
- **Goal Hijacking**: Be aware that instruction files can steer agent behavior. Review instructions before running autonomous tasks in untrusted repos.
## References
- [AGENTS.md Homepage](https://agents.md/)
- [VS Code Custom Instructions Docs](https://code.visualstudio.com/docs/copilot/customization/custom-instructions)
- [GitHub Copilot AGENTS.md Support](https://github.blog/changelog/2025-08-28-copilot-coding-agent-now-supports-agents-md-custom-instructions/)
- [Prompt Security: Risks of AGENTS.md](https://prompt.security/blog/when-your-repo-starts-talking-agents-md-and-agent-goal-hijack-in-vs-code-chat)Related Skills
manage-agents
Create, modify, and manage Claude Code subagents with specialized expertise. Use when you need to "work with agents", "create an agent", "modify an agent", "set up a specialist", "I need an agent for [task]", or "agent to handle [domain]". Covers agent file format, YAML frontmatter, system prompts, tool restrictions, MCP integration, model selection, and testing.
langchain-agents
Expert guidance for building LangChain agents with proper tool binding, memory, and configuration. Use when creating agents, configuring models, or setting up tool integrations in LangConfig.
kramme:agents-md
This skill should be used when the user asks to "update AGENTS.md", "add to AGENTS.md", "maintain agent docs", or needs to add guidelines to agent instructions. Guides discovery of local skills and enforces structured, keyword-based documentation style.
git-commit-for-ai-agents
Commit changes to a git repository. Use whenever a git commit is to be executed.
dispatching-parallel-agents
Use when facing 3+ independent failures that can be investigated without shared state or dependencies. Dispatches multiple Claude agents to investigate and fix independent problems concurrently.
custom-sub-agents
Guidance for creating and organizing custom sub-agents in local repos, including folder conventions, per-agent structure, and AGENTS.md indexing. Use when asked where to store sub-agents or how to document them.
custom-agents
GitHub Custom Agent File Format
creating-agents
Create and review agent definition files (agents.md) that give AI coding agents a clear persona, project knowledge, executable commands, code style examples, and explicit boundaries. Use when a user asks to create an agent, define an agent persona, write an agents.md file, set up a custom Copilot agent, review an existing agent definition, or improve agent quality. Covers the six core areas: commands, testing, project structure, code style, git workflow, and boundaries.
create-agents-md
Create or rewrite AGENTS.md files for Open Mercato packages and modules. Use this skill when adding a new package, creating a new module, or when an existing AGENTS.md needs to be created or refactored. Ensures prescriptive tone, MUST rules, checklists, and consistent structure across all agent guidelines.
building-agents
Expert at creating and modifying Claude Code agents (subagents). Auto-invokes when the user wants to create, update, modify, enhance, validate, or standardize agents, or when modifying agent YAML frontmatter fields (especially 'model', 'tools', 'description'), needs help designing agent architecture, or wants to understand agent capabilities. Also auto-invokes proactively when Claude is about to write agent files (*/agents/*.md), create modular agent architectures, or implement tasks that involve creating agent components.
audit-agents-md
Audit AGENTS.md files for token efficiency, completeness, scope hygiene, and actionability. Also considers skills and Cursor rules for redundancy. Use when the user wants to review, optimize, or restructure project agent instructions.
ai-coding-agents
Comprehensive guide for using Codex CLI (OpenAI) and Claude Code CLI (Anthropic) - AI-powered coding agents. Use when orchestrating CLI commands, automating tasks, configuring agents, or troubleshooting issues.