One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
AWSAGENTS.mdaws/bedrock-agentcore-sdk-typescript/AGENTS.md
This document provides guidance specifically for AI agents working on the AWS Bedrock AgentCore TypeScript SDK codebase. For human contributor guidelines, see CONTRIBUTING.md. AGENTS.md contains agent-specific repository information including: For human contributors: See CONTRIBUTING.md for setup, testing, and contribution guidelines.
AWSCLAUDE.mdaws/modern-data-architecture-accelerator/CLAUDE.md
See developer-code-review Operational guidance for commits, issues, MRs, reviews, and repo workflows See developer-operational-guidance Non-optional working requirements for all tasks See developer-working-requirements
AWSCursor ruleaws/modern-data-architecture-accelerator/.cursor/rules/developer-code-documentation.mdc
Code documentation standards for all MDAA code
AWSCursor ruleaws/modern-data-architecture-accelerator/.cursor/rules/developer-code-review.mdc
See @agent_rules/developer-code-review.md
AWSCursor ruleaws/modern-data-architecture-accelerator/.cursor/rules/developer-code-review-python.mdc
See @agent_rules/developer-code-review-python.md
AWSCursor ruleaws/modern-data-architecture-accelerator/.cursor/rules/developer-code-review-typescript.mdc
See @agent_rules/developer-code-review-typescript.md
AWSCursor ruleaws/modern-data-architecture-accelerator/.cursor/rules/developer-coding-standards.mdc
See @agent_rules/developer-coding-standards.md
AWSCursor ruleaws/modern-data-architecture-accelerator/.cursor/rules/developer-iterative-development.mdc
See @agent_rules/developer-iterative-development.md
AWSCursor ruleaws/modern-data-architecture-accelerator/.cursor/rules/developer-module-creation.mdc
See @agent_rules/developer-module-creation.md
AWSCursor ruleaws/modern-data-architecture-accelerator/.cursor/rules/developer-operational-guidance.mdc
Operational guidance for commits, issues, MRs, reviews, and repo workflows
AWSCursor ruleaws/modern-data-architecture-accelerator/.cursor/rules/developer-pre-push-review.mdc
See @agent_rules/developer-pre-push-review.md
AWSCursor ruleaws/modern-data-architecture-accelerator/.cursor/rules/developer-review-agent-authoring.mdc
See @agent_rules/developer-review-agent-authoring.md
AWSCursor ruleaws/modern-data-architecture-accelerator/.cursor/rules/developer-sample-config-authoring.mdc
See @agent_rules/developer-sample-config-authoring.md
AWSCursor ruleaws/modern-data-architecture-accelerator/.cursor/rules/developer-scripts-authoring.mdc
See @agent_rules/developer-scripts-authoring.md
AWSCursor ruleaws/modern-data-architecture-accelerator/.cursor/rules/developer-working-requirements.mdc
Non-optional working requirements for all tasks
AWSCursor ruleaws/modern-data-architecture-accelerator/.cursor/rules/review-architecture.mdc
See @agent_rules/review-architecture.md
AWSCursor ruleaws/modern-data-architecture-accelerator/.cursor/rules/review-cli-architecture.mdc
CLI shell-safety invariants — parameter validation, sink quoting, and their tests
AWSCursor ruleaws/modern-data-architecture-accelerator/.cursor/rules/review-compliance.mdc
See @agent_rules/review-compliance.md
AWSCursor ruleaws/modern-data-architecture-accelerator/.cursor/rules/review-diff-risk.mdc
See @agent_rules/review-diff-risk.md
AWSCursor ruleaws/modern-data-architecture-accelerator/.cursor/rules/review-documentation.mdc
See @agent_rules/review-documentation.md
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
