modern-data-architecture-accelerator / rules
aws/modern-data-architecture-accelerator/.cursor/rules/review-module-quality.mdc
See @agent_rules/review-module-quality.md
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.
aws/modern-data-architecture-accelerator/.cursor/rules/review-module-quality.mdc
See @agent_rules/review-module-quality.md
aws/modern-data-architecture-accelerator/.cursor/rules/review-mr-summary.mdc
See @agent_rules/review-mr-summary.md
aws/modern-data-architecture-accelerator/.cursor/rules/review-starter-kit-standards.mdc
See @agent_rules/review-starter-kit-standards.md
aws/modern-data-architecture-accelerator/.cursor/rules/review-testing-standards.mdc
See @agent_rules/review-testing-standards.md
aws/modern-data-architecture-accelerator/.cursor/rules/user-config-authoring.mdc
See @agent_rules/user-config-authoring.md
aws/modern-data-architecture-accelerator/.github/copilot-instructions.md
See developer-code-review See developer-operational-guidance See developer-working-requirements
aws/aws-durable-execution-sdk-js/AGENTS.md
Rules for coding agents that change this repository. People follow them too. 1. Read the rules for every change. Reviewers, people and agents, enforce them. 2. Before you change the SDK package, read packages/aws-durable-execution-sdk-js/AGENTS.md. It lists the SDK invariants and the contract tests that guard them. 3. A new feature, a new option or a public API change starts with a design note. A maintainer agrees to it before you write code. 1. Keep the change as small as the…
aws/aws-durable-execution-sdk-js/packages/aws-durable-execution-sdk-js/AGENTS.md
This file is for people and coding agents who change the SDK itself. The root AGENTS.md covers the whole repository. The rules for every change in CONTRIBUTING.md apply too. The checkpoint manager suspends the invocation when no operation is EXECUTING and another operation is waiting. It sees only lifecycle states. So SDK work that runs while no operation is EXECUTING can be cut off, and the code after it then runs in no recorded invocation. The rules below prevent that.…
aws/aws-durable-execution-sdk-js/packages/aws-durable-execution-sdk-js-telemetry-mcp/src/skill/SKILL.md
Query AWS Lambda durable function execution history through the durable-telemetry MCP server — use when investigating workflow failures, execution timing, or step-level errors across DynamoDB, Athena/S3, Aurora, Redshift, OpenSearch, or CloudWatch Logs destinations.
aws/aws-durable-execution-sdk-python/AGENTS.md
This repository contains the AWS Durable Execution SDK for Python and its companion packages, used to author AWS Lambda durable functions. Do not rely on this file for method signatures, configuration objects, or code examples. The canonical reference is the AWS Durable Execution SDK Developer Guide, which is maintained alongside SDK releases and covers TypeScript, Python, and Java. Key sections: For Lambda service topics such as deployment, infrastructure as code, invocation, IAM permissions, and quotas, see the Lambda durable functions…
aws/Unified-Studio-for-Amazon-Sagemaker/migration/glue/SKILL.md
Use when migrating Glue Python jobs and connections to SageMaker Unified Studio, including manual selections, discovery results, and partially completed migrations.
aws/aws-networking-best-practices/content/llms.txt
A reference architecture for AWS networking best practices, covering enterprise network design across five pillars: Foundation, Connectivity, Application Networking, Security, and Observability. This guide provides opinionated, production-ready networking guidance for AWS environments. It assumes multi-account AWS Organizations deployments, treats IPv6 as a core element, and includes cost implications in every architectural decision. Essential building blocks that everything else depends on. How AWS resources communicate with the internet, with each other, and with networks outside AWS. Traffic distribution, service discovery, and…
aws/aws-durable-execution-sdk-java/AGENTS.md
AI coding agent instructions for the AWS Lambda Durable Execution Java SDK. Read and follow the Rules for every change and SDK invariants in CONTRIBUTING.md before implementing or reviewing a change. They apply alongside the Java-specific guidance below. AWS Lambda Durable Execution SDK for Java - enables building resilient, multi-step Lambda workflows that can run for up to one year with automatic state management, checkpoint-and-replay, and failure recovery. This repository is the Java implementation of the AWS Lambda durable execution…
aws/pgcollection/AGENTS.md
Guidance for AI agents (and new contributors) working on the pgcollection source. For what the extension does and how to use it, read README.md and doc/. This file covers how to change it safely. A PostgreSQL extension written in C (PGXS build) that provides two in-memory associative array types for PL/pgSQL: collection (text keys) and icollection (bigint keys). Requires PostgreSQL 14 or later. - src/ C implementation. Files are split by type and concern, e.g. collection.c, collection_io.c, collection_userfuncs.c, collection_subs.c, collection_parse.c,…
aws/CICD-for-SageMakerUnifiedStudio/skills/generate-bundle-manifest/SKILL.md
Generate an SMUS CI/CD deployment manifest (and orchestration workflow) to replicate a SageMaker Unified Studio project environment across stages. Use when the user asks to: generate/create/scaffold a manifest, bundle my project, replicate environment, set up CI/CD, promote to test/prod, deploy my project to prod, move my project to another environment, package my code for deployment, set up multi-account deployment, copy environment to production, or asks how to promote code across environments. Does NOT activate for: authoring standalone Airflow DAGs unrelated to deployment, querying data, exploring catalog, or managing standalone Glue jobs.
aws/n8n-nodes-agentcore/AGENTS.md
n8n community node for Amazon Bedrock AgentCore harness. Lets n8n workflow authors run config-driven AI agents on AgentCore from inside their workflows without writing infrastructure code. This file is read by AI coding agents (Claude, Cursor, GitHub Copilot Workspace, Amazon Q) and by humans onboarding to the repo. Treat it as authoritative for the conventions below. - It is an n8n community node distributed on npm as @aws/n8n-nodes-agentcore. - It targets the AgentCore harness primitive (declarative spec), not AgentCore Runtime…
aws/n8n-nodes-agentcore/CLAUDE.md
This project keeps all agent instructions in AGENTS.md. Always follow the rules in ./AGENTS.md, and when working in subdirectories, also check for a closer AGENTS.md in that directory tree.
aws/aws-durable-execution-sdk-rust/AGENTS.md
This repository contains the AWS Durable Execution SDK for Rust, the aws-durable-execution-sdk crate, used to author AWS Lambda durable functions. Do not rely on this file for method signatures, builder options, or code examples. The API reference for this SDK is the README and the rustdoc comments in src/. To read the rustdoc in a browser, run cargo doc --no-deps --all-features --open. The AWS Durable Execution SDK Developer Guide explains the concepts that all the durable execution SDKs share. Its…
aws/neptune-gremlin-client/AGENTS.md
Guidance for AI agents and developers working in this repository. Neptune Gremlin Client is a Java Gremlin client for Amazon Neptune that lets you change the endpoints used by the client while it is running. It includes an endpoint refresh agent that retrieves cluster topology details and updates the client periodically, support for custom endpoint selectors (filtering instances by tag, instance type, instance ID, Availability Zone, etc.), and support for connecting to Neptune through a proxy such as a network…
aws/aws-advanced-drivers/skills/driver-version-check/SKILL.md
Check latest GitHub release versions for AWS Advanced Driver wrappers and compare against documented versions. Use when asked to "check versions", "update versions", "are drivers up to date", or for scheduled version monitoring.
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.