How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
AWSAGENTS.mdaws/amazon-chime-sdk-ios/AmazonChimeSDK/AmazonChimeSDKTests/AGENTS.md
Tests use handwritten spies and the verification helpers in common/CommonTestCase.swift. Do not add Cuckoo, generated mocks, or method-specific verifier proxies without explicit approval. Avoid reintroducing equivalent boilerplate: Run the affected test class first, then run the complete suite before submitting broad test refactors:
AWSAGENTS.mdaws/aws-cdk-cli/AGENTS.md
Contributor-focused guide for AI agents working on the AWS CDK CLI monorepo. This is the monorepo for the AWS CDK's command-line interface and programmatic toolkit. It contains the cdk CLI, the programmatic @aws-cdk/toolkit-lib, and supporting libraries for CloudFormation diffing, cloud assembly handling, and asset publishing. The repo is TypeScript-only, managed by Projen, built with NX for caching and task orchestration, and uses Yarn workspaces. This is not the construct library repo (aws/aws-cdk). This repo focuses exclusively on the CLI toolchain…
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.
AWSAGENTS.mdaws/aws-durable-execution-sdk-js/AGENTS.md
Build resilient, long-running AWS Lambda functions with automatic state persistence, retry logic, and workflow orchestration. AWS Lambda durable functions extend Lambda's programming model to build multi-step applications and AI workflows with automatic state persistence. Applications can run for days or months, survive failures, and only incur charges for actual compute time. Core Primitives: Durable functions use a "replay" execution model. On replay (after wait/failure/resume), code runs from the beginning. Steps that already completed return their checkpointed results WITHOUT re-executing. Code…
AWSAGENTS.mdaws/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…
AWSAGENTS.mdaws/aws-durable-execution-sdk-java/AGENTS.md
AI coding agent instructions for the AWS Lambda Durable Execution Java SDK. 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 SDK. Related SDKs exist for JavaScript/TypeScript and Python. Cloud example tests are disabled by default. Enable them only when the required Lambda functions and AWS credentials…
AWSAGENTS.mdaws/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, collectionio.c, collectionuserfuncs.c, collectionsubs.c, collectionparse.c,…
AWSAGENTS.mdaws/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…
AWSAGENTS.mdaws/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…
An open format for instructions to coding agents, read by Codex, Cursor and others. Think of it as a README written for agents.
At the repository root, with more specific files in subdirectories. Agents read the one closest to the file they're editing.
Setup and test commands, code style, and the rules a new contributor would need to know.
Claude Code reads CLAUDE.md. A one-line CLAUDE.md that points at AGENTS.md covers both.
