How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
MicrosoftAGENTS.mdmicrosoft/agent-framework/python/packages/devui/AGENTS.md
bash # Run with auto-discovery devui ./agents # Run with specific entities devui --entities my_agent.py ``` ## Security Posture DevUI is a development-only sample app, not a production hosting surface. Authentication
AWSAGENTS.mdaws/aws-cdk/AGENTS.md
factory methods instead - No `Token` type in props - `SecretValue` type for any password/secret/token properties ## Security Rules - SHOULD prefer specific IAM actions over full-service wildcards (`s3:*`), but suffix wildcards
ElasticAGENTS.mdelastic/beats/AGENTS.md
services and endpoints, detecting uptime/downtime | | `auditbeat` | Gathers audit data from systems to track security events, user activities, and compliance requirements | | `packetbeat` | Analyzes network traffic by capturing and inspecting packets
BeehiveInnovationsAGENTS.mdBeehiveInnovations/pal-mcp-server/AGENTS.md
Install GitHub CLI: `brew install gh` (macOS) or visit https://cli.github.com for other platforms. ## Security & Configuration Tips Store API keys and provider URLs in `.env` or your MCP client config
OpenAIAGENTS.mdopenai/openai-node/AGENTS.md
checker and effective budget come from main, not the PR. Keep default CODEOWNERS. ## Security and lifecycle correctness - Never commit API keys, tokens, private keys, `.env` files, customer data, or other
Model Context ProtocolAGENTS.mdmodelcontextprotocol/inspector/AGENTS.md
release`](.claude/skills/release/SKILL.md) | Cutting a release: bump on `v2/main`, milestone merge, tag `origin/main`, publish | `/release` | | [`security-advisory`](.claude/skills/security-advisory/SKILL.md) | A privately reported vulnerability end to end: the draft card, who owns
OpenAIAGENTS.mdopenai/codex-security/AGENTS.md
Keep it simple Codex Security is a thin wrapper around Codex and its security plugin. - Trust local tools and processes running as the current user. - Treat repository contents, model output
OpenAIAGENTS.mdopenai/codex-security/sdk/typescript/AGENTS.md
Codex Security CLI Codex Security is a thin CLI and SDK wrapper around Codex and its security plugin. Use their existing behavior instead of building another runtime. ## Threat model
LangChainAGENTS.mdlangchain-ai/open-swe/AGENTS.md
controls may ship without a corresponding tool, especially for secret input until a secure tool-driven input flow exists. Do not add a tool when the agent can already
GoogleAGENTS.mdgoogle/adk-recipes/core/python/long-horizon-harness/AGENTS.md
prefix, prefix cache, the four bounds on context growth), and [`docs/security-model.md`](docs/security-model.md) (per-layer security). Don't duplicate those here — link to them. ## What this recipe teaches Horizon leans
KuberwastakenAGENTS.mdKuberwastaken/claurst/docs/agents.md
same name. ```json { "agents": { "review": { "description": "Senior code reviewer focused on correctness and security", "model": "anthropic/claude-opus-4-6", "temperature": 0.3, "prompt": "You are a senior software engineer performing code review. Focus
CloudflareAGENTS.mdcloudflare/cloudflare-os/AGENTS.md
rethink the design); and prefer reusing existing mechanisms over adding parallel ones. Capability-based security note: a resource becomes "ambient" (auto-injected) only by user/admin configuration — a gatekeeper must never
CloudflareAGENTS.mdcloudflare/cloudflare-os/packages/workshop-frontend/AGENTS.md
block already says. Comments are appropriate for gotchas, non-obvious invariants, external constraints, security or performance reasoning, and deliberate departures from a convention. Explain why the surprising choice is necessary
open-gsdAGENTS.mdopen-gsd/gsd-core/docs/AGENTS.md
checker, ui-checker | | Verifiers | 2 | verifier, dom-verifier | | Auditors | 3 | nyquist-auditor, ui-auditor, security-auditor | | Mappers | 1 | codebase-mapper | | Debuggers | 1 | debugger | | Doc Writers | 2 | doc-writer, doc-verifier
AWSAGENTS.mdawslabs/mcp/src/dynamodb-mcp-server/AGENTS.md
variable #### MySQL Analyzer - **Issue**: Connection timeout or permission denied - **Solution**: Verify AWS credentials, check Security Group rules, ensure RDS Data API is enabled - **Debug**: Set `FASTMCP_LOG_LEVEL=DEBUG
backnotpropAGENTS.mdbacknotprop/plannotator/AGENTS.md
# Plannotator A plan review UI for Claude Code that intercepts `ExitPlanMode` via hooks, letting
CloudflareAGENTS.mdcloudflare/vinext/AGENTS.md
Before writing a fix, confirm how Next.js handles the same scenario. This applies to security fixes, bug reports, and behavioral changes. We have repeatedly shipped fixes that diverged from Next.js
GoogleAGENTS.mdgoogle/adk-go/AGENTS.md
request and response bodies, headers, credentials, tokens and API keys are customer content or security material, at every level including debug. Log the shape instead — a type, a count
NVIDIAAGENTS.mdNVIDIA/OpenShell/AGENTS.md
direct request proceeds after warning about missing or incomplete expected labels. - **Security:** `review-security-issue` → `fix-security-issue` - General build agents must not process `topic:security` issues. For unattended processing
CloudflareAGENTS.mdcloudflare/workerd/AGENTS.md
capnp` format) - Main schema: `src/workerd/server/workerd.capnp` - Sample configurations in `samples/` directory - Configuration uses capability-based security model ### Where to Look | Task | Location | Notes | | ---------------------- | ------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------ | | Add/modify JS API | `src/workerd/api/` | C++ with JSG macros
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.
