ElasticAGENTS.mdeui
elastic/eui/AGENTS.md
This is a Yarn v4 monorepo; packages live in packages/. All contributor knowledge lives in the wiki: If the wiki disagrees with this file, the wiki wins — open a…
AGENTS.md examples from real projects
How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
Most stars first · from page 42Worked for most · soon
ElasticAGENTS.md
MicrosoftAGENTS.mdagent-governance-toolkit / agent-governance-claude-code
microsoft/agent-governance-toolkit/agent-governance-claude-code/AGENTS.md
The agent-governance-claude-code/ directory contains the first-party Claude Code plugin package for Agent Governance Toolkit. It wires AGT policy evaluation into Claude-native hooks, markdown commands, and a bundled MCP server.
MicrosoftAGENTS.mdagent-governance-toolkit / agent-governance-dotnet
microsoft/agent-governance-toolkit/agent-governance-dotnet/AGENTS.md
agent-governance-dotnet/ contains the .NET SDK for Agent Governance Toolkit: policy enforcement, execution rings, trust, SRE controls, MCP security, lifecycle management, and auditability for .NET applications.
MicrosoftAGENTS.mdagent-governance-toolkit / agent-governance-opencode
microsoft/agent-governance-toolkit/agent-governance-opencode/AGENTS.md
Scope: this folder publishes @microsoft/agent-governance-opencode, the AGT governance plugin for OpenCode. OpenCode loads plugins in-process as async JS/TS functions. The plugin entry point is src/index.mjs, which: - caches a single loadPolicy() state per OpenCode process - maps AGT decisions (allow / review / deny) onto OpenCode's contract: - deny → throw new Error(...) from the hook - review → annotate output.args._agtreviewreason - allow → return undefined - exposes agtpolicystatus and agtpolicychecktext as both in-process custom tools and stdio MCP server…
MicrosoftAGENTS.mdagent-governance-toolkit / agent-compliance
microsoft/agent-governance-toolkit/agent-governance-python/agent-compliance/AGENTS.md
Agent Compliance (agent-governance-toolkit) provides runtime policy enforcement and security scanning for AI agent systems. This package ensures agents operate within organizational compliance boundaries and security policies. Core Capabilities: Security exemptions use .security-exemptions.json: Security scanner integrates with: - detect-secrets: Secret detection - pip-audit: Python CVE scanning - npm audit: Node.js CVE scanning - bandit: Python SAST All tool integ
MicrosoftAGENTS.mdagent-governance-toolkit / agent-mesh
microsoft/agent-governance-toolkit/agent-governance-python/agent-mesh/AGENTS.md
AgentMesh is a trust-first communication layer for AI agents — providing cryptographic identity, multi-dimensional trust scoring, scope chains, and governance enforcement for multi-agent systems. Architecture: 4-layer trust stack - All data models use Pydantic BaseModel - Identity: AgentIdentity with .sign(data: bytes) -> str (base64 Ed25519 signatures) - Trust scores: 5 dimensions — competence, integrity, availability, predictability, transparency - DID format: did:mesh:{hex} — see the proof-of-possession note under Boundaries: registry/app.py derives DIDs from the public key, while AgentDID.generate mints a random…
MicrosoftAGENTS.mdagent-governance-toolkit / sdks
microsoft/agent-governance-toolkit/agent-governance-python/agent-mesh/sdks/AGENTS.md
This directory contains cross-language AgentMesh SDKs: These SDKs should stay conceptually aligned with the trust, identity, governance, and MCP security surfaces provided elsewhere in the repo. This directory reflects the repo layout at this point in time. Some language implementations may eventually move into standalone top-level directories such as agent-governance-golang/, agent-governance-rust/, or agent-governance-python/. If that happens, treat the standalone top-level directory as the primary home for new work. This directory should then be treated as legacy/shared-layout guidance for the code…
MicrosoftAGENTS.mdagent-governance-toolkit / agent-os
microsoft/agent-governance-toolkit/agent-governance-python/agent-os/AGENTS.md
Agent-OS is a governance-first kernel for AI agents — a Python framework providing policy enforcement, semantic intent classification, identity management, and execution control for autonomous AI agents. Architecture: 4-layer modular kernel Framework adapters route intervention points through HostSession and receive PolicyEvaluation. Raise the canonical PolicyViolationError.fromevaluationresult(result) for denied or escalated results. Hosts should surface str(error) and use error.evaluationresult.reasoncode for structured handling. Use conventional commits: feat:, fix:, docs:, test:, refactor:, chore:
MicrosoftAGENTS.mdagent-governance-toolkit / agent-governance-python
microsoft/agent-governance-toolkit/agent-governance-python/AGENTS.md
agent-governance-python/ is the top-level home for first-party published Python packages in Agent Governance Toolkit. Use this directory for reusable SDK/package surfaces that are meant to be consumed directly by external Python users. Applications, dashboards, demos, and larger runtime/product assemblies should stay in the repo root, examples/, or other existing homes unless maintainers explicitly decide to promote them into this package workspace. - Prefer this directory for first-party Python packages that are published independently. - Keep package names, import paths, and…
MicrosoftAGENTS.mdagent-governance-toolkit / agent-sre
microsoft/agent-governance-toolkit/agent-governance-python/agent-sre/AGENTS.md
Agent-SRE is an SRE toolkit for AI agent reliability — providing SLO management, error budgets, chaos engineering, progressive delivery, cost guardrails, incident management, and observability for autonomous AI agents. Key engines: Use conventional commits: feat:, fix:, docs:, test:, refactor:, chore:
MicrosoftAGENTS.mdagent-governance-toolkit / agent-governance-rust
microsoft/agent-governance-toolkit/agent-governance-rust/AGENTS.md
agent-governance-rust/ contains the Rust SDK workspace for Agent Governance Toolkit: policy enforcement, trust, audit, identity, lifecycle, execution rings, and MCP security surfaces for Rust applications.
MicrosoftAGENTS.mdagent-governance-toolkit
microsoft/agent-governance-toolkit/AGENTS.md
Agent Governance Toolkit is a multi-package OSS monorepo for runtime governance of AI agents: policy enforcement, zero-trust identity, execution sandboxing, SRE, compliance, examples, docs, demos, SDKs, and publishing pipelines. Use this file for repository-wide routing. When you enter a subdirectory that has its own AGENTS.md, that narrower file takes precedence. This routing reflects the repo as it exists today while reserving room for approved language SDK migrations. Language SDKs may live in standalone top-level directories at the repository root. For…
MicrosoftAGENTS.mdagent-governance-toolkit
microsoft/agent-governance-toolkit/docs/AGENTS.md
The docs/ tree powers the published documentation site for Agent Governance Toolkit: reference material, tutorials, architecture docs, threat modeling, compliance content, package pages, and integration guides. - Be precise and honest; do not claim a feature is shipped unless the repo actually contains it. - Prefer updating an existing page over creating a near-duplicate page. - Use repo-relative links that work from the current document location. - Match existing tone: technical, direct, and evidence-based. - Keep package names, CLI commands,…
MicrosoftAGENTS.mdagent-governance-toolkit / examples
microsoft/agent-governance-toolkit/examples/AGENTS.md
The examples/ directory is the preferred place for runnable, self-contained integrations and worked examples. For OSS contributors, examples are often the best starting point for proposing support for a new framework or ecosystem tool. Use examples/ when you want to: Prefer an example over a core package change when the external project is new, niche, or still proving community demand.
MicrosoftAGENTS.mdagent-governance-toolkit / demos
microsoft/agent-governance-toolkit/examples/demos/AGENTS.md
The demo/ directory contains live demonstrations of AGT capabilities, including real-service walkthroughs and visual dashboards. Demos should help users see the system working end-to-end without changing the core product contract.
MicrosoftAGENTS.mdagent-governance-toolkit / pipelines
microsoft/agent-governance-toolkit/.github/pipelines/AGENTS.md
The pipelines/ directory contains Azure DevOps release automation, especially ESRP-backed publishing flows for Python, npm, NuGet, Rust, and Go artifacts. - Treat every pipeline edit as security-sensitive. - Keep secrets, client IDs, key vault names, and certificate identifiers in pipeline secrets or variables, not inline in YAML. - Pin package-install commands to explicit versions where applicable. - Preserve least privilege and existing release gates. - Prefer comments that explain non-obvious ESRP or platform constraints.
MicrosoftAGENTS.mdagent-governance-toolkit / policy-engine
microsoft/agent-governance-toolkit/policy-engine/AGENTS.md
The policy decision runtime now ships from the registry as agent-control-spec, rebased on the agent-hooks control contract. This tree is what AGT layers on top of it. core/ is a deprecation shim that keeps the historical agentcontrolspecification_core symbols importable for one release cycle, and sdk/rust/ is AGT's host SDK. Read docs/acs-retarget.md before changing anything here. Use ACS terms when writing issues, docs, tests, and code comments. Do not introduce predecessor project concepts that ACS removed, and do not reintroduce the…
MicrosoftAGENTS.mdaspire
microsoft/aspire/AGENTS.md
Instructions for GitHub Copilot and other AI coding agents working with the Aspire repository. Aspire provides tools, templates, and packages for building observable, production-ready distributed applications. At its core is an app model that defines services, resources, and connections in a code-first approach. When reviewing a pull request, check whether eng/github-ci/test-trigger-map.yml needs to change if the diff: * Adds, removes, or renames a test project. * Adds or changes a CI job, reusable workflow, or run_* selection gate. * Adds…
MicrosoftAGENTS.mdVFSForGit
microsoft/VFSForGit/AGENTS.md
This file is for AI coding assistants (GitHub Copilot, Claude Code, Cursor, OpenAI Codex, Gemini CLI, Aider, etc.). It captures project-specific knowledge that isn't obvious from a fresh git clone and which routinely trips up agents. See CONTRIBUTING.md for coding standards (StyleCop rules, error handling, exception logging) — do not duplicate those here. The build scripts (scripts\Build.bat and friends) put build outputs one level up from the git working tree. The Readme documents the recommended clone-into-src\ convention, which matches the…
ElasticAGENTS.mdgo-elasticsearch
elastic/go-elasticsearch/AGENTS.md
CLAUDE.md is a symlink to this file — they are the same file, do not update both. Official Elasticsearch Go client. Module: github.com/elastic/go-elasticsearch/v9. This is a public library with external consumers. Maintain backwards compatibility: PRs are squash-merged into a single commit when landing on main or a version branch. Because of this, each PR should represent one distinct, self-contained change — a single feature, bug fix, or refactor. Mixing unrelated changes in one PR means they become inseparable in history,…
About AGENTS.md
What is AGENTS.md?
An open format for instructions to coding agents, read by Codex, Cursor and others. Think of it as a README written for agents.
Where does it go?
At the repository root, with more specific files in subdirectories. Agents read the one closest to the file they're editing.
What should it contain?
Setup and test commands, code style, and the rules a new contributor would need to know.
Does Claude Code read it?
Claude Code reads CLAUDE.md. A one-line CLAUDE.md that points at AGENTS.md covers both.