How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
xyTomAGENTS.mdxyTom/coding-tools-mcp/AGENTS.md
unless the feature requires it. ## Repository map - `coding_tools_mcp/`: core Python MCP runtime and public server behavior. - `apps/desktop-client/`: desktop client UI and desktop runtime integration. - `integrations/tunnels/`: user-facing tunnel
MicrosoftAGENTS.mdmicrosoft/testfx/AGENTS.md
diagnoses MSBuild build failures from a `.binlog` file. The preferred path uses the **binlog MCP server** (`Microsoft.AITools.BinlogMcp`, exposed under the `binlog` MCP namespace) which is bundled with this plugin
stackqlAGENTS.mdstackql/stackql/AGENTS.md
popular idioms: - App internals in [`internal`](/internal). - Re-usable modules in [`pkg`](/pkg). - The MCP server function is built upon the golang MCP SDK. - CICD: please see [the github actions
johannesjoAGENTS.mdjohannesjo/parallel-code/AGENTS.md
utilities, and app state. - `electron/ipc/`: terminal, Git/worktree, task, persistence, and other desktop handlers. - `electron/mcp/`: MCP server and subtask coordinator; `electron/agent-hooks/`: agent lifecycle hooks. - `src/remote/`, `electron/remote/`: phone UI and its server
hoangsonwwAGENTS.mdhoangsonww/Claude-Code-Agent-Monitor/AGENTS.md
work - `server/` for API/routes/data processing. - `client/` for React UI behavior. - `mcp/` for local MCP server tooling. - `scripts/` for hook/install/import/cleanup utilities. ## Validation expectations - Full local gate (headers + format + client typecheck + server
MicrosoftAGENTS.mdmicrosoft/work-iq/AGENTS.md
plugin marketplace** for managing AI agent plugins for GitHub Copilot CLI. It provides MCP servers, skills, and tools that connect AI assistants to Microsoft 365 data. ## Repository Structure ``` work
alpacahqAGENTS.mdalpacahq/alpaca-mcp-server/AGENTS.md
Agent Instructions ## Architecture Overview This MCP server auto-generates tools from bundled OpenAPI specs (`src/alpaca_mcp_server/specs/`) using FastMCP's `from_openapi()`. Tool names, descriptions, and output risk classifications are defined
Azure-SamplesAGENTS.mdAzure-Samples/AI-Gateway/AGENTS.md
management | | `snippets/` | Reusable Python code snippets loaded into notebooks via `%load` magic command | | `mcp-servers/` | Sample MCP server implementations (`weather/`, `spotify/`, `github/`, `oncall/`, `prm-graphapi/`) | **Snippets usage:** Labs reference `utils
ericbuessAGENTS.mdericbuess/claude-code-docs/docs/agents.md
Claude sessions. To involve a different tool, expose it to Claude as an [MCP server](/docs/en/mcp). Three more tools support this work without being a way to run agents themselves
shanraisshanAGENTS.mdshanraisshan/codex-cli-best-practice/AGENTS.md
Config** (`.codex/config.toml`) — TOML-based layered config with 5 profiles (conservative, development, trusted, ci, review), MCP server registration, and agent definitions. Project-level overrides user-level (`~/.codex/config.toml`); CLI flags override both
MicrosoftAGENTS.mdmicrosoft/wassette/AGENTS.md
Agent Guide for Wassette Wassette is an MCP server that runs tools as WebAssembly components with Wasmtime. This file is the entry point for coding agents and contributors; the linked
SylphxAIAGENTS.mdSylphxAI/anymd/AGENTS.md
Markdown for AI agents. It is one Rust binary (`crates/anymd`) that is both the MCP server and the CLI, published to npm as `@sylphx/anymd`. Project facts are in `PROJECT.md`; publishing
MicrosoftAGENTS.mdmicrosoft/power-platform-skills/AGENTS.md
version, keywords) - `.claude-plugin/plugin.json` — legacy mirror of `.plugin/plugin.json` kept for existing subscriptions - `.mcp.json` — MCP server configuration (optional) - `agents/` — Agent definitions (`.md` files with YAML frontmatter) - `skills/` — Skill definitions, each
MicrosoftAGENTS.mdmicrosoft/power-platform-skills/plugins/canvas-apps/AGENTS.md
This Plugin Is A plugin for authoring Power Apps Canvas Apps. The Canvas Authoring MCP server (`CanvasAuthoringMcpServer`) exposes tools that agents use to generate, validate, and compile Canvas App YAML
MicrosoftAGENTS.mdmicrosoft/power-platform-skills/plugins/model-apps/AGENTS.md
# AGENTS.md — Model Apps Plugin This file provides guidance to AI Agents when working with
MicrosoftAGENTS.mdmicrosoft/power-platform-skills/plugins/power-automate/AGENTS.md
cancel_all**, **resubmit**, **diagnose**, loop repetitions), dynamic resolvers, templates, and `get_expression_help`. The MCP server (`.mcp.json` → `flowagent`) is the supported integration path: it handles auth (Azure CLI + MSAL), session
MicrosoftAGENTS.mdmicrosoft/power-platform-skills/plugins/power-pages/AGENTS.md
browsing the marketplace. ## Skill Development Conventions ``` .plugin/plugin.json ← Open Plugins metadata (name, version, keywords) .mcp.json ← MCP server config (Playwright for browser automation) agents/ data-model-architect.md ← Agent: proposes Dataverse data models (read-only
repopromptAGENTS.mdrepoprompt/repoprompt-ce/AGENTS.md
daemon build/test command above to validate a change. If the change affects packaging, the MCP server, the MCP CLI, Agent Mode, or any feature that depends on the running
Auriti-LabsAGENTS.mdAuriti-Labs/geo-optimizer-skill/AGENTS.md
project shape: - Python package with CLI commands, core audit/fix logic, FastAPI web demo, and MCP server support - MIT licensed - Python 3.9+ compatibility is required Primary user-facing surfaces: - `geo audit
opentabs-devAGENTS.mdopentabs-dev/opentabs/AGENTS.md
Project Instructions for Codex ## Project Overview **OpenTabs Platform** is a Chrome extension + MCP server with a plugin-based architecture. A plugin SDK allows anyone to create OpenTabs plugins as standalone
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.
