ctx
stevesolun/ctx/AGENTS.md
product; older harness commands live under `ctx advanced`. `ctx-mcp-server` is the machine contract name. A few maintenance console scripts (`ctx-init`, `ctx-scan-repo`, `ctx-source-registry
How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
stevesolun/ctx/AGENTS.md
product; older harness commands live under `ctx advanced`. `ctx-mcp-server` is the machine contract name. A few maintenance console scripts (`ctx-init`, `ctx-scan-repo`, `ctx-source-registry
jianruntech/geo-score/AGENTS.md
file so `curl … \| python3 -` works | | `cli/geo_watch.py` | Levels 2 and 3 (`--ask`, `watch`) and the MCP server | | `cli/fixtures/mcp/` | The MCP `tools/list` snapshot and the 1.3.0 contract baseline (names and required arguments
KeyValueSoftwareSystems/agent-opfor/AGENTS.md
core subsystems fit together. For user-facing CLI docs see [`docs/cli.md`](docs/cli.md); for MCP-server-mode docs see [`docs/mcp.md`](docs/mcp.md). --- ## What this project is Opfor is an open-source
Azure/azure-dev/cli/azd/AGENTS.md
aka.ms/agency) with Azure DevOps MCP access for the `azure-sdk` organization and Kusto MCP access to the `DevCli` database. Prefer these tools for ADO operations and authorized telemetry investigations
Azure/azure-dev/cli/azd/extensions/azure.ai.agents/AGENTS.md
suite of goal-based scenarios for the [cli-interactive-tester](https://github.com/coreai-microsoft/cli-interactive-tester) MCP server under `tests/cli-interactive-tester-scenarios/`. They drive real `azd ai agent` flows end-to-end (init, provision, deploy
Abilityai/trinity/AGENTS.md
localhost` (port 80) | | Backend API | `http://localhost:8000` — OpenAPI at `/docs` | | MCP server | `http://localhost:8080/mcp` (Streamable HTTP) | | Health check | `GET http://localhost:8000/health` → `{"status": "healthy", ...}`; 503 + `"unhealthy"` while
neiltron/apple-health-mcp/AGENTS.md
Repository guidance ## Project This package is a local `stdio` MCP server that queries Simple Health Export CSV files through an in-memory DuckDB database. The public npm package and MCP
wuxiran/cc-pane/AGENTS.md
support, Markdown preview, image preview - **Screenshot** — Region capture with global shortcut, multi-monitor support - **MCP Server Config** — Configure MCP servers per project ## Technology Stack | Layer | Technology | Purpose | |-------|-----------|---------| | Desktop Framework | Tauri
bex-co/bex/AGENTS.md
code (cascading): - operator / activator / pg-sni-proxy / kv-sni-proxy / egress-meter / static-server → [lego/operator/AGENTS.md](lego/operator/AGENTS.md) - bex-api / ssh-gateway → [lego/backend/AGENTS.md](lego/backend/AGENTS.md) - dashboard SSR → [dashboard/AGENTS.md](dashboard/AGENTS.md) ## Docs — where to look
levnikolaevich/claude-code-skills/AGENTS.md
plugins/ /skills/ /SKILL.md`. - Keep each skill standalone. It must not require another skill, MCP server, task tracker, separately installed coordinator or worker, or shared runtime. A skill may require host
HoangNguyen0403/agent-skills-standard/AGENTS.md
/caveman` mode for reporting. ## 🔌 Runtime Enforcement via MCP If the `agent-skills-standard` MCP server is registered in your runtime (check your tool list — look for `load_skills_for_files
HoangNguyen0403/agent-skills-standard/server/AGENTS.md
project-specific skills applicable." ## 🔌 Runtime Enforcement via MCP If the `agent-skills-standard` MCP server is registered in your runtime (check your tool list — look for `load_skills_for_files
microsoft/Generative-AI-for-beginners-java/AGENTS.md
Building a project:** ```bash cd [project-directory] mvn clean install ``` **Starting the MCP Calculator Server:** ```bash cd 04-PracticalSamples/calculator mvn spring-boot:run # Server runs on http://localhost:8080 ``` **Running
microsoft/Generative-AI-for-beginners-java/translations/bg/AGENTS.md
Създаване на проект:** ```bash cd [project-directory] mvn clean install ``` **Стартиране на MCP Calculator Server:** ```bash cd 04-PracticalSamples/calculator mvn spring-boot:run # Сървърът работи на http://localhost:8080 ``` **Изпълнение
microsoft/Generative-AI-for-beginners-java/translations/cs/AGENTS.md
projektu:** ```bash cd [project-directory] mvn clean install ``` **Zahájení MCP Calculator Serveru:** ```bash cd 04-PracticalSamples/calculator mvn spring-boot:run # Server běží na http://localhost:8080 ``` **Spuštění klientských příkladů:** ```bash
microsoft/Generative-AI-for-beginners-java/translations/da/AGENTS.md
boot:run ``` **Byg et projekt:** ```bash cd [project-directory] mvn clean install ``` **Start MCP Calculator Server:** ```bash cd 04-PracticalSamples/calculator mvn spring-boot:run # Server kører på http://localhost
microsoft/Generative-AI-for-beginners-java/translations/de/AGENTS.md
spring-boot:run ``` **Ein Projekt bauen:** ```bash cd [project-directory] mvn clean install ``` **MCP Calculator Server starten:** ```bash cd 04-PracticalSamples/calculator mvn spring-boot:run # Server läuft auf http://localhost
microsoft/Generative-AI-for-beginners-java/translations/el/AGENTS.md
spring-boot:run ``` **Κατασκευή έργου:** ```bash cd [project-directory] mvn clean install ``` **Εκκίνηση MCP Calculator Server:** ```bash cd 04-PracticalSamples/calculator mvn spring-boot:run # Ο διακομιστής τρέχει στο http://localhost
microsoft/Generative-AI-for-beginners-java/translations/en/AGENTS.md
Building a project:** ```bash cd [project-directory] mvn clean install ``` **Starting the MCP Calculator Server:** ```bash cd 04-PracticalSamples/calculator mvn spring-boot:run # Server runs on http://localhost:8080 ``` **Running
microsoft/Generative-AI-for-beginners-java/translations/et/AGENTS.md
koostamine:** ```bash cd [project-directory] mvn clean install ``` **MCP kalkulaatori serveri käivitamine:** ```bash cd 04-PracticalSamples/calculator mvn spring-boot:run # Server töötab aadressil http://localhost:8080 ``` **Kliendi näidete käitamine:** ```bash
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.