anthropics/launch-your-agent

Claude Code skills that take a founder from idea to a live Claude Managed Agent: interview, scope a v0, launch in their own account, grade it, iterate, and schedule it

What it solves

It simplifies the process of building and deploying agents using Claude Managed Agents (CMA). It acts as an interactive guide that helps technical founders move from a vague idea to a live, graded, and potentially scheduled agent in their own account.

How it works

The project is implemented as a skill for Claude Code. It follows a four-phase process: it interviews the user to define the agent's purpose, scopes a initial version (v0), launches the agent using CMA primitives, grades the agent's performance against a defined 'definition of done', and iterates on the design. If the agent needs to run on a schedule, it sets up a scheduled deployment.

Who it’s for

Technical founders who want to build internal workers, product features, or customer-facing agents using the Claude Managed Agents platform.

Highlights

  • End-to-end workflow: Covers everything from initial interview and scoping to launch and iteration.
  • Integrated grading: Includes a phase to grade the agent against specific success criteria.
  • CMA Integration: Directly leverages Claude Managed Agents primitives and API payloads.
  • Automated deployment: Supports scheduled deployments for recurring tasks.
  • Comprehensive output: Provides a build sheet, API payloads, a launch script, and a roadmap for future versions (v1/v2).

Related

  • Project
    Mininglamp-OSS/octo-server

    OCTO Server is a Go‑based backend that provides REST/WebSocket APIs, orchestrates OpenClaw‑powered "Lobster" AI agents, and controls real‑time messaging via WuKongIM. It serves as the central hub for OCTO’s web, mobile, and admin clients, handling authentication, RBAC, storage, and extensible adapters.

  • Project
    Softeria/ms-365-mcp-server

    ms‑365‑mcp‑server is a Node.js MCP server that wraps Microsoft 365 Graph APIs as a large set of declarative “tools” for LLM assistants. It handles MSAL authentication, lets you filter the tool surface and OAuth scopes, supports read‑only mode, and can output results in JSON or the token‑saving TOON format. Designed for Claude Desktop, Open WebUI, and similar AI‑agent platforms.

  • Project
    cisco-ai-defense/mcp-scanner

    MCP Scanner is a Python security tool that scans Model Context Protocol (MCP) servers, their tools, prompts, resources, and associated code for malicious behavior. It combines Cisco AI Defense API, YARA rules, and LLM‑based analysis, supports CLI and REST API modes, integrates vulnerability scanning, VirusTotal checks, and supply‑chain analysis for Python and npm packages, and offers extensive configuration and reporting options.

  • Project
    ruc-datalab/EvoOntology

    A self-evolving ontology layer for data agents that bridges the gap between raw data and AI agents by automatically constructing and refining a semantic layer via MCP tools.