launch-your-agent skill
A Claude Code skill that takes a founder from idea to a live Claude Managed Agent: interview, v0 build, launch, grading and scheduling
- 1,123 ★ on the repository
- Last commit
- Apache-2.0
Extended access
Why this level
- Launches an agent through an external API with your key
- Runs consume funds from your Anthropic account
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/launch-your-agentDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Launches an agent through an external API with your key
- Runs consume funds from your Anthropic account
This is third-party code. Review the repository files before installing.
What it does
The skill walks a technical founder through building an agent on Claude Managed Agents. It first asks what needs doing and scopes a minimal v0 that covers the core job. Then it launches the agent in the user's own account, grades the result against their own definition of done and suggests fixes. If the task recurs, it sets up a scheduled deployment, and larger work goes into a v1 and v2 plan. A companion wrap-up skill refreshes an overview page and points to the next upgrades.
Who it is for. For technical founders who want to launch a first agent on Anthropic's hosted runtime without building their own harness.
Good fit when
- You want to build and launch an agent on Claude Managed Agents quickly
- You want to go from idea to a working, graded v0
- You need an agent that runs on a schedule
Not a fit when
- You have no Anthropic account or API key
- You need an agent on a different platform, not CMA
Example request
/launch-your-agent, help me build an agent that prepares a morning task digestLimitations
This is an educational reference implementation, not maintained and not accepting contributions. It needs your own ANTHROPIC_API_KEY, runs cost money, and the Claude Managed Agents platform is unavailable from Russia without a VPN. The skill is deliberately verbose and uses more tokens than a purpose-built agent.
How to disable. Remove the repository folder or the .claude/skills/launch-your-agent directory from the project.
FAQ
Do I need to install anything?
No. Skills under .claude/skills are picked up automatically when Claude Code runs inside the repo folder.
What do runs cost?
Runs go through your Anthropic account and cost cents per run; the key goes into a local .env.
Discussion
No questions or reviews yet.
Related
SkillsA Claude Code template: 15 department agents, five skills and an approval queue for outward actions such as emails and invoices.
A tool that builds tested skills from a real workflow and governs their lifecycle through your own marketplace
A set of skills, slash commands and agents for Claude Code that helps you build your own skills, agents, hooks, slash commands and prompts
One agent launches others in the background: Claude Code, Codex, Copilot CLI, Grok Build and Pi, with a model chosen per stage.
AI Builder Club Skills
AI Builder Club — Skills
A Claude Code plugin marketplace to make a repo agent-ready and run compounding agent loops
Anthropic skill for Claude Code that audits a multi-agent system and, by measurement, folds subagents into one loop with skills.
README in short
The README frames the skill as a copilot for a technical founder building an agent on Claude Managed Agents. It names four phases: interview, stage and launch, grade and iterate, run on a schedule, plus a plan for further work. There is no install step: clone the repo, run claude and invoke /launch-your-agent. It needs your own Anthropic key, and all API calls are documented in reference files. Apache 2.0 licensed.
README badge
Original SKILL.md
--- name: launch-your-agent description: Help a technical founder build whatever they want on Claude Managed Agents — an internal worker, a piece of their product, a customer-facing agent. Find out what they want to build, scope a v0, launch it in their account, grade it, iterate, and (if it should run on a clock) put it on a scheduled deployment, with everything bigger laid out as v1/v2. Use when a founder says "launch my agent", "/launch-your-agent", "build me a managed agent", or wants to build something on CMA. Keywords: managed agents, CMA, founder, launch, scheduled deployment, outcome rubric. version: 0.3.0 dependencies: ANTHROPIC_API_KEY (their own account) from the launch step onward. `ant` CLI optional — curl forms included for everything. --- # Launch Your Agent — founder copilot You are pairing with a technical founder inside Claude Code. They have something they want an agent to do. They should walk away with a Claude Managed Agent that does it — launched in their own account, graded against their own definition of done, and (if it should run on a clock) running on a schedule without them.