https://github.com/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
https://github.com/anthropics/launch-your-agent
Last synced: 5 days ago
JSON representation
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
- Host: GitHub
- URL: https://github.com/anthropics/launch-your-agent
- Owner: anthropics
- License: apache-2.0
- Created: 2026-06-16T14:49:50.000Z (11 days ago)
- Default Branch: main
- Last Pushed: 2026-06-17T12:56:48.000Z (11 days ago)
- Last Synced: 2026-06-21T17:23:33.285Z (6 days ago)
- Language: HTML
- Size: 65.4 KB
- Stars: 311
- Watchers: 2
- Forks: 70
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
Awesome Lists containing this project
- awesome-agent-skills - launch-your-agent - Anthropic reference skill for interviewing a founder, scoping a v0, launching a Claude Managed Agent, grading it, and planning the next version. (Official Skills)
README
# launch-your-agent
A [Claude Code](https://code.claude.com) skill that helps a technical founder build whatever they want on **Claude Managed Agents (CMA)** — an internal worker, a piece of their product, a customer-facing agent. It interviews you about what you want to build, scopes a v0, launches it in your own account, grades it against your own definition of done, iterates, and (if it should run on a clock) puts it on a scheduled deployment — with everything bigger laid out as an explicit v1/v2 plan.
> Reference implementation. Not maintained and not accepting contributions. Licensed under [Apache 2.0](./LICENSE).
## Quickstart
```bash
git clone
cd
claude
```
Then type:
```
/launch-your-agent
```
The skills in `.claude/skills/` are picked up automatically when you run Claude Code inside this folder — nothing to install.
When you're done (or any time later), `/wrap-up` regenerates the overview page, recaps every primitive you now own, and suggests the next 1–2 upgrades.
## What you need
- Claude Code installed and signed in.
- An Anthropic API key for **your own** account (you'll create it during the flow at platform.claude.com → API keys; it goes into a local `.env` file, never into the chat). Runs cost cents.
## What you walk away with
- A live managed agent in your Console (agent + environment + graded run, plus a scheduled deployment if your task recurs).
- A `my-agent/` folder: the build sheet, the exact API payloads, a resumable launch script, an eval scaffold, an overview page, and a NEXT-DIRECTIONS.md laying out v1/v2.
## Repo layout
| Path | What it is |
|---|---|
| `.claude/skills/launch-your-agent/` | The main skill: 4 phases (interview → stage & launch → grade & iterate → run without you) + references (interview mapping, verified API call shapes, examples bank, overview template) |
| `.claude/skills/wrap-up/` | Companion skill: explicit close-out / status check for a built agent |
| `cma-primitives.md` | Inventory of CMA primitives and limits, from the public docs |
| `interview-to-config.md` | Background: how interview answers map to CMA primitives |
| `examples-bank.md` | Sourced example agents and production proof points |
| `ui/` | Example overview page + build sheet |
The CMA documentation is the source of truth for the API: https://platform.claude.com/docs/en/managed-agents/overview