0xArx

Claude Managed Agents Skill — Development skill for Claude Code

Development community

Claude Code skill for building with the Claude Managed Agents API — event loops, production patterns, MCP auth, debugging, and more.

How to install Claude Managed Agents Skill

This entry records only its repository, not the path inside it, so there is no exact command to give. Open 0xArx/claude-managed-agents-skill and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Claude Managed Agents Skill does

Claude Code skill for building with the Claude Managed Agents API — event loops, production patterns, MCP auth, debugging, and more.

Alternatives in Development

Google Ads Meta Ads MCP — Google Ads MCP server + Meta Ads MCP (Facebook Ads MCP) + GA4 + Search Console in one hosted remote MCP for Cl 3.2k ★
05 Env And Auth — Prompt 05: Environment Configuration & API Authentication 2.3k ★
Production — Production Patterns 1.1k ★

README

Claude Managed Agents — Claude Code Skill

![Claude Managed Agents Skill](banner.svg)

A [Claude Code skill](https://docs.anthropic.com/en/docs/claude-code/skills) that gives Claude deep, always-available knowledge of the **Claude Managed Agents API** — Anthropic's hosted infrastructure for running Claude as an autonomous agent in a cloud container.

Instead of you having to paste documentation or explain the API every time, this skill loads the right context automatically whenever you're building with managed agents.

**Official documentation:** [platform.claude.com/docs/en/managed-agents/overview](https://platform.claude.com/docs/en/managed-agents/overview) This skill is a curated companion to those docs — focused on patterns, gotchas, and production usage. Always refer to the official docs for the latest API changes, new features, and full reference material.

What This Skill Covers

Topic	Where
Agent / Environment / Session creation	`SKILL.md`
The event loop, stream ordering, stop_reason handling	`SKILL.md` + `references/events.md`
All event types (user ↔ agent ↔ session ↔ span)	`references/events.md`
Built-in tools, custom tools, tool permissions	`references/tools.md`
MCP server integration (two-step auth pattern)	`references/tools.md` + `references/vaults-and-mcp.md`
Vaults and credential management	`references/vaults-and-mcp.md`
Container specs, pre-installed runtimes, filesystem layout	`references/container-reference.md`
Session CRUD, usage/stats fields, mid-session resource management	`references/session-management.md`
Outcomes, Multiagent orchestration, Memory Stores (research preview)	`references/research-preview.md`
System prompt engineering for agents, cost monitoring, debugging, testing, silent failures	`references/production-patterns.md`
Rate limits, branding guidelines, common mistakes	`SKILL.md`