Skip to main content

Overview

Agents you build on Aster are yours. The prompt is markdown, the skills are SKILL.md files, the tool definitions are JSON Schema, and the knowledge base documents are your own files. None of it is a proprietary format, and all of it comes out through the public API whenever you want it — no export request, no support ticket. This page gives you the scripts. The first pulls an agent into a portable bundle; the second stands that bundle up on Anthropic’s Managed Agents API, running on Anthropic’s infrastructure under your own API key, with Aster nowhere in the request path.
You need an Aster API key (Control Hub → Settings → API Access) and, for the second script, an Anthropic API key.

What travels and what doesn’t

Being straight about this matters more than the pitch.

Comes with you

System prompts — plain markdown, no wrapper.SkillsSKILL.md plus bundled files, in the open Agent Skills format. The same format Anthropic’s Skills API accepts, so they upload unchanged.Tool schemas — JSON Schema, one entry per tool.Knowledge base documents — your own source files, which you already hold.

Stays on Aster

Tool implementations. Aster ships 200+ tool integrations — Salesforce, Snowflake, NetSuite, Egnyte, and the rest — plus retrieval, the Python sandbox, scheduling, audit logging, and app hosting. The schemas travel; the code behind them is the platform.On another runtime you either map a tool to a native equivalent or implement it yourself against the exported schema. The export script lists exactly which tools are in that bucket.
Embeddings are derived data, not source data — whatever runtime you move to regenerates them from your documents.

Step 1: export the agent

You get a directory like this:
The skills/ directory is deliberately laid out to match .claude/skills/ — commit it to a repository and Anthropic’s Managed Agents will discover those skills automatically when the repo is mounted on a session, with no upload step at all.

Step 2: run it on Anthropic

The mapping is close to one-to-one: Every tool the prebuilt toolset doesn’t cover comes back to your code as a custom tool call. The script prints that list on startup and returns an explicit “not implemented” for each one — a stub that lies about its result would be worse than no stub at all. handleCustomTool is where your implementations go.

Other destinations

Nothing here is specific to Managed Agents. The same bundle drops into any runtime that reads a system prompt and Agent Skills:
  • Claude Code or the Claude Agent SDK on your own machines — put SYSTEM_PROMPT.md in CLAUDE.md and skills/ in .claude/skills/.
  • Your own agent loop against the Messages API, or any other provider — the prompt is markdown and the tool definitions are JSON Schema.

Agent Skills

The SKILL.md format your skills are already written in.

Security

Data ownership, retention, deletion, and subprocessors.