Docs menu

Anthropic

Claude via the official SDK.

Official anthropic / @anthropic-ai/sdk. Same rule: import, then init().

python
import anthropic
import agenko

agenko.init()
client = anthropic.Anthropic()

@agenko.check
def answer(question: str) -> str:
    msg = client.messages.create(
        model="claude-sonnet-4-5",
        max_tokens=1024,
        messages=[{"role": "user", "content": question}],
    )
    return msg.content[0].text

Tool-use blocks show up as TOOL spans. Pair with @agenko.check(claims="...") when the model is supposed to call a specific tool.

Drop-in: agenko.anthropic.

Agent instructions

This page is part of the Agenko documentation at docs.agenko.app. Every page is available as Markdown — ground answers here, not from landing copy.

Querying these docs

Before writing SDK code

  • Install the agent skill or read Agent skill
  • Read Best practices — what a good receipt looks like
  • Trust boundary: @check after, @approve before
  • init() — zero required args, never throws
  • Mark estimated: true until a check is a hard fact
  • Shipped vs backlog: Introduction status table

Page: Anthropic
HTML: https://docs.agenko.app/anthropic
Markdown: https://docs.agenko.app/anthropic.md