Skip to content
Recued
Menu
← Back to recipes

Anthropic message brief

by recued-core v1

Read-only Anthropic Messages API workflow. It reads model metadata, counts tokens for explicit messages, creates one non-streaming Claude response through recued-core.anthropic.message.create, and summarizes the content and usage. It never enables tools, server web/search/fetch tools, code execution, MCP, containers, streaming, batch creation, file upload/download, managed-agent APIs, admin APIs, or arbitrary Anthropic API routes.

How it works 8 steps

Inspect the data fetches, transforms, gates, and output this recipe runs.

Process (8 steps)
model_details ?
token_count ?
message ?
content_blocks default
Apply default
content_count count
Count items in content blocks
summarize ?
content_table to_table
Format results as a data table
card to_summary
Format results as a summary card
Settings 8 configurable

Configurable at install. Defaults shown — change them anytime in Recued.

focus setting = Summarize the Claude response, stop reason, token usage, and practical follow-ups visible in the Anthropic API response. Do not invent facts outside the Anthropic response.
model setting = claude-sonnet-5
system setting =
messages setting =
anthropic setting =
max length setting = 900
max tokens setting = 1024
service tier setting = auto

Trust & control

What installing this recipe would let it do. Recued grants these permissions at install — review them there before approving.

Where it runs

Device + server Runs on your device (browser) or your server.

Permissions it requires

Read your Anthropic connection
Declared by the recipe — Recued grants these at install, where you review them before approving.

About

Tags

anthropic anthropicclaudemessagesai-summarytokenspack:anthropic

Details

8 steps 8 configurable settings recipe_id: anthropic-message-brief