Use “Anthropic token readiness brief” in Recued. It provides a read-only Anthropic prompt readiness workflow.

How it works 5 steps

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

Process (5 steps)

◆ model_details recued-core.anthropic.model.read

Read model on anthropic

◆ token_count recued-core.anthropic.message_token.count

Count message token on anthropic

■ message_count count

Count items in setting messages

✦ summarize core.ai.summarize

AI generates a concise summary

■ card to_summary

Format results as a summary card

▼

Output

summary card

Settings 6 configurable

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

focus setting = Review the prompt for Anthropic API readiness: input token count, model context limits, planned output budget, obvious context-window risks, and next prompt-sizing steps. Do not invent facts outside the model metadata and token count.

model setting = claude-sonnet-5

system setting =

messages setting = [object Object]

max length setting = 700

planned max tokens setting = 1024