Astra Básico – trilingual guide with prompts, skill and token calculator
Material presenting Astra Básico, including prompt examples, skills and token‑usage calculation.
Astra Básico is a trilingual guide to token usage, with prompts, a skill, and a local calculator. The complete lesson with Nei covers 22 illustrated topics, narrated and subtitled in Portuguese. It explains how to monitor usage and choose resources for each task.
The guide helps distinguish usage in ChatGPT, Codex, and the API, since limits and charges vary across these environments. It offers guidance on organizing context, adjusting reasoning effort, and dividing tasks when appropriate. Its aim is to reduce waste without sacrificing quality, using available indicators and comparisons between equivalent tasks.
To get started, obtain the materials. Python 3 is required only for the local calculator; the guide and prompts work in a browser. Installing the skill is optional. When testing changes, adjust one variable at a time and keep the quality criteria. The calculator shows an API pricing simulation, which does not represent subscription limits.
The link opens the original content; some require a subscription.
Go further on INEMA.CLUB
More news
- 02/10Raio-X de Margem helps clinics and salons track losses and goalsThe dashboard compares results before and after, and tracks losses, targets, and attributable bonuses in a pilot with 1,302 clinics and salons in Batel.
- 01/10OpenAI Dots: analysis, criticism, and comparison with other toolsAn analysis explains what OpenAI Dots is, compares it with Muse, Grokbot, and Hermes, and gathers reported criticism and issues.
- 29/09San Martín — new visual concept and homepage in three languagesA new desk-style visual concept with sticky notes and folders, plus a homepage available in Portuguese, English, and Spanish.
- 29/09Codex + Claude in a video: how each one plans and reviewsA video presents the six levels of Use Both and explains each tool’s role, while also showing open courses and kits.
- 28/09Trade com Agentes: a 7-day study with GPT-6 AstraA study presents routines, task handoffs, and strategy with GPT-6 Astra, and explains why the result fell short of the S&P; it is not a recommendation.