Guides to Claude Code, Cursor, Codex and the Claude and GPT APIs: setup, token savings and troubleshooting.
6 min · · IDE
The Codex extension lives in the VS Code sidebar and uses the same config.toml as the CLI. Features, connecting a gateway and the limits.
5 min · · models
Opus 4.6, 4.7 and 4.8 are the previous generation, and the catalogue now has Opus 5 and 5.5. A four-step migration plan: model id, your own prompts, cost comparison, rollback.
5 min · · development
C++ forgives a model a lot at compile time and punishes it later. How to build a build, test and sanitizer loop for an agent and what it costs on different models.
6 min · · агенты
Claude Code understands Russian but answers in whatever language your instructions set. Where to put the language rule, what not to translate and what it costs in tokens.
6 min · · errors
Why a card payment can be rejected on a foreign service, what you can check yourself and how to connect models when payment does not go through.
6 min · · models
How to call claude-sonnet-5-5 from Python and curl, what a typical request costs with and without cache, and how it differs from Sonnet 5 and Sonnet 4.6.
6 min · · development
Schema, sample data and a query plan in the request to the model, an EXPLAIN check and read-only access. Working Python code and a cost estimate.
5 min · · development
The langchaingo library accepts any OpenAI-compatible address. We show the client, a request, streaming and a templated chain in Go, and estimate call costs.
5 min · · бизнес
Where a model really saves an accountant's time and where it cannot be trusted unchecked. Code to extract fields from a document with an arithmetic check, and a cost estimate.
6 min · · автоматизация
Two ways to question a PDF with a model: put the document in context and cache it, or retrieve the relevant parts. Python code and the price of twenty questions.
4 min · · автоматизация
A Word template, a data table and a script: hundreds of standard documents in one run. What to give the model, what to compute in code and how to verify fields.
6 min · · IDE
How to open a 1C configuration dump in Cursor, write rules for BSL, give the agent metadata and avoid accepting invented code. With a session cost estimate.
5 min · · бизнес
How a teacher can prepare materials with a model: tiered assignments, criteria, draft feedback. What to check, what not to delegate and what it costs.
5 min · · автоматизация
A monthly content plan and thirty posts in one voice from a single script. How to describe the brand voice, generate in batches and check the output.
5 min · · бизнес
Where a model really saves a marketer's time and where it invents numbers. Code for review analysis, fact-checking rules and a cost estimate.
5 min · · автоматизация
Combine an ordinary text diff with a model's semantic review to see which edits change the terms and which are cosmetic. Code, report format and cost.
6 min · · errors
A Cursor limit is consumption of an included amount of usage, not a message counter. What eats it and four ways to keep working when it runs out.
6 min · · агенты
We connect Ollama to Roo Code, Cline, Aider and OpenCode per each tool's documentation, cover the limits and show when it is simpler to return to a cloud API.
5 min · · development
How to get a Pydantic object instead of text from a model: with_structured_output, three methods, include_raw, retries on errors and testing several models on your data.
6 min · · payments
How Google bills the Gemini API, where setup gets stuck on payment, and how to call Gemini from a single dollar balance instead.
5 min · · development
Install Claude Code on Linux and macOS, put the address and key into your shell profile and verify the connection with curl. PATH and permission errors included.
4 min · · автоматизация
Collect page data with a script, send the model compact JSON and get a report on headings, meta tags and text structure. With a cost estimate and honest limits.
7 min · · агенты
A skill is a folder with a SKILL.md file that Claude Code loads only when needed. We compare it with CLAUDE.md and write one of our own.
6 min · · экономия
We price requests to Grok 4.7, 4.6 and 4.5 in Zukko on three scenarios and compare with official xAI prices. Formulas are shown and the arithmetic can be checked.