Zukko Blog
Guides to Claude Code, Cursor, Codex and the Claude and GPT APIs: setup, token savings and troubleshooting.
AI for testers: test cases, checklists and bug reports
5 min · · бизнес
How a QA engineer can use a model for test cases, checklists and bug reports, check coverage, and avoid requirements the model made up.
Invalid API key in opencode: why the key is rejected and how to check
5 min · · errors
The Invalid API key error in opencode almost always comes down to four causes. We test the key outside opencode and find where the chain breaks.
OpenAI SDK or LangChain: when a framework helps and when it gets in the way
5 min · · development
One scenario written with the plain SDK and with LangChain: how much code, where debugging is easier and how to keep control of token spend.
How much an AI agent costs: a step-by-step model spend calculation
8 min · · агенты
Agent cost is set by the number of steps, context growth, cache and the model. A formula, three examples with arithmetic and a calculator you can plug your own numbers into.
OpenAI API vs Anthropic API: the format differences and what to pick for your code
6 min · · API keys
Two request formats solve the same task but differ in details that break code when porting. A comparison of structure, tools, streaming, cache and headers.
Anthropic SDK for Python: base_url, key and a first request via a gateway
5 min · · development
The official anthropic package for Python just needs a different address. We cover base_url, the key, streaming, token counting, caching and errors.
Translating subtitles with a neural network: SRT without broken timecodes
6 min · · автоматизация
The main risk when translating SRT with a neural network is a broken file structure. A scheme where timecodes never reach the model, and a Python script with validation.
Skills in Codex: what they are and how to write your own
5 min · · агенты
A Codex skill is a folder with SKILL.md that the agent loads by description or on your call. Structure, a pytest example, and how it differs from plugins and hooks.
Claude Code: a checklist of best practices for daily work
6 min · · development
Habits that make working with Claude Code predictable: a short CLAUDE.md, a plan before edits, small tasks, checking results and keeping spend under control.
AI agent vs AI assistant: the difference and what to pick for a task
5 min · · агенты
A model answers, an assistant remembers the dialogue, an agent takes steps with tools on its own. The differences by example, and how to decide what your task needs.
The API key header: Authorization Bearer or x-api-key and where each goes
5 min · · errors
OpenAI clients send the key in Authorization, Anthropic clients in x-api-key. What the gateway accepts and how to tell from the response where the key got lost.
Claude Code security: a checklist before running the agent on a project
6 min · · development
The agent reads files and runs commands, so security settings belong before the first launch. A checklist: permissions, secrets, sandbox, a separate key with a limit.
Claude Code in Zed: connecting an external agent to your own key
6 min · · IDE
In Zed you can open Claude Code as a terminal thread, as an external agent over ACP, or configure the built-in agent. We cover each option and connect it to your key.
Claude Fable 5.1 or Sonnet 5.5: when a big price gap is justified
6 min · · сравнение
Fable 5.1 costs far more than Sonnet 5.5. We price the same task in both API formats and give a way to choose the model from results on your own examples.
DeepSeek V4 Flash or V4.1 Flash: which cheap model to pick
6 min · · сравнение
A newer version is not always more expensive. We compare DeepSeek V4 Flash and V4.1 Flash on price, cache, context and intelligence index, cost a workload and show how to test.
Saving tokens in opencode: a checklist of settings and habits
6 min · · экономия
opencode spend comes from habits and a few lines of config. A checklist you can verify: what to turn on, what to remove, and how to see the result in the dashboard.
Claude Code with Qwen, GLM and DeepSeek models through one key
7 min · · IDE
Claude Code is not tied to Claude: the model is set by a variable. A configuration for Qwen, GLM and DeepSeek, a session calculated, and how to keep Opus for the hard parts.
Claude Code for 1C: setting up an agent to work with a configuration
5 min · · IDE
The agent edits BSL text modules, not the infobase. How to dump a configuration, what goes into CLAUDE.md, how to check edits and what it costs.
Editing texts with a neural network: proofreading, style and cutting
5 min · · development
Different kinds of editing need different prompts. Wording for proofreading, style and cutting, how to get edits with explanations and how not to lose the author's voice.
Vibe coding for Bitrix24: apps and handlers built with an agent
6 min · · агенты
How to hand an agent a Bitrix24 app or handler without getting invented methods: project rules, webhooks, pagination, tests and a session cost.
How much Cline costs: the extension is free, you pay for tokens — a calculation
6 min · · экономия
With your own key Cline sells no model subscription: you pay for tokens. A workday on several models, calculated, and how to stay within budget.
Zed AI vs Cursor: a fast editor against an AI fork of VS Code
6 min · · IDE
Zed and Cursor approach AI differently: one builds around its own editor and the ACP protocol, the other extends VS Code. We compare them and connect your own key.
JetBrains AI vs Cursor: what a developer on IntelliJ and PyCharm should pick
6 min · · IDE
Stay in a JetBrains IDE with AI Assistant or move to Cursor? We compare features, own-model support and costs, with step-by-step settings.
An MCP server in Java: a minimal example with one tool
6 min · · development
We write a minimal MCP server in Java with one tool, register it in Claude Code, and learn to find the cause when the agent doesn't see it.