Zukko Blog
Guides to Claude Code, Cursor, Codex and the Claude and GPT APIs: setup, token savings and troubleshooting.
opencode agents: setting up roles, models and tools
5 min · · агенты
A custom agent in opencode is a role, a model and a set of permissions. A working config where a cheap model handles routine work and a stronger one edits code.
Plan mode in Claude Code: plan first, then edit the code
6 min · · агенты
In plan mode Claude Code reads your code and proposes a plan but edits nothing until you agree. How to enable it, use it and what it costs.
Prompt Injection: What It Is and How to Protect a Bot and an Agent
5 min · · development
How prompt injection works through user input and third-party documents, and which measures limit the damage: data isolation, tool permissions, key limits.
An AI agent for job hunting: a résumé tailored to the job and cover letters
4 min · · агенты
We build a small tool: you give a vacancy text and a file with your real experience, and get a tailored résumé, a letter and a list of gaps. No invented skills.
Claude Code YOLO: Permission Modes and Working Without Prompts
6 min · · агенты
Claude Code has no mode literally called YOLO, but it has several permission modes and flexible rules. How to stop clicking Yes without losing files.
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.
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.
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.
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 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.
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.
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.
RAG or MCP: what is the difference and which to choose for giving a model data
6 min · · сравнение
RAG puts retrieved pieces into the prompt, MCP gives the model tools it calls itself. How they differ, what each costs and how to combine them.
Claude Desktop or Claude Code: What Is the Difference and Which to Pick
6 min · · сравнение
The desktop app and the console agent share one engine but sign in differently. We compare scenarios, model access and cost.
LangChain agents: tools, the loop and capping spending
5 min · · агенты
We build an agent with create_agent and two tools and run it on a model through an OpenAI-compatible gateway, then cap the steps and count tokens.
MCP in Open WebUI: giving models access to external tools
5 min · · агенты
Open WebUI can connect MCP servers and hand their tools to models. We cover step-by-step setup, the limits, and what it does to token usage when you work through a gateway.
Claude Code Router: do you need it if the gateway speaks the Anthropic format
6 min · · агенты
Claude Code Router appeared to point Claude Code at other providers' models. If the gateway already accepts the Anthropic format, much of that is one variable.
An AI agent for 1C: which tasks to automate and how
5 min · · агенты
An agent around 1C answers questions from data, drafts documents and looks for anomalies. We cover the scenarios, the HTTP-service architecture and safety measures.
AI for game programming: Unity, Godot and browser games
6 min · · development
An agent writes scripts but does not see the engine editor. How to structure a game project for AI, what to hand the agent, what to do by hand, and what it costs.
Cline "hit repeated tool call failures": causes and fixes
6 min · · errors
The message means the agent failed several tool calls in a row. Causes and a checking order, from the base URL to context size.
Qwen Code: error 401 invalid access token or token expired
5 min · · errors
A 401 in Qwen Code often means a stale Qwen OAuth login or a key sent to the wrong address. Step-by-step diagnosis and a switch to your own key.
Project rules in Qwen Code: context files and token savings
5 min · · агенты
How to explain project rules to Qwen Code once: QWEN.md, path-conditional rules, skills and MCP, and how many tokens each such file costs.