Intermediate
Claude Agents Explained: Subagents, Agent SDK, Managed
Claude agents come in four forms: Claude Code subagents, the Agent SDK, Managed Agents and the API tool runner. See how each works and which to pick.
Intermediate Guides
Intermediate guides for Claude, curated and kept up to date by Claudekit. Browse all 23 intermediate entries with summaries, sources and related resources.
Intermediate
How to Build an AI Agent with Claude (Step by Step)
Build an AI agent with Claude: compare subagents, the Agent SDK, Managed Agents and the API tool loop, then run a Python agent with a custom tool and a budget.
Intermediate
Claude Code GitHub Actions: @claude Mentions and PR Review
Set up Claude Code GitHub Actions: /install-github-app, secrets, @claude mentions, automated PR review, scheduled jobs, claude_args and cloud providers.
Intermediate
Claude Code Review: Official, /code-review, Action or Kit?
Four ways to get Claude to review code: the managed Code Review app, /code-review in your terminal, the GitHub Action or a kit you own. Cost and setup compared.
Intermediate
Claude Code Security Checklist for Teams
A Claude Code security checklist for teams: permission modes, secret deny rules, the Bash sandbox, guard hooks, MCP and plugin review, CI and managed settings.
Intermediate
Claude Code Statusline: Show Your Rate Limit Usage
Show your Claude Code 5-hour and weekly limit usage in the status line: a tested bash script using the documented rate_limits fields, with setup and fixes.
Intermediate
Claude Code Subagents: How to Create and Use Them
A practical guide to Claude Code subagents: built-in agents, .claude/agents files, frontmatter, tool limits, models, memory and patterns that save context.
Intermediate
How to Reduce Claude Token Usage (Claude Code, Chat and API)
Documented ways to cut Claude token usage: /clear and /compact, model and effort choice, a lean CLAUDE.md, subagents, MCP hygiene, and prompt caching on the API.
Intermediate
The Agent Skills Standard Explained (SKILL.md, 2026)
What the Agent Skills open standard is, the SKILL.md fields the spec allows, how progressive disclosure works, and what Claude Code adds on top of the standard.
Intermediate
Build an MCP Server in TypeScript (SDK v2 Tutorial)
Build your first MCP server in TypeScript with the v2 SDK: setup, a tool, a resource and a prompt, testing in MCP Inspector, then connecting it to Claude Code.
Intermediate
Claude API Pricing (2026): Per-Token Costs and Examples
Claude API pricing for every current model: input, output and cache prices per million tokens, Batch API discounts, tool fees and four worked cost examples.
Intermediate
Claude Code Best Practices: 20 Tips That Actually Work
Claude Code best practices and tips from the official guide and daily use: verification loops, plan mode, lean CLAUDE.md, context hygiene and parallel work.
Intermediate
Claude Code Context Window: /context, /compact and /clear
Manage the Claude Code context window: what loads at startup, when to use /context, /compact and /clear, how compaction works, and habits that keep it lean.
Intermediate
Block Dangerous Commands in Claude Code with PreToolUse Hooks
Stop rm -rf, curl | sh, force-pushes and DROP TABLE before they run: a tested PreToolUse hook for Claude Code, deny rules, onFailure and the limits to know.
Intermediate
Claude Code --dangerously-skip-permissions: When It's Safe
What --dangerously-skip-permissions does in Claude Code, what still stops it, and how to run it safely in a container as a non-root user. Checked October 2026.
Intermediate
Claude Code Hooks Guide: Automate and Guard Your Agent
How Claude Code hooks work: lifecycle events, matchers, exit codes and JSON output, plus ready-made hooks for formatting, alerts and blocking risky edits.
Intermediate
Claude Code Headless Mode: claude -p for Scripts and CI
Run Claude Code headless with claude -p: output formats, JSON schema, streaming, tool allowlists, bare mode, resuming sessions and copy-paste CI scripts.
Intermediate
Claude Code Plugins Guide: Install, Build and Share
How Claude Code plugins work: installing from marketplaces, install scopes, the best official plugins, and building your own with skills, agents, hooks and MCP.
Intermediate
Claude Code Permission Modes: Auto, Plan, Accept Edits & More
Every Claude Code permission mode explained: Manual, acceptEdits, plan, auto, dontAsk and bypass, plus allow/ask/deny rules and safe defaults for local and CI.
Intermediate
Claude Code Sandbox: Set Up /sandbox for Safer Bash Commands
Turn on the Claude Code sandbox with /sandbox: what it blocks, auto-allow vs regular mode, allowWrite, allowedDomains, credentials and strict mode explained.
Intermediate
Claude Code Skills Guide: How to Write a SKILL.md
Learn what Claude Code skills are, where SKILL.md files live, the key frontmatter fields, and how to write, test and share skills, with copy-paste examples.
Intermediate
Claude Code Worktrees: Run Parallel Sessions Safely
Run Claude Code sessions in parallel with git worktrees: the --worktree flag, .worktreeinclude, subagent isolation, /batch, cleanup rules and manual setup.
Intermediate
Skills vs Subagents vs Hooks: When to Use Each in Claude Code
Skills vs subagents vs hooks in Claude Code, answered: what each one does, context cost, when to pick which, how they combine, plus CLAUDE.md, MCP and plugins.