Claude Code Subagent Not Working? Common Problems and Fixes
Fix a Claude Code subagent not working: check agent files, delegation, tools, permissions, and model settings with a small reproducible test.
Topic
Tutorials and reference guides for Anthropic Claude Code, the agentic command-line tool for software engineers. Articles in this section cover hooks, slash commands, skills, subagents, memory files, the /doctor and /compact commands, and the workflows that hold up in real repos. Every guide is written from real use on production codebases, with named version numbers, exact terminal output, and the actual error messages users hit. If you are new to Claude Code, start with the basics and work outward to the hooks and skills sections.
Fix a Claude Code subagent not working: check agent files, delegation, tools, permissions, and model settings with a small reproducible test.
Explore 10 Claude Code subagent use cases with example prompts, useful outputs, and clear limits. Choose the right helper for your next development task.
Create your first Claude Code subagent with a complete beginner tutorial. Copy the agent file, review sample code, and check that your setup works.
Protect API keys when using AI coding agents. Learn what .gitignore cannot do, how to limit access, and what to do if a secret leaks.
Claude Code 2.1.277 reads AGENTS.md, but CLAUDE.md still wins by default. See the four modes, the CLAUDE.local.md gotcha, and when to keep both files.
Full decision matrix for Claude Opus 5.5, Sonnet 5, and Haiku 4.5 with real cost math, task-by-task recommendations, and how to switch models.
Full Claude Opus 5.5 migration guide with fixes for the four breaking changes: thinking, tool_choice, thinking blocks, and computer_20251124.
Claude Code has 5 real primitives: Skills, MCP, Hooks, Plugins, Subagents. Plain guide with a decision tree and Anthropic's own trigger table.
Plain guide to fix MCP server not connecting in Claude Desktop, Claude Code, Cursor and VS Code. Covers error -32000, -32001, npx ENOENT, and timeouts.
On Aug 14 2026 Claude Code made auto mode the default. On Sept 1 a new Containment Escape rule blocked three risky moves. Plain non-tech guide.
Claude Code hooks let you block risky commands, auto-format code, and inject project context. Plain guide to events, settings.json wiring, and 5 examples.
Anthropic's +50% Claude Code weekly promo ends Sept 13 and a smaller +25% base takes over Sept 14. Plain guide with per-plan numbers and workarounds.
Understand Claude Max and Team API credits, how to claim them, what they cover, and how API billing differs from your Claude subscription limits.
Claude Code feels slow when context bloats, MCP tools chain in loops, or memory files grow. See the seven fixes with /doctor and /compact walkthroughs.
What Claude Code's /goal command and Agent View do, how they work together, how to write a completion condition that holds, and when to actually use them.
A plain-English breakdown of Anthropic's internal report on how its own teams use Claude Code: the real workflows, the numbers, and what you can copy.
I used Claude Code and Cursor side by side for three months on production work. Here is where each one wins, where it loses, and the one I kept.
Claude Code Ultraplan moves your planning to the cloud while your terminal stays free. Here is what it does, how to use it, and when it actually helps.
AutoDream cleans Claude Code's MEMORY.md between sessions. /dream runs it on demand. See what gets rewritten and how to turn it off.
How Claude Code Outcomes work, why a separate grading agent improves agent quality, and how to write a rubric that catches the failures you actually care about.
What Claude Code Routines are, how scheduled, API, and GitHub triggers work, and seven practical workflows you can copy into your own setup this week.
A plain-English comparison of Claude Code skills, MCP servers, subagents, and hooks. When to pick each, with a decision tree, code, and common confusion.
Build your first Claude Code skill. See the SKILL.md format, where skills live on disk, the YAML frontmatter fields, and how to test the skill.
A friendly, hands-picked list of the best MCP servers to use in 2026, with notes on what each one does, who it is for, and when it actually helps.
Hooks let Claude Code run small commands before and after it does things. This guide explains what they are, how to set them up, and the few mistakes to avoid.
A short and friendly walk through of building a Model Context Protocol server in Node.js. Plain code, no jargon, and the small mistakes to watch for.