Skip to main content
affpapa.org
RU EN
subagent

agent-expert — Claude Code subagent: what it does, how to install

A subagent that helps you design other Claude agents: structure, expertise boundaries, prompts and examples.

Install into Claude Code · claude-code-templates All methods and platforms ↓ 
npx claude-code-templates@latest --agent expert-advisors/agent-expert
Open on GitHub

What agent-expert does

agent-expert is a Claude subagent for building specialized agents. It works through the domain, sets expertise boundaries, drafts a description with examples, and lays it all out as a Markdown file in the claude-code-templates format.

Inside you get templates for several agent types: technical specializations (frameworks, databases, infrastructure), domain experts (security, performance, testing), industry agents, and workflow ones like code review or architecture design. Prompt engineering gets its own treatment: how to describe competency areas, how to write examples with context, and how to state limitations so an agent stays out of someone else's lane.

It earns its place when you maintain a set of agents and want them to stop overlapping. Creation starts with domain analysis. Without a clear idea of what the agent handles and what it doesn't, there's nothing to fill the template with. The source text is truncated, so check the agent file itself for the full list of sections and format requirements.

What it helps with

  • write a new Claude agent in Markdown in the right format
  • split expertise areas between several agents
  • find examples with context for an agent description
  • state limitations so an agent stays inside its domain
  • pick the right agent type: technical, domain or workflow

Example prompts for the agent

  • Help me create an agent for React performance optimization
  • Design an agent that covers both frontend and backend security
  • Review my agent description and point out where the expertise boundaries blur

How to install agent-expert

1claude-code-templates

npx claude-code-templates@latest --agent expert-advisors/agent-expert

2Manually: put the files in place

.claude/agents/agent-expert.md

For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about agent-expert

How do I install agent-expert in Claude?

Through the templates: npx claude-code-templates@latest --agent expert-advisors/agent-expert. The agent file then lands at .claude/agents/agent-expert.md.

What does agent-expert do?

It helps you create and design specialized Claude agents: domain analysis, structure, examples and limitations, all written into a Markdown file.

How is agent-expert different from a regular agent?

It works on the agents themselves rather than your project code: descriptions, prompts and expertise boundaries. It's for people maintaining an agent set in claude-code-templates.

Similar subagents

All subagents for Agent setup: memory, context, orchestration →
h3-prompt-writing MiniMax-AI Transforms multimodal video generation requests into MiniMax H3 prompts. It structures base keyframe transitions and full-reference rewrites. CX Codex +1 11,600installs asd-ste100 danyuchn Rewrites tool descriptions, system prompts, and agent instructions under ASD-STE100 rules. It eliminates ambiguity before downstream models parse the text. CX Codex +1 7,400installs skill-creator official openai Official guide for drafting and updating agent skills. It structures procedures, bundled scripts, and documentation while keeping token overhead low. CX Codex +1 4,900installs prompt-master nidhinjs This skill writes and improves prompts for a named AI tool. Use it when a rough request needs to become a ready-to-paste prompt for Claude Code, Cursor, or another supported tool. CX Codex +1 4,000installs ralph-plan mastra-ai An interactive planning skill for Claude Code and coding agents. It helps build structured ralph-loop commands through guided dialog and codebase exploration. CX Codex +1 2,600installs senior-prompt-engineer Alireza Rezvani Skill for systematic prompt optimization via eval sets, RAG quality measurement, and agent validation. Works with any model, uses only stdlib Python. 970installs

From the same set205

The whole set →
project-supervisor-orchestrator A subagent that runs a chain of other agents step by step and returns the result as JSON. Useful when one request has to pass through several specialized agents. 1,563installs competitive-intelligence-analyst A Claude subagent that gathers competitor and market data: company profiles, SWOT, industry trends. Useful before a product launch or when shaping strategy. 1,561installs flow-status Shows which Git Flow branch you are on, how far it has drifted from remote, and where it will merge. 1,514installs web-accessibility-checker A subagent that checks markup against WCAG, reviews HTML semantics and keyboard access, and returns a report listing violations. 1,438installs format-python-files This hook runs black on every .py file Claude edits. Formatting stops being a separate step you remember to do. 1,405installs supabase-schema-sync Synchronizes local database files with a remote Supabase project via MCP. It detects structural differences and generates migration scripts. 1,405installs init-project Scaffolds a new project: folders, git, linters, tests and CI. Useful when you want a clean start instead of wiring everything by hand. 1,382installs backup-before-edit A Claude hook that copies a file with a timestamp before every edit. Useful when the agent rewrites code and you want a way back. 1,328installs

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor