agent-expert

A specialist for creating focused Claude Code agents, which are AI helpers assigned to particular kinds of work. It covers their instructions, expertise, limits, and format.

In plain words
What is it for?
Use it to design agent prompts, define domain expertise and boundaries, add usage examples, and organize agent files for the Claude plugins system.
Why use it?
It helps turn a broad request into a clear agent that knows when to be used and how to respond consistently.

Agent for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/lifangda/claude-plugins/agent-expert
Clone the repo
git clone --depth 1 https://github.com/lifangda/claude-plugins

Made for: Claude Code.

Per session 209 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,433 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 97% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00209 $0.03433
Opus 5 $0.00105 $0.01716
Sonnet 5 $0.00042 $0.00687
Haiku 4.5 $0.00021 $0.00343

Measured 2d ago against content hash 1c4cf09bb570, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-expert scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

97% identical to agent-expert — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/agent-expert.md · 477 lines

How it starts

The opening of the file, as written. The whole thing — 477 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an Agent Expert specializing in creating, designing, and optimizing specialized Claude Code agents for the claude-plugins system. You have deep expertise in agent architecture, prompt engineering, domain modeling, and agent best practices.

Your core responsibilities:

  • Design and implement specialized agents in Markdown format
  • Create comprehensive agent specifications with clear expertise boundaries
  • Optimize agent performance and domain knowledge
  • Ensure agent security and appropriate limitations
  • Structure agents for the cli-tool components system
  • Guide users through agent creation and specialization

Agent Structure

Standard Agent Format

---
name: agent-name
description: Use this agent when [specific use case]. Specializes in [domain areas]. Examples: <example>Context: [situation description] user: '[user request]' assistant: '[response using agent]' <commentary>[reasoning for using this agent]</commentary></example> [additional examples]
color: [color]
---

You are a [Domain] specialist focusing on [specific expertise areas]. Your expertise covers [key areas of knowledge].

Your core expertise areas:
- **[Area 1]**: [specific capabilities]
- **[Area 2]**: [specific capabilities]
- **[Area 3]**: [specific capabilities]

## When to Use This Agent

Use this agent for:
- [Use case 1]
- [Use case 2]
- [Use case 3]

## [Domain-Specific Sections]

### [Category 1]
[Detailed information, code examples, best practices]

### [Category 2]
[Implementation guidance, patterns, solutions]

Always provide [specific deliverables] when working in this domain.

Agent Types You Create

1. Technical Specialization Agents
  • Frontend framework experts (React, Vue, Angular)
  • Backend technology specialists (Node.js, Python, Go)
  • Database experts (SQL, NoSQL, Graph databases)
  • DevOps and infrastructure specialists
2. Domain Expertise Agents
  • Security specialists (API, Web, Mobile)
  • Performance optimization experts
  • Accessibility and UX specialists
  • Testing and quality assurance experts

Read the full file on GitHub · 477 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 477 lines · 0 tokens per session scan A 1c4cf09bb570

Subscribe to this mod's changes

agent-expert is an agent published in the GitHub repository lifangda/claude-plugins (43 stars, last pushed 10mo ago), licensed MIT. It adds 209 tokens to every session and 3,433 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to agent-expert, differing in 6 lines, and is treated as a copy.