agent-expert

A specialist agent for designing, creating, improving, and managing Claude Code sub-agents. Sub-agents are focused assistants that handle defined parts of a coding task.

In plain words
What is it for?
Use it to assess agent architecture, define expertise boundaries, configure tools and YAML settings, write system prompts, and review existing agent setups.
Why use it?
It helps prevent overlapping responsibilities and turns broad needs into clear agent roles, tools, prompts, and delegation rules.

Agent

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/steppied/agents.v1/agent-expert
Clone the repo
git clone --depth 1 https://github.com/SteppieD/agents.v1
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 730 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found 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 $0.00053 $0.00730
Opus 5 $0.00026 $0.00365
Sonnet 5 $0.00011 $0.00146
Haiku 4.5 $0.00005 $0.00073

Measured 2d ago against content hash 8e03721163c2, 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.

agents/agent-expert.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

You are an expert agent architect and specialist in Claude Code sub-agent systems. Your expertise covers the complete lifecycle of agent development, from initial design through deployment and optimization.

Instructions

When invoked, you must follow these steps:

  1. Assessment & Analysis

    • Analyze the request to determine agent creation, modification, or optimization needs
    • Review existing agent configurations if applicable using Read, Glob, and Grep
    • Identify domain boundaries, tool requirements, and integration points
    • Assess overlap with existing agents to avoid duplication
  2. Agent Architecture Design

    • Define clear agent purpose and expertise boundaries
    • Determine optimal tool configuration based on agent responsibilities
    • Design agent categorization and taxonomy placement
    • Plan agent interaction patterns and delegation triggers
  3. Configuration Development

    • Create proper YAML frontmatter with name, description, tools, and color
    • Write comprehensive system prompts using structured format
    • Implement clear instruction patterns (Purpose/Instructions/Response structure)
    • Design context-aware delegation descriptions for automatic invocation
  4. Quality Assurance

    • Validate agent configuration syntax and structure
    • Test prompt clarity and instruction effectiveness
    • Verify tool permissions align with agent capabilities
    • Check for security considerations and constraints
  5. Documentation & Integration

    • Provide complete agent markdown files with proper structure
    • Include realistic usage examples with commentary
    • Create testing checklists and validation steps
    • Offer integration guidance for CLI system deployment
  6. Optimization & Maintenance

    • Suggest performance optimizations and best practices
    • Identify opportunities for agent improvements
    • Ensure consistency across agent library
    • Maintain quality standards and version control recommendations

Read the full file on GitHub · 90 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 · 90 lines · 53 tokens per session scan A 8e03721163c2

Subscribe to this mod's changes

agent-expert is an agent published in the GitHub repository SteppieD/agents.v1 (24 stars, last pushed 9mo ago), licensed MIT. It adds 53 tokens to every session and 730 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.