Claude Code Agent Smith

Slash commands for Claude Code that analyze, validate, and optimize your configuration.

Requires Claude Code CLI — Run these commands inside a Claude Code session

What is Claude Code? Claude Code is Anthropic's official agentic coding CLI. Agent Smith adds slash commands that help you check and improve your Claude Code configuration.

What It Does

Agent Smith analyzes, validates, and fixes your Claude Code configuration in one interactive workflow:

• Analyze — Full 7-pillar evaluation with token metrics, instruction quality, and extension ratings
• Track — Score history with trend indicators and regression detection
• Triage — Interactive walkthrough of findings by effort level
• Fix — Apply accepted changes with an execution plan
• Create — Scaffold new configurations with best practices

Quick Start

# Add the marketplace (one-time)
claude plugin marketplace add maxencemeloni/claude-code-agent-smith

# Install the plugin
claude plugin install agent-smith

# Use (in any project)
cd your-project
claude
/analyze-agent

Update: claude plugin marketplace update agent-smith-marketplace && claude plugin update agent-smith@agent-smith-marketplace

Commands

/analyze-agent Workflow

1. Analyze — Validates structure, scores all 7 pillars, measures tokens, rates instructions and extensions
2. Save Report — Writes full report to AGENT_SMITH_REPORT.md
3. Triage — Pick a category: Quick Wins, Recommended, or Advanced
4. Decide — For each finding: Yes (apply) / No (skip) / Custom instruction
5. Execute — Review the execution plan, confirm, and apply all changes

Sample Output

/analyze-agent

# Agent Smith Analysis

**Project:** your-project
**Type:** Node.js
**Score:** 7.8/10

## Pillar Scores

| Pillar | Score | Notes |
|--------|:-----:|-------|
| Security Posture | 7/10 | Could add more deny rules |
| Instruction Clarity | 8/10 | Well-structured CLAUDE.md |
| Configuration Quality | 8/10 | Good structure |
| Context Efficiency | 6/10 | Missing .claudeignore patterns |
| Command & Extension Design | 9/10 | Clear, well-documented |
| Hook Safety | N/A | No hooks configured |
| MCP Integration | 7/10 | 3 servers configured |

## Content Overview

| Category | Files | Est. Tokens |
|----------|------:|------------:|
| Instructions | 1 | ~4,800 |
| Commands | 5 | ~8,600 |
| Agents | 6 | ~10,500 |
| **Total user content** | | **~23,900** |

## Limitations

This analysis covers user-configurable components only.
Claude Code's system prompt and tool schemas are outside this scope.

Interactive Triage

Which category do you want to address?
  A) Quick Wins     — 3 low-effort fixes
  B) Recommended    — 2 medium-effort improvements
  C) Advanced       — 1 high-effort optimization
  D) All categories — Walk through everything
  E) Done           — Just the report, no changes

After choosing, you walk through each item one by one and decide what to do. Then Agent Smith builds an execution plan and applies your choices.

See examples/reports/ for a full real-world report from Agent Smith's self-analysis, and examples/configs/ for starter configurations for Node.js, Python, and generic projects.

The 7 Evaluation Areas

What Issues It Finds

Honest About Limitations

This tool measures what you can control:

We provide real measurements with honest scope, not inflated claims.

Security: Deny Rules

Prevent Claude from reading sensitive files:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(./.env.*)",
      "Read(./secrets/)",
      "Read(./**/*.pem)",
      "Read(./**/*.key)",
      "Read(./**/*_rsa)"
    ]
  }
}

/create-agent includes these by default. /analyze-agent checks for missing rules.

Install

# 1. Add the marketplace (one-time)
claude plugin marketplace add maxencemeloni/claude-code-agent-smith

# 2. Install the plugin
claude plugin install agent-smith

Works on all platforms.

# Update (refresh marketplace first, then update)
claude plugin marketplace update agent-smith-marketplace
claude plugin update agent-smith@agent-smith-marketplace

# Uninstall
claude plugin uninstall agent-smith@agent-smith-marketplace

Upgrading from v1.x? The install script (install.sh/install.ps1) method was removed in v2.0. To migrate:

1. Run the old uninstall script: bash uninstall.sh (or .\uninstall.ps1 on Windows)
2. Install fresh using the plugin commands above

If you no longer have the uninstall script, manually delete the Agent Smith commands from ~/.claude/commands/ and the ~/.claude/agent-smith-repo file, then install the plugin.

Contributing

1. Fork the repo
2. Add/modify commands in commands/
3. Validate with claude plugin validate .
4. Submit a PR

See IMPROVEMENTS.md for the full changelog and the wiki Roadmap for planned features.

Development

When working on Agent Smith with Claude Code, the CLAUDE.md file at the project root provides development context including:

• Design principles — Honesty over hype, scope clarity, evidence required
• 7-pillar system — Rationale for each evaluation area
• Out of scope — What we explicitly don't measure (system prompt, model routing, etc.)
• Version management — How to bump versions and update documentation
• Repository structure — Where everything lives

This context is only loaded when developing Agent Smith itself, not when users run the commands in their projects.

Release Checklist

When releasing a new version:

Wiki

The GitHub Wiki is maintained as a separate repository. When making changes that affect documentation, update both the README and relevant wiki pages.

License

MIT

More Claude Code Plugins

Tools built by the same developer to enhance your Claude Code experience.

Check out Prompt Smith for more details

GitHub · Wiki · Website