agentdev

agentdev is a plugin for Claude Code from MadAppGang/claude-code. Its manifest loads nothing; the 5 skills, 5 commands, 3 agents it bundles cost 381 tokens per session together, scanned A, original, MIT.

A toolkit for creating, implementing, and reviewing Claude Code agents and commands. It also validates them with multiple AI models, records model performance, and keeps session-specific work separate.

In plain words
What is it for?
It is for building agent definitions and commands, reviewing their quality, validating them across models, tracking performance, and recording sessions.
Why use it?
It helps agent builders test their designs, compare results, and keep generated artifacts organized by session.

Plugin 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.

Claude Code
/plugin marketplace add MadAppGang/claude-code
agentmods
npx agentmods add plugins/madappgang/claude-code/agentdev
Clone the repo
git clone --depth 1 https://github.com/MadAppGang/claude-code

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for agentdev

README.md
[![agentmods](https://agentmods.dev/badge/plugins/madappgang/claude-code/agentdev.svg)](https://agentmods.dev/plugins/madappgang/claude-code/agentdev)
Your own site
<a href="https://agentmods.dev/plugins/madappgang/claude-code/agentdev"><img src="https://agentmods.dev/badge/plugins/madappgang/claude-code/agentdev.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 5 skills, 5 commands, 3 agents cost 381 tokens a session between them.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

agentdev 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 yesterday.

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.

.claude-plugin/marketplace.json#agentdev · 25 lines

What it actually says

{
  "name": "agentdev",
  "source": "./plugins/agentdev",
  "description": "Create, implement, and review Claude Code agents and commands with multi-model validation, LLM performance tracking, and session-based artifact isolation. v1.5.2: Updated for claudish v4.5.1 (--agent flag removed).",
  "version": "1.5.2",
  "author": {
    "name": "Jack Rudenko",
    "email": "[email protected]",
    "company": "MadAppGang"
  },
  "category": "development",
  "keywords": [
    "agents",
    "commands",
    "development",
    "multi-model",
    "claudish",
    "quality-review",
    "xml-standards",
    "orchestration",
    "debug-mode",
    "session-recording"
  ],
  "strict": true
}
Files

What ships with it

1 file beside marketplace.json#agentdev in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. yesterday First seen · 25 lines scan A 1826f99d7c53

Subscribe to this mod's changes

agentdev is a plugin published in the GitHub repository MadAppGang/claude-code (279 stars, last pushed 5mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-03.