A Claude Code plugin for testing AI interactions and pull requests from an attacker's point of view. A pull request is a proposed code change for review; the plugin systematically probes it for weaknesses and can coordinate fixes through GitHub.

Use its red-team commands to analyze staged changes, working changes, diffs, branches, or pull requests. Use its fix workflows to organize responses to the problems it finds.

It helps reveal unsafe, fragile, or duplicated behavior that ordinary review may miss, especially in systems that use language models.

red-agent — Plugin for Claude Code by abossenbroek: A Claude Code plugin for testing AI interactions and…

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 abossenbroek/abossenbroek-claude-plugins

agentmods

npx agentmods add plugins/abossenbroek/abossenbroek-claude-plugins/red-agent

Clone the repo

git clone --depth 1 https://github.com/abossenbroek/abossenbroek-claude-plugins

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.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/abossenbroek/abossenbroek-claude-plugins/red-agent.svg)](https://agentmods.dev/plugins/abossenbroek/abossenbroek-claude-plugins/red-agent)

Your own site

<a href="https://agentmods.dev/plugins/abossenbroek/abossenbroek-claude-plugins/red-agent"><img src="https://agentmods.dev/badge/plugins/abossenbroek/abossenbroek-claude-plugins/red-agent.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 2 skills, 7 commands, 5 agents cost 347 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

red-agent 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 5d 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.

red-agent/.claude-plugin/plugin.json · 39 lines

What it actually says

{
  "name": "red-agent",
  "version": "1.7.0",
  "description": "Adversarial red/rainbow team analysis plugin for Claude Code. Finds weaknesses in LLM interactions through systematic probing using a 10x10 attack taxonomy (11 categories for PR analysis including code-duplication). Includes automated fix orchestrator with GitHub integration.",
  "author": {
    "name": "Red Agent Team"
  },
  "commands": {
    "redteam": {
      "source": "./commands/redteam.md"
    },
    "redteam-w-fix": {
      "source": "./commands/red-team-w-fix.md"
    },
    "redteam-fix-orchestrator": {
      "source": "./commands/redteam-fix-orchestrator.md"
    },
    "redteam-pr:staged": {
      "source": "./commands/pr-redteam-staged.md"
    },
    "redteam-pr:working": {
      "source": "./commands/pr-redteam-working.md"
    },
    "redteam-pr:diff": {
      "source": "./commands/pr-redteam-diff.md"
    },
    "redteam-pr:branch": {
      "source": "./commands/pr-redteam-branch.md"
    }
  },
  "agents": [
    "./agents/red-team-coordinator.md",
    "./agents/fix-coordinator.md",
    "./agents/fix-orchestrator.md",
    "./agents/pal-availability-checker.md",
    "./agents/pr-analysis-coordinator.md"
  ]
}

Contents

What it installs

The manifest is a name and a version. 2 skills, 7 commands, 5 agents travel with it, and installing the plugin installs all of them — 347 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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.

5d ago First seen · 39 lines scan A 9bc52eb5af7c

Subscribe to this mod's changes

red-agent is a plugin published in the GitHub repository abossenbroek/abossenbroek-claude-plugins (2 stars, last pushed 4mo ago), licensed BSD-3-Clause. 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 2026-08-31.

Code review Security

red-agent

Getting it into your agent

Wrote this? Show the measurements

Grade A, and why

Nothing flagged

What it actually says

What it installs

What this file has done since we first saw it

Other plugins, from other repositories

nextjs

claude-plugins-official marketplace

humanizer

knowledge-work-plugins marketplace

ecc

container