redteam-fix-orchestrator

redteam-fix-orchestrator is a command for Claude Code from abossenbroek/abossenbroek-claude-plugins. It costs 9 tokens per session (2,986 once invoked), scanned A, original, BSD-3-Clause.

A command that coordinates fixes after a red-team security review. Red-team findings are identified weaknesses or problems found by deliberately testing a system like an attacker.

In plain words
What is it for?
Loading findings from a previous review or file, selecting or automatically applying fixes, and organizing fix execution with per-fix or per-phase commits.
Why use it?
It turns a list of findings into selected fix work and coordinates the stages needed to apply those changes. It can also run several independent fix phases at the same time within a chosen limit.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the AskUserQuestion tool; mentions Claude Code.

Part of the red-agent plugin — 2 skills, 7 commands shipped together

Good fit Loading findings from a previous review or file, selecting or automatically applying fixes, and organizing fix execution with per-fix or per-phase commits.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/abossenbroek/abossenbroek-claude-plugins/redteam-fix-orchestrator
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.

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

Made for: Claude Code.

Or install red-agent, the plugin that ships this one along with the rest of its 2 skills, 7 commands.

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 redteam-fix-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/commands/abossenbroek/abossenbroek-claude-plugins/redteam-fix-orchestrator/github.svg)](https://agentmods.dev/commands/abossenbroek/abossenbroek-claude-plugins/redteam-fix-orchestrator)
Your own site
<a href="https://agentmods.dev/commands/abossenbroek/abossenbroek-claude-plugins/redteam-fix-orchestrator"><img src="https://agentmods.dev/badge/commands/abossenbroek/abossenbroek-claude-plugins/redteam-fix-orchestrator/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for redteam-fix-orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/commands/abossenbroek/abossenbroek-claude-plugins/redteam-fix-orchestrator"><img src="https://agentmods.dev/badge/commands/abossenbroek/abossenbroek-claude-plugins/redteam-fix-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,986 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00009 $0.02986
Opus 5 $0.00005 $0.01493
Sonnet 5 $0.00002 $0.00597
Haiku 4.5 $0.00001 $0.00299

Measured 10d ago against content hash cb63c4fb60d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

redteam-fix-orchestrator 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 10d 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/commands/redteam-fix-orchestrator.md · 426 lines

How it starts

The opening of the file, as written. The whole thing — 426 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/redteam-fix-orchestrator Command

Red team analysis fix orchestration with automated execution. Takes findings from red team analysis, interactively selects fixes to apply (CLI mode) or auto-applies based on policy (GitHub hook mode), then orchestrates parallel fix execution through a 6-stage pipeline.

Usage

/redteam-fix-orchestrator [findings-source] [options]

Arguments

findings-source (optional):

  • last - Use findings from most recent /redteam run (default)
  • file:path - Load findings from YAML file at specified path

options (optional):

  • --auto - Force automated mode even in CLI (use default policy)
  • --max-parallel=N - Limit concurrent fix phases (default: 4)
  • --commit-strategy=per-fix|per-phase - Git commit granularity (default: per-fix)

Instructions

You are the entry point for red team fix orchestration. Your job is to:

  1. Check PAL MCP availability (optional enhancement)
  2. Detect execution mode (interactive CLI vs GitHub hook)
  3. Load findings from source
  4. Launch the fix-orchestrator agent
  5. Handle interactive fix selection (if CLI mode)
  6. Return execution summary

Step 1: Check PAL Availability (Non-Blocking)

Launch the pal-availability-checker agent to detect if PAL MCP is available:

Task: Launch pal-availability-checker agent
Agent: agents/pal-availability-checker.md
Prompt: Check if PAL MCP is available and list models

Parse the YAML result and extract pal_available: true/false.

This step is NON-BLOCKING - if PAL check fails or times out, continue with pal_available: false. PAL is optional enhancement, not required.

Step 2: Detect Execution Mode

Check the CLAUDE_CODE_REMOTE environment variable to determine execution mode:

Interactive CLI Mode:

  • CLAUDE_CODE_REMOTE is unset or empty
  • Use AskUserQuestion for fix selection
  • Return implementation summary

GitHub Hook Mode:

  • CLAUDE_CODE_REMOTE equals "true"
  • Load policy from .claude/fix-policy.yaml
  • Auto-select fixes based on policy
  • Return summary formatted for PR comment
  • CRITICAL: Create local commits only, do NOT push to remote

Read the full file on GitHub · 426 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. 10d ago First seen · 426 lines · 9 tokens per session scan A cb63c4fb60d8

Subscribe to this mod's changes

redteam-fix-orchestrator is a command published in the GitHub repository abossenbroek/abossenbroek-claude-plugins (2 stars, last pushed 4mo ago), licensed BSD-3-Clause. It adds 9 tokens to every session and 2,986 once invoked, about $0.0000 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 2026-08-31.