red-team

red-team is a command for Claude Code from MaxwellCalkin/sentinel-ai. It costs 0 tokens per session (200 once invoked), scanned A, original, Apache-2.0.

A command for testing whether a safety scanner can recognize altered versions of a prompt-injection attempt.

In plain words
What is it for?
It helps generate adversarial test cases and report which variants the scanner detected or missed.
Why use it?
It reveals which changes to wording, characters, or payload structure might evade detection.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Part of the sentinel-ai plugin — 1 skill, 5 commands, 1 MCP server shipped together

Good fit It helps generate adversarial test cases and report which variants the scanner detected or missed.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/maxwellcalkin/sentinel-ai/red-team
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/MaxwellCalkin/sentinel-ai

Made for: Claude Code.

Or install sentinel-ai, the plugin that ships this one along with the rest of its 1 skill, 5 commands, 1 MCP server.

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 red-team

README.md
[![agentmods](https://agentmods.dev/badge/commands/maxwellcalkin/sentinel-ai/red-team/github.svg)](https://agentmods.dev/commands/maxwellcalkin/sentinel-ai/red-team)
Your own site
<a href="https://agentmods.dev/commands/maxwellcalkin/sentinel-ai/red-team"><img src="https://agentmods.dev/badge/commands/maxwellcalkin/sentinel-ai/red-team/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 red-team

Your own site · 80×15
<a href="https://agentmods.dev/commands/maxwellcalkin/sentinel-ai/red-team"><img src="https://agentmods.dev/badge/commands/maxwellcalkin/sentinel-ai/red-team.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 200 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 $0.00000 $0.00200
Opus 5 $0.00000 $0.00100
Sonnet 5 $0.00000 $0.00040
Haiku 4.5 $0.00000 $0.00020

Measured 9d ago against content hash 2221725d81b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

red-team 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 9d 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.

commands/red-team.md · 28 lines

What it actually says

/red-team — Test safety scanning robustness

Red-team your safety scanning by generating adversarial variants of a prompt injection attempt.

Usage

/red-team

Behavior

Use the Sentinel AI test_robustness MCP tool to:

  1. Take the provided text (a known injection attempt)
  2. Generate adversarial variants using 10+ evasion techniques (homoglyphs, zero-width characters, leetspeak, payload splitting, synonym substitution, etc.)
  3. Test whether each variant is still detected by the safety scanner
  4. Report the detection rate, total variants tested, and any variants that evaded detection

Present results showing:

  • Overall detection rate (e.g., 95%)
  • Number of variants tested vs detected
  • List of evasion techniques used
  • Any variants that evaded detection (with the technique used)

This helps identify weaknesses in safety scanning before they can be exploited.

Input

$ARGUMENTS

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. 9d ago First seen · 28 lines · 0 tokens per session scan A 2221725d81b8

Subscribe to this mod's changes

red-team is a command published in the GitHub repository MaxwellCalkin/sentinel-ai (24 stars, last pushed 6mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 200 tokens. 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.