red-team

red-team is a skill for Claude Code, Codex from docxology/codomyrmex. It costs 29 tokens per session (225 once invoked), scanned A, original, MIT.

A security and reliability review method that tests a design, implementation, agent workflow, or tool interface from an adversarial viewpoint.

In plain words
What is it for?
Use it to define trust boundaries, test likely abuse and failure paths, document evidence and risk, and check that mitigations work.
Why use it?
It helps find realistic ways that malformed input, excessive permissions, stale data, partial failures, or misleading results could cause harm.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

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.

agentmods
npx agentmods add skills/docxology/codomyrmex/red-team
Any agent
npx skills add docxology/codomyrmex --skill red-team
Clone the repo
git clone --depth 1 https://github.com/docxology/codomyrmex

Made for: Claude Code, Codex.

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/skills/docxology/codomyrmex/red-team.svg)](https://agentmods.dev/skills/docxology/codomyrmex/red-team)
Your own site
<a href="https://agentmods.dev/skills/docxology/codomyrmex/red-team"><img src="https://agentmods.dev/badge/skills/docxology/codomyrmex/red-team.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 225 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00029 $0.00225
Opus 5 $0.00015 $0.00112
Sonnet 5 $0.00006 $0.00045
Haiku 4.5 $0.00003 $0.00022

Measured 6d ago against content hash d12a49a11832, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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.

.agents/skills/red-team/SKILL.md · 17 lines

What it actually says

Red-Team Review

Use this skill for security, reliability, permission, prompt-injection, data-loss, or operational-risk review. Work only within the explicitly authorized repository and systems.

  1. Define the asset, trust boundaries, attacker or failure capabilities, and out-of-scope actions.
  2. Enumerate plausible abuse and failure paths, including malformed input, confused-deputy behavior, excessive permissions, stale state, partial failure, and misleading success signals.
  3. Exercise the highest-risk paths with the least invasive reproducible checks. Prefer real components and fixtures over mocks.
  4. For every finding, capture evidence, preconditions, impact, likelihood, severity, and a narrowly scoped mitigation.
  5. Re-test the mitigation and distinguish confirmed findings from hypotheses.

Report findings first, ordered by risk. Include “not exploitable under current scope” when a tempting path was checked and rejected. Never turn a red-team review into an unauthorized destructive action.

Files

What ships with it

2 files beside SKILL.md 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. 6d ago First seen · 17 lines · 29 tokens per session scan A d12a49a11832

Subscribe to this mod's changes

red-team is a skill published in the GitHub repository docxology/codomyrmex (11 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 225 once invoked, about $0.0001 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 2026-08-30.

Related

Other skills, from other repositories

implementation-final-review

Perform the repository's risk-tiered independent final review before implementation completion. Use only when explicitly invoked or when repository instructions require it after behavior-impacting implementation work; audit the complete task diff, supported contracts, lifecycle and security boundaries, complexity, and…

openai/openai-agents-python · 58 tokens

deploy-docker-compose

Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…

omnigent-ai/omnigent · 84 tokens

api-docs

Document a module or public API surface (functions, classes, CLI commands, endpoints) from the code itself. Use when the user asks for API reference, to document a module, or to write usage docs for a public interface.

omnigent-ai/omnigent · 50 tokens

benchmark-tune

Use this skill when running, debugging, interpreting, or documenting mesh-llm benchmark tune model-serving throughput trials, including choosing ctx/batch/ubatch/mmap/mlock/speculative-decoding sweeps, running benchmark tune on local or SSH hosts, collecting JSON evidence, and applying tolerance-aware recommendations.…

Mesh-LLM/mesh-llm · 106 tokens

deploy-windows

Use this skill when installing, deploying, launching, serving, or troubleshooting mesh-llm on a Windows machine — PowerShell install via install.ps1, flavor selection (CUDA/ROCm/Vulkan/CPU), source builds, the contrib helper scripts, and verifying it serves.

Mesh-LLM/mesh-llm · 60 tokens

research

Run deep research on any topic using the Deep Research MCP server. Use this skill whenever the user wants to research a topic, gather information, find sources, or create a research document. Triggers on: 'research this', 'find out about', 'gather information on', 'I need to understand', 'deep dive into', or any…

Arindam200/awesome-ai-apps · 78 tokens