adversarial-qa

adversarial-qa is an agent for coding agents from cunhaax/ai-workflow. It costs 72 tokens per session (533 once invoked), scanned A, original, MIT.

An exploratory quality-assurance agent that tests a completed feature through its user interface, application programming interface, or both.

In plain words
What is it for?
It helps probe running web features with browser automation or command-line requests after code review and committed tests.
Why use it?
It looks for unexpected behavior and edge cases that planned tests may not cover.

Agent

Part of the ai-workflow plugin — 8 skills, 4 agents, 2 MCP servers shipped together

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 agents/cunhaax/ai-workflow/adversarial-qa
Clone the repo
git clone --depth 1 https://github.com/cunhaax/ai-workflow

Or install ai-workflow, the plugin that ships this one along with the rest of its 8 skills, 4 agents, 2 MCP servers.

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 adversarial-qa

README.md
[![agentmods](https://agentmods.dev/badge/agents/cunhaax/ai-workflow/adversarial-qa.svg)](https://agentmods.dev/agents/cunhaax/ai-workflow/adversarial-qa)
Your own site
<a href="https://agentmods.dev/agents/cunhaax/ai-workflow/adversarial-qa"><img src="https://agentmods.dev/badge/agents/cunhaax/ai-workflow/adversarial-qa.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 533 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00072 $0.00533
Opus 5 $0.00036 $0.00267
Sonnet 5 $0.00014 $0.00107
Haiku 4.5 $0.00007 $0.00053

Measured 5d ago against content hash 881cbe3acd4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

adversarial-qa scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

description: "Runs an exploratory, adversarial pass over a feature after the code-critic passes, through whichever surface(s) it exposes (UI via Playwright, API via curl/Bash). Probes beyond the plan and committed tests
plugins/ai-workflow/agents/adversarial-qa.md · 25 lines

What it actually says

Adversarial QA Agent

You are a QA engineer running an exploratory, adversarial pass over a feature in the running app.

Your job is NOT to review code quality (the code-critic handles that) and NOT to re-verify the spec — the committed end-to-end tests and the code-critic already lock that down. Your job is to go beyond them: exercise the feature through whichever surface(s) it exposes — UI, API, or both — and surface anything that looks wrong, confusing, or likely to bite a real user.

Validation

Apply the /adversarial-qa skill to run the exploratory probe.

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. 5d ago First seen · 25 lines · 72 tokens per session scan A 881cbe3acd4e

Subscribe to this mod's changes

adversarial-qa is an agent published in the GitHub repository cunhaax/ai-workflow (5 stars, last pushed 8d ago), licensed MIT. It adds 72 tokens to every session and 533 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.