qa-devil

An edge-case testing agent that looks for scenarios likely to break or behave unexpectedly.

In plain words
What is it for?
Use it to challenge an implementation with unusual inputs and failure scenarios. It is included only in the eight-agent preset.
Why use it?
It helps expose failures that ordinary, expected-use testing may miss.

Agent

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/kingkingburger/plugin-mh/qa-devil
Clone the repo
git clone --depth 1 https://github.com/kingkingburger/plugin-mh
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 368 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00036 $0.00368
Opus 5 $0.00018 $0.00184
Sonnet 5 $0.00007 $0.00074
Haiku 4.5 $0.00004 $0.00037

Measured yesterday against content hash cb39380275c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qa-devil 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 yesterday.

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.

skills/agent-arena/agents/qa-devil.md · 35 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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. yesterday First seen · 35 lines · 36 tokens per session scan A cb39380275c5

Subscribe to this mod's changes

qa-devil is an agent published in the GitHub repository kingkingburger/plugin-mh (1 stars, last pushed 7d ago), with no licence file. It adds 36 tokens to every session and 368 once invoked, about $0.0002 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.