qa-agents

An internal research document about testing software with AI agents, focused on a Mac app called MacParakeet. It discusses how existing AI quality-assurance tools may not fit this app’s macOS design.

In plain words
What is it for?
Use it as background when evaluating quality-assurance agents for MacParakeet; the description does not specify an executable testing feature.
Why use it?
It helps track the gap between general AI testing tools and the app’s specific desktop, keyboard, microphone, and screen-recording behavior.

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/moona3k/macparakeet/qa-agents
Clone the repo
git clone --depth 1 https://github.com/moona3k/macparakeet
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 2,571 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 $0.00000 $0.02571
Opus 5 $0.00000 $0.01286
Sonnet 5 $0.00000 $0.00514
Haiku 4.5 $0.00000 $0.00257

Measured 2d ago against content hash 0a24b15b3c42, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qa-agents 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 2d 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.

docs/agents/qa-agents.md · 144 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. 2d ago First seen · 144 lines · 0 tokens per session scan A 0a24b15b3c42

Subscribe to this mod's changes

qa-agents is an agent published in the GitHub repository moona3k/macparakeet (610 stars, last pushed 5d ago), with no licence file. It costs nothing until one of its globs matches a file; then it loads 2,571 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.

Related

Other agents, from other repositories

collaboration

How coding agents (Claude Code, Codex, or any future harness) collaborate on this repo: who orchestrates, who implements, who reviews, and what each layer may touch. This is the map; the skills own the mechanics — never restate a skill's commands here or anywhere else (single owner per fact).

open-software-network/os-clovy · 0 tokens

domain

How the engineering skills should consume this repo's domain documentation.

open-software-network/os-clovy · 0 tokens

issue-tracker

Issues for this repo live on the Open Software platform (os-platform), org june — NOT GitHub Issues. GitHub Issues exist on the repo but are a legacy/watchdog surface, not the triage queue.

open-software-network/os-clovy · 0 tokens

triage-labels

The skills speak in terms of five canonical triage roles. os-platform Issues have both statuses and labels; this repo maps roles across both axes.

open-software-network/os-clovy · 0 tokens

flow-verifier

Runs the VZT Flow end-to-end verification ladder (build, tests, TTS-transcribe checks, clean-test latency, paste-test, daemon socket checks, overlay states) and reports real measured numbers — never estimates. Use before claiming a change works, before a release, or when asked to verify VZT Flow.

vonzelle-vzt/vzt-flow · 68 tokens

flow-feature-builder

Implements VZT Flow features observing this repo's boundaries — additive edits, the gotcha list from CLAUDE.md, pull-rebase discipline in a shared worktree, never touching the user's running daily-driver app without relaunching it. Use for routine feature/bugfix work in this repo.

vonzelle-vzt/vzt-flow · 65 tokens