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.
npx skills add dangnhit/qa-tester --skill qa-skills-setupgit clone --depth 1 https://github.com/dangnhit/qa-testerWrote 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.
[](https://agentmods.dev/skills/dangnhit/qa-tester/qa-skills-setup)<a href="https://agentmods.dev/skills/dangnhit/qa-tester/qa-skills-setup"><img src="https://agentmods.dev/badge/skills/dangnhit/qa-tester/qa-skills-setup/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.
<a href="https://agentmods.dev/skills/dangnhit/qa-tester/qa-skills-setup"><img src="https://agentmods.dev/badge/skills/dangnhit/qa-tester/qa-skills-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00059 | $0.01348 |
| Opus 5.5 | $0.00024 | $0.00539 |
| Sonnet 5.5 | $0.00012 | $0.00270 |
| Haiku 4.5 | $0.00006 | $0.00135 |
Grade A, and why
qa-skills-setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Skills setup
This skill installs a runtime, not skills of its own. The eight QA skills — qa-tester,
requirement-analyzer, testcase-designer, test-data-manager, browser-test-executor,
evidence-collector, bug-reporter, qa-report-generator — are written into the project by
qa-skill skills install, checksummed, and bound to the exact runtime binary that wrote them
(ADR-0011). This plugin carries no copy of them: a second copy could not be checked by
qa-skill skills verify and would drift from the canonical bundle silently.
Run the four steps below in order. Stop at the first one that does not succeed and report what it said — do not work around a refusal, and do not continue to the next step on a non-zero exit.
1. Resolve the runtime
In this exact order: ./node_modules/.bin/qa-skill, then qa-skill on PATH.
QA_SKILL="${PWD}/node_modules/.bin/qa-skill"; [ -x "$QA_SKILL" ] || QA_SKILL="$(command -v qa-skill)" || exit 1
PowerShell:
$QaSkill = Join-Path $PWD "node_modules/.bin/qa-skill.cmd"
if (-not (Test-Path $QaSkill)) { $QaSkill = (Get-Command qa-skill -ErrorAction Stop).Source }
Never use npx against a remote registry, a globally cached binary of unknown origin, or any
substitute runtime. The QA Runtime's guarantees rest on the caller having reviewed the exact binary
that executes the run.
If neither path resolves, stop and give the user this setup, then wait — do not install packages on their behalf:
npm install --save-dev @gwinnguyen/qa-skills
npx playwright install chromium
Node.js 22 or 24 is required. Chromium must be installed at setup time; QA execution never downloads a browser or a package implicitly.
2. Verify the runtime version range
"$QA_SKILL" runtime verify --range ">=1.0.0 <2.0.0"
Prints JSON with executable, version, range, compatible. If compatible is false, the
installed package does not satisfy the v1 contract — report the printed version and stop. Do not
widen the range to make it pass.
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.
- 2mo ago First seen · 118 lines · 59 tokens per session scan A d484f5fddd66
qa-skills-setup is a skill published in the GitHub repository dangnhit/qa-tester (3 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 59 tokens to every session and 1,348 once invoked, about $0.0002 per session on Opus 5.5. 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.
qa-skills-setup compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| qa-skills-setupdangnhit/qa-tester | Skill | 3 | 3mo ago | Apache-2.0 | A | 59 | Claude Code |
| qawolf-cliqawolf/cli | Skill | 3.5k | today | Apache-2.0 | C | 112 | Claude Code, Codex |
| test-reviewakovalion/paranoid-qa | Skill | 16 | 11d ago | MIT | A | 137 | Claude Code |
| bug-reportakovalion/paranoid-qa | Skill | 16 | 11d ago | MIT | A | 41 | Claude Code |
| interviewakovalion/paranoid-qa | Skill | 16 | 11d ago | MIT | A | 52 | Claude Code |
| playwright-expertpersonamanagmentlayer/pcl | Skill | 45 | 18d ago | Apache-2.0 | A | 77 | Claude Code |
| argus-testchriswu727/argus | Skill | 6 | yesterday | MIT | A | 45 | Claude Code, Codex |