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.
git clone --depth 1 https://github.com/Ardaka/cursor-mcp-qa-agentWrote 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/rules/ardaka/cursor-mcp-qa-agent/qa-agent)<a href="https://agentmods.dev/rules/ardaka/cursor-mcp-qa-agent/qa-agent"><img src="https://agentmods.dev/badge/rules/ardaka/cursor-mcp-qa-agent/qa-agent/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/rules/ardaka/cursor-mcp-qa-agent/qa-agent"><img src="https://agentmods.dev/badge/rules/ardaka/cursor-mcp-qa-agent/qa-agent.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 | $0.00149 | $0.00149 |
| Opus 5.5 | $0.00060 | $0.00060 |
| Sonnet 5.5 | $0.00030 | $0.00030 |
| Haiku 4.5 | $0.00015 | $0.00015 |
Grade A, and why
qa-agent 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 1mo 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.
What it actually says
QA agent workflow
- Start feature reviews by calling
analyze_user_story. - Separate stated requirements, assumptions, and open questions.
- Prioritize by product risk: customer impact × likelihood.
- Prefer a small set of valuable tests over exhaustive permutations.
- Use
create_test_charterfor uncertain or high-risk behavior. - Call
draft_bug_reportonly after the behavior has been reproduced. - Never invent logs, screenshots, environments, severity, or reproduction evidence.
- Mark AI output as a draft until a human confirms it.
- Do not expose secrets, access tokens, customer data, or production identifiers.
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.
- 1mo ago First seen · 18 lines · 149 tokens per session scan A 1765dbd1e867
qa-agent is a cursor rule published in the GitHub repository Ardaka/cursor-mcp-qa-agent (0 stars, last pushed 2mo ago), licensed MIT. It adds 149 tokens to every session, about $0.0006 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.
Other cursor rules, from other repositories
qualitymax-qa
Verify relevant web changes with QualityMax before completion.
bdd-specs
Executable Gherkin specifications, layout, style, tags, offline by construction.
workflow
BDD delivery order, Gherkin spec before tests before code, definition of done, Rules Sync.
testing
Vitest conventions and the mandatory unit-test set.
python-code-validator
Validate generated Python at every step, not once at the end.
testing
Testpflicht für nicht-trivialen Code.