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/HomenShum/NodeBenchAIWrote 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/homenshum/nodebenchai/nodebench-auto-qa)<a href="https://agentmods.dev/rules/homenshum/nodebenchai/nodebench-auto-qa"><img src="https://agentmods.dev/badge/rules/homenshum/nodebenchai/nodebench-auto-qa/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/homenshum/nodebenchai/nodebench-auto-qa"><img src="https://agentmods.dev/badge/rules/homenshum/nodebenchai/nodebench-auto-qa.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 | $0.00000 | $0.00297 |
| Opus 5.5 | $0.00000 | $0.00119 |
| Sonnet 5.5 | $0.00000 | $0.00059 |
| Haiku 4.5 | $0.00000 | $0.00030 |
Grade A, and why
nodebench-auto-qa 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
NodeBench: Auto-QA After Code Changes
After ANY implementation change (new feature, bug fix, refactor, style change), automatically run QA checks.
Auto-trigger conditions
This rule activates after:
- Creating or modifying source files (.ts, .tsx, .css, .html)
- Completing a todo item or multi-step plan
- Before any git commit touching 3+ files
Quick QA sequence
- Build check: Run TypeScript compiler — must be 0 errors
- Test check: Run test suite — must be 0 failures
- Quality gate: Call
run_quality_gate()if NodeBench MCP is connected - Visual check: Call
capture_responsive_suite()for UI changes
Deeper QA with NodeBench MCP
If NodeBench MCP is connected, use these tools:
site_map({ url: '<dev-server>' })— crawl all pages, check for errorsdiff_crawl({ url: '<dev-server>' })— compare against baselinesuggest_tests({ session_id: '<from site_map>' })— generate test casescompare_savings()— track improvement metrics
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 · 32 lines · 0 tokens per session scan A ec161a40a230
nodebench-auto-qa is a cursor rule published in the GitHub repository HomenShum/NodeBenchAI (15 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 297 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 2026-09-03.
Other cursor rules, from other repositories
running-tests
How to run tests, check for failures, and rerun specific failing tests — use the :agent variants of slow commands.
hatch3r-testing
Coverage thresholds, mocking strategy, property-based testing, mutation-score targets, flaky test quarantine, and snapshot test discipline.
test-engineer
Test Engineer agent.
300-testing
Comprehensive testing guide covering unit, integration, E2E, test frameworks, patterns, and CI/CD integration.
testing
Cursor rule "testing" from andersonlemesc/Oryntra, covering testes oryntra, laravel (pest), python (pytest), contract tests (laravel ↔ python) and browser/e2e.
tester
Tester role - Unit, E2E, and visual regression testing.