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 agentmods add rules/virtuslab-open-source/strapi-plugin-mcp/gwt-testsgit clone --depth 1 https://github.com/VirtusLab-Open-Source/strapi-plugin-mcpWhat 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 | $0.00202 | $0.00202 |
| Opus 5 | $0.00101 | $0.00101 |
| Sonnet 5 | $0.00040 | $0.00040 |
| Haiku 4.5 | $0.00020 | $0.00020 |
Grade A, and why
gwt-tests 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.
What it actually says
Title: Given/When/Then test convention
Scope: tests (**/*.test.ts, **/*.spec.ts)
Rule:
- Each test block must clearly separate three phases with comments:
// Givenfor setup// Whenfor exercising the system under test// Thenfor assertions
Guidance:
- Prefer one assertion group under the
// Thensection. - Keep setup minimal; use factories/helpers for noisy data.
- Name tests in behavior terms, not implementation details.
Examples:
Bad:
it('does X', () => {
const a = 1; doSomething(a);
expect(result).toBe(1);
});
Good:
it('does X', () => {
// Given
const a = 1;
// When
const result = doSomething(a);
// Then
expect(result).toBe(1);
});
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.
- 2d ago First seen · 40 lines · 202 tokens per session scan A 87f36c51cc4c
gwt-tests is a cursor rule published in the GitHub repository VirtusLab-Open-Source/strapi-plugin-mcp (3 stars, last pushed 6mo ago), licensed MIT. It adds 202 tokens to every session, about $0.0010 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.
Other cursor rules, from other repositories
astro-strapi-starter
Astro x Strapi starter — layout, content collections, block renderer vs StrapiBlocks, types.
tailwind-shadcn
Tailwind CSS 4 + shadcn-style UI — global.css, components.json, cn(), Astro + React.
astro-strapi-blocks
Astro + Strapi Blocks — StrapiBlocks, data, theme (extend/overwrite), custom blocks.
astro-strapi-loader
Strapi 5 + @sensinum/astro-strapi-loader — content.config.ts, populate, qs, locales.
test-architect
Test Architect agent (Murat).
api-property-optionality-hygiene
Fix ApiProperty/ApiPropertyOptional optionality mismatches in DTO files; use for scheduled batch fixes or DTO edits.