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/pr-pm/prpm/test-skillgit clone --depth 1 https://github.com/pr-pm/prpmWrote 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/pr-pm/prpm/test-skill)<a href="https://agentmods.dev/rules/pr-pm/prpm/test-skill"><img src="https://agentmods.dev/badge/rules/pr-pm/prpm/test-skill.svg" alt="Measured on agentmods" 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 | $0.00009 | $0.00496 |
| Opus 5 | $0.00005 | $0.00248 |
| Sonnet 5 | $0.00002 | $0.00099 |
| Haiku 4.5 | $0.00001 | $0.00050 |
Grade A, and why
test-skill 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
Test Skill
Overview
This is a comprehensive test skill for validating format conversion between Claude Skills and Cursor Rules.
Core Principles
- Write clean, maintainable code
- Test thoroughly before deploying
- Document your work clearly
- Follow established patterns
Workflow
-
Understand Requirements
- Read the task description carefully
- Identify all constraints and dependencies
- Ask clarifying questions if needed
-
Plan Implementation
- Break down the task into steps
- Identify potential challenges
- Consider edge cases
-
Write Code
- Follow coding standards
- Keep functions small and focused
- Use meaningful variable names
-
Test Thoroughly
- Write unit tests
- Run integration tests
- Verify edge cases
-
Document Solution
- Add code comments
- Update README if needed
- Document any gotchas
Best Practices
- Version Control: Commit often with clear messages
- Code Review: Always get feedback before merging
- Refactoring: Improve code structure continuously
- Learning: Stay updated with best practices
Integration
This skill works well with:
- Systematic debugging approaches
- Test-driven development
- Code review practices
Examples
Good Code Pattern
function calculateTotal(items: Item[]): number {
return items.reduce((sum, item) => sum + item.price, 0);
}
Bad Code Pattern (Avoid)
function calc(x) {
let t = 0;
for (let i = 0; i < x.length; i++) {
t = t + x[i].p;
}
return t;
}
Troubleshooting
-
Issue: Code not working
- Solution: Check syntax errors, verify inputs
-
Issue: Tests failing
- Solution: Review test assertions, check mock data
-
Issue: Performance problems
- Solution: Profile code, optimize bottlenecks
Converted from: Claude Code Skill - test-skill Format: Cursor Rules (.mdc)
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 · 96 lines · 9 tokens per session scan A 3a905de05d65
test-skill is a cursor rule published in the GitHub repository pr-pm/prpm (120 stars, last pushed 2mo ago), licensed MIT. It adds 9 tokens to every session and 496 once invoked, about $0.0000 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 2026-09-03.
Other cursor rules, from other repositories
cypress-defect-tracking-cursorrules-prompt-file
Cursor rules for Cypress development with defect tracking.
cypress-integration-testing-cursorrules-prompt-file
Cursor rules for Cypress development with integration testing.
playwright-integration-testing-cursorrules-prompt-file
Cursor rules for Playwright development with integration testing.
playwright-accessibility-testing-cursorrules-prompt-file
Cursor rules for Playwright development with accessibility testing.
playwright-defect-tracking-cursorrules-prompt-file
Cursor rules for Playwright development with defect tracking.
playwright-e2e-testing-cursorrules-prompt-file
Cursor rules for Playwright development with E2E testing.