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/holasoymalva/ai-pr-reviewer-tasks/propose-test-casesgit clone --depth 1 https://github.com/holasoymalva/AI-PR-Reviewer-TasksWhat 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 | $0.00008 | $0.02531 |
| Opus 5 | $0.00004 | $0.01265 |
| Sonnet 5 | $0.00002 | $0.00506 |
| Haiku 4.5 | $0.00001 | $0.00253 |
Grade A, and why
propose-test-cases 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 yesterday.
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 — 440 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rule: Propose Test Cases and Testing Strategy
Goal
To guide an AI assistant in analyzing Pull Request changes and proposing comprehensive test cases, testing strategies, and quality assurance recommendations to ensure robust code coverage.
Process
-
Analyze Changed Functionality: Examine the code changes to understand what functionality needs testing.
-
Understand Testing Context: Gather information about testing requirements:
- Current Coverage: "What's the existing test coverage for these areas?"
- Testing Framework: "What testing framework and tools are being used?"
- Test Types: "Should I focus on unit, integration, or end-to-end tests?"
- Critical Paths: "Are there critical business flows that must be thoroughly tested?"
- Performance Requirements: "Are there performance benchmarks to meet?"
-
Analyze Test Gaps: Identify missing or insufficient test coverage.
-
Generate Test Strategy: Create comprehensive testing recommendations with specific test cases.
Test Analysis Framework
🔍 Functionality Analysis
- New Features: Identify all new functionality added
- Modified Behavior: Understand changes to existing functionality
- Dependencies: Map external dependencies and integrations
- Business Logic: Identify critical business rules and workflows
- Error Conditions: Catalog potential failure scenarios
📊 Test Coverage Assessment
- Existing Tests: Analyze current test coverage
- Coverage Gaps: Identify untested code paths
- Test Quality: Evaluate existing test effectiveness
- Regression Risks: Identify areas prone to regression
Test Categories
🧪 Unit Tests
Function-Level Testing
- Test individual functions with various inputs
- Verify correct outputs for expected inputs
- Test boundary conditions and edge cases
- Validate error handling and exceptions
Class/Module Testing
- Test object state management
- Verify method interactions
- Test inheritance and polymorphism
- Validate encapsulation and data integrity
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.
- yesterday First seen · 440 lines · 8 tokens per session scan A c286c4b1ccf8
propose-test-cases is a cursor rule published in the GitHub repository holasoymalva/AI-PR-Reviewer-Tasks (14 stars, last pushed 1y ago), licensed Apache-2.0. It adds 8 tokens to every session and 2,531 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 2026-08-30.
Other cursor rules, from other repositories
refactor-test
Review and refactor generated unit tests for improved quality and coverage.
generate-unit-test
Generate comprehensive unit tests based on function analysis.
extract-functions
Extract and analyze functions from source code for unit test generation.
create-readme-from-codebase
Generate a professional README.md by analyzing existing codebase.
improve-readme
Improve and enhance an existing README.md file.
create-readme-from-description
Generate a professional README.md from project description.