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/drumnation/unsplash-smart-mcp-serverWrote 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/drumnation/unsplash-smart-mcp-server/tdd-tom-testing-rules)<a href="https://agentmods.dev/rules/drumnation/unsplash-smart-mcp-server/tdd-tom-testing-rules"><img src="https://agentmods.dev/badge/rules/drumnation/unsplash-smart-mcp-server/tdd-tom-testing-rules.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 5.1 | $0.00033 | $0.00918 |
| Opus 5 | $0.00016 | $0.00459 |
| Sonnet 5 | $0.00007 | $0.00184 |
| Haiku 4.5 | $0.00003 | $0.00092 |
Grade A, and why
tdd-tom-testing-rules 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
New Feature TDD Rule
Description:
Mandatory Rule: All new features MUST be implemented using Test-Driven Development (TDD) principles. Prioritize tests before code, ensuring comprehensive coverage and a robust design. Tests should be focused and efficient, employing either unit or integration tests as appropriate. All tests MUST adhere to the Test Object Model for improved maintainability and reusability where it makes sense.
Instructions:
-
Choose the Right Testing Strategy:
- BEFORE writing any tests, deeply consider whether a UNIT test or an INTEGRATION test is most effective for the feature or component being developed.
- UNIT Tests: Focus on individual modules or functions in isolation, mocking dependencies. Ideal for testing complex logic within a single unit.
- Consider using unit tests when:
- The logic within a single function or class is complex and needs thorough testing.
- Dependencies can be easily and realistically mocked.
- You need to isolate a specific unit to verify its behavior in detail.
- For guidance on writing unit tests, refer to the Unit Test Writing Guide: READ
@.brain/knowledge/testing/vitest/vitest-unit-testing.rules.ts
- Consider using unit tests when:
- INTEGRATION Tests: Test the interaction between multiple modules or systems. They verify that different parts of the application work together correctly.
- Consider using integration tests when:
- The functionality depends on the interaction between multiple components, services, or external systems (e.g., databases, APIs, CLIs).
- Mocking is difficult, unrealistic, or overly complex.
- You need to ensure that different parts of the system work together correctly in a realistic environment.
- For guidance on writing integration tests, refer to the Integration Test Writing Guide: READ
@.brain/knowledge/testing/vitest/vitest-integration-testing.rules.ts
- Consider using integration tests when:
- Document the reasoning behind your choice of unit or integration testing in the code or test file.
-
Start with tests: Before writing any implementation code, create a failing test case that defines the desired behavior of the new feature, based on the chosen testing strategy.
-
Follow the Red-Green-Refactor cycle:
- Red: Write a failing test (unit or integration).
- Green: Write the minimal code to make the test pass.
- Refactor: Improve code structure while keeping the test green. Be cautious about over-abstracting or introducing unnecessary complexity during refactoring. If tests get more complicated because of the refactoring, it is a code smell.
- Repeat: Move to the next part of the feature
-
Employ the Test Object Model (When Appropriate):
-
If the Test Object Model is deemed beneficial for organization and reusability (e.g., in complex integration tests or UI tests), create a
*.to.tsfile for each logical group of interactions or components being tested. -
Encapsulate interaction logic within this test object.
-
Example:
// user-registration.to.ts import { UserService } from './user-service'; export class UserRegistrationTestObject { private userService: UserService; constructor() { this.userService = new UserService(); } async registerUser(userData: any) { return await this.userService.register(userData); } } -
Do not force the use of the Test Object Model if it adds unnecessary complexity or doesn't provide significant value in simpler scenarios.
-
-
Consult the detailed guidelines for comprehensive instructions:
- TDD: READ
@.brain/knowledge/testing/vitest/vitest-tdd.rules.ts - Test Object Model: READ
@.brain/knowledge/testing/vitest/vitest-test-object-model.rules.ts - Unit vs. Integration Testing: READ
@.brain/knowledge/testing/unit-vs-integration-testing.rules.ts
- TDD: READ
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.
- 8d ago First seen · 65 lines · 33 tokens per session scan A 17bbabafe04a
tdd-tom-testing-rules is a cursor rule published in the GitHub repository drumnation/unsplash-smart-mcp-server (63 stars, last pushed 7mo ago), licensed MIT. It adds 33 tokens to every session and 918 once invoked, about $0.0002 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
manual-review.backend
A set of rules for verifying backend-only changes and changes that use different verification channels. It separates evidence the agent can collect from checks that require a person, a production authorization, or a business decision.
mcpnuke-tests
Test conventions for mcpnuke — enforces TDD workflow.
debug-issue
When the user reports a bug, an error, or unexpected behavior. Enforces four structured phases — reproduction, failing test, root cause isolation, fix and verify — to stop guess-and-check loops.
testing-discipline
TDD, BDD, and testing best practices — stack-agnostic.
common-testing
Testing requirements: 80% coverage, TDD workflow.
tdd
Test-driven development — red-green-refactor cycle.