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/wiggitywhitney/mcp-commit-storyWrote 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/wiggitywhitney/mcp-commit-story/tdd_requirements)<a href="https://agentmods.dev/rules/wiggitywhitney/mcp-commit-story/tdd_requirements"><img src="https://agentmods.dev/badge/rules/wiggitywhitney/mcp-commit-story/tdd_requirements.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 | $0.01009 | $0.01009 |
| Opus 5 | $0.00504 | $0.00504 |
| Sonnet 5 | $0.00202 | $0.00202 |
| Haiku 4.5 | $0.00101 | $0.00101 |
Grade A, and why
tdd_requirements 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 7d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TDD Requirements and Subtask Structure
TDD Methodology Requirements
Strict TDD methodology is REQUIRED for:
- Creating/modifying application logic
- Adding new functions
- Changing business logic
- Core code changes
TDD is NOT required for:
- Integration testing subtasks
- Documentation updates
- Cleanup tasks
- Telemetry verification
- Boilerplate subtasks
Subtask Structure Patterns
For Core Code Changes (TDD Required)
All subtasks that modify core application logic must follow this exact pattern:
1. GET APPROVAL FOR DESIGN CHOICES (if needed)
**PAUSE FOR MANUAL APPROVAL**: [Specific design choice 1]
**PAUSE FOR MANUAL APPROVAL**: [Specific design choice 2]
- Include this section only if design decisions are needed
- The developer prefers to answer design questions during planning phase rather than having pauses in implementation plans
2. WRITE TESTS FIRST
- Create tests/[unit|integration]/test_[module_name].py
- Test [function_name]() function
- Test cases: [specific scenarios - success, failures, edge cases]
- RUN TESTS - VERIFY THEY FAIL
3. IMPLEMENT FUNCTIONALITY
- Implement [function_name]() in src/[module_path]/[file_name].py
- Handle all error cases identified in tests
- Include comprehensive telemetry with specific metrics/spans
- RUN TESTS - VERIFY THEY PASS
4. DOCUMENT AND COMPLETE
- Add documentation in code docstrings
1. Do not reference tasks
2. Do not reference historical implementations or development processes
3. Write for the reader: A user with no preexisting project knowledge
- Do not remove existing information unless it's incorrect
- No approval needed - make documentation edits directly
- Run the entire test suite and make sure all tests are passing
- Verify that all requirements have been met
- Double check all subtask requirements are met before marking this subtask as complete
- MARK COMPLETE
For Boilerplate Tasks (Simplified Structure)
For integration testing, documentation, cleanup, and telemetry verification subtasks:
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.
- 7d ago First seen · 138 lines · 1,009 tokens per session scan A eba3b3ded3da
tdd_requirements is a cursor rule published in the GitHub repository wiggitywhitney/mcp-commit-story (15 stars, last pushed 1y ago), licensed MIT. It adds 1,009 tokens to every session, about $0.0050 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.