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/MeenakshiSundaram-MS/prove-itWrote 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/meenakshisundaram-ms/prove-it/prove-it-tdd)<a href="https://agentmods.dev/rules/meenakshisundaram-ms/prove-it/prove-it-tdd"><img src="https://agentmods.dev/badge/rules/meenakshisundaram-ms/prove-it/prove-it-tdd/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/meenakshisundaram-ms/prove-it/prove-it-tdd"><img src="https://agentmods.dev/badge/rules/meenakshisundaram-ms/prove-it/prove-it-tdd.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00028 | $0.00557 |
| Opus 5 | $0.00014 | $0.00279 |
| Sonnet 5 | $0.00006 | $0.00111 |
| Haiku 4.5 | $0.00003 | $0.00056 |
Grade A, and why
prove-it-tdd 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 11d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
prove-it — TDD Mode
Write the failing test first. Show it fails. Then implement. Show it passes.
Mandatory Sequence
1 — Verification Plan
VERIFICATION PLAN
─────────────────
Test name: [what the test asserts]
Framework: [jest / pytest / go test / cargo test / etc.]
Failing for: [why it will fail — function doesn't exist / wrong return / missing branch]
2 — Write the Failing Test
Write ONLY the test. No implementation yet. A test that passes without any implementation is a bad test — fix it before proceeding.
3 — Show Red
RED — expected failure
──────────────────────
Command: [test command]
Output:
[paste actual failure output — the real error, not a summary]
4 — Implement
Write the minimum code to make the test pass. No gold-plating beyond what the test requires.
5 — Show Green
GREEN — passing
───────────────
Command: [same test command as RED]
Output:
[paste actual passing output]
6 — Refactor (if any)
If you refactor: re-run and show output again. A refactor that breaks tests is not a refactor — revert it.
7 — Say Done
Only after the GREEN block is shown.
Red→Green Integrity Rule
The test name in RED and the test name in GREEN must be the same.
Showing red on test A then green on test B is a violation — the test for the actual implementation was never proven to be failing first.
If you notice this: go back, show the correct test failing, then show it passing.
When a Test Passes on First Run Without Implementation
This means the test is not testing the right thing. Debug:
- Is the assertion actually checking the new behavior?
- Is there a pre-existing implementation that already satisfies the test?
- Is the import path correct?
Fix the test before writing implementation.
Refactoring Phase Rules
- Refactor means: restructure without changing behavior
- Every refactor must be followed by a passing test run
- Show the test output after each refactor step
- If a refactor introduces a failure: revert it and try a smaller change
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.
- 11d ago First seen · 85 lines · 28 tokens per session scan A 26b5fb8fc5ff
prove-it-tdd is a cursor rule published in the GitHub repository MeenakshiSundaram-MS/prove-it (2 stars, last pushed 4mo ago), licensed MIT. It adds 28 tokens to every session and 557 once invoked, about $0.0001 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
manual-review.backend
The obligations, predicates, evidence schema, failure handling, and review timing in this source are shared. Concrete browser, dispatch, question, filesystem, and command mechanics are target-native and MUST come from the selected runtime fragment at the matching adapter path. A fragment declares only the capability…
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.