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 skills add jesse-merhi/skills --skill tddgit clone --depth 1 https://github.com/jesse-merhi/skillsWrote 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/skills/jesse-merhi/skills/tdd)<a href="https://agentmods.dev/skills/jesse-merhi/skills/tdd"><img src="https://agentmods.dev/badge/skills/jesse-merhi/skills/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/skills/jesse-merhi/skills/tdd"><img src="https://agentmods.dev/badge/skills/jesse-merhi/skills/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 | $0.00032 | $0.00615 |
| Opus 5 | $0.00016 | $0.00308 |
| Sonnet 5 | $0.00006 | $0.00123 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
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 6d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test-driven development
Use one vertical red-green-refactor cycle at a time. Tests should describe observable behavior and remain useful when the implementation changes.
Choose the seam
A seam is the stable boundary through which a caller experiences behavior: a CLI command, HTTP request, exported function, component interaction, adapter, or another durable interface.
Before the first test, load test-audit and apply its test-portfolio policy.
State the proposed seam, observable outcome, external dependencies, distinct
reachable regression, and nearest existing coverage. Prefer an existing public
boundary. Done when the proposed test has the narrowest useful proof level, an
independent expected result, and no equivalent owner will remain after the
change. Ask the user only when the choice would materially change architecture,
testing cost, or product behavior.
Prefer tests at stable behavioral boundaries. Focused tests of internal pure logic are appropriate when that logic has a durable contract and exercising it through a larger boundary would obscure failures or make the suite needlessly slow.
Read tests.md for examples and mocking.md for boundary guidance.
Red-green-refactor
- Red: Write one focused behavior test. Run it and confirm it fails because the behavior is missing, not because the test, fixture, or environment is broken.
- Green: Implement the smallest complete solution that passes. Small does not mean knowingly temporary, duplicated, or awkward.
- Refactor: While the suite remains green, improve names, remove duplication, simplify control flow, deepen useful modules, and repair awkward interfaces. Do not add new behavior during refactoring.
- Repeat for the next behavior, letting the previous cycle inform the next test.
Run the affected test after red, green, and refactor. Run the broader relevant suite when the slice is stable.
Test quality
- Test behavior users or callers care about, not private methods or incidental call order.
- Keep one behavior per test. Use multiple assertions when they jointly prove that behavior.
- Derive expected results independently from the implementation.
- Mock external boundaries when a real boundary is impractical. Prefer real repository modules and collaborators inside the system.
- Avoid horizontal slicing in which every imagined test is written before any implementation. Each test should teach the next implementation move.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago Changed · +4 lines 3da86b99d0b1
- 10d ago First seen · 62 lines · 32 tokens per session scan A 7b007c45e497
tdd is a skill published in the GitHub repository jesse-merhi/skills (3 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 615 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 2026-08-31.
Other skills, from other repositories
engram-testing-coverage
TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.
iterative-development
TDD iteration loops using Claude Code Stop hooks - runs tests after each response, feeds failures back automatically.
python
Python development with ruff, mypy, pytest - TDD and type safety.
nw-fp-clojure
Clojure language-specific patterns, data-first modeling, REPL-driven development, and spec.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
mobiai-mobile-tdd
You MUST use this before writing any implementation code for a mobile feature, bug fix, refactor, or behavior change. Tests come before implementation — no exceptions.