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 metaspartan/cybara --skill test-driven-developmentgit clone --depth 1 https://github.com/metaspartan/cybaraWrote 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/metaspartan/cybara/test-driven-development)<a href="https://agentmods.dev/skills/metaspartan/cybara/test-driven-development"><img src="https://agentmods.dev/badge/skills/metaspartan/cybara/test-driven-development/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/metaspartan/cybara/test-driven-development"><img src="https://agentmods.dev/badge/skills/metaspartan/cybara/test-driven-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00037 | $0.00386 |
| Opus 5.5 | $0.00015 | $0.00154 |
| Sonnet 5.5 | $0.00007 | $0.00077 |
| Haiku 4.5 | $0.00004 | $0.00039 |
Grade A, and why
test-driven-development 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 1mo 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.
What it actually says
Test-Driven Development (TDD)
Write the test first. It forces precise specifications and gives a free regression net.
Red → Green → Refactor
- Red. Write ONE small test for the behavior you want. Run it. It must FAIL (and fail for the right reason — an assertion, not a compile error in unrelated code).
- Green. Write the minimum code to make that test pass. No more, no less. Run it.
- Refactor. Clean up duplication while keeping tests green. Re-run after each change.
Repeat with the next smallest increment.
Rules of thumb
- Test behavior, not implementation. Prefer public API; don't poke private internals.
- One assertion concept per test. If "and" appears in the test name, consider splitting.
- Name tests like
it("returns X when Y")/should do Z when …. - If a bug fix, write the test that reproduces the bug FIRST (see
systematic-debugging). - Don't write tests that depend on wall-clock, random, or network unless you stub them.
Running tests
- Match the project's framework and command (
bun test,pytest,go test, …). - For Bun projects:
bun test(perAGENTS.md, Bun is the only JS runner).
When TDD is overkill
- Throwaway exploration / spikes — write the test after you know the shape.
- Pure UI tweaks with no logic — a visual check is fine.
TDD pays off most for: parsers, state machines, financial/permission logic, and anything with many edge cases.
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.
- 1mo ago First seen · 37 lines · 37 tokens per session scan A e87fb888e1f9
test-driven-development is a skill published in the GitHub repository metaspartan/cybara (32 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 386 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
superpowers-test-driven-development
Use when implementing any feature or bugfix, before writing implementation code.
08-debug
Reproduce and fix a known bug, or find an unknown root cause by hypothesis validation. Use when the user wants to fix a bug, find why something breaks, or reopen a stuck investigation. Not for building a feature or reviewing a diff.
test-driven-development
TDD: enforce RED-GREEN-REFACTOR, tests before code.
hatch3r-bug-fix
Step-by-step bug fix workflow. Diagnose root cause, implement minimal fix, write regression test. Use when fixing bugs, working on bug report issues, or when the user mentions a bug.
ap-policies
Attach a completion policy gate (shell check or judge-agent rubric) to a session or fan-in group so turn-end only passes when the gate is green, then optionally auto-commit pending human ack. Use when the user says "gate this session on tests passing", "attach a policy", "commit only if tests are green", "judge…
kodama-verification
Define measurable success criteria and collect targeted test, build, lint, type-check, or smoke-test evidence before claiming work is complete.