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 SylphAI-Inc/atskills --skill simple-tddgit clone --depth 1 https://github.com/SylphAI-Inc/atskillsWrote 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/sylphai-inc/atskills/simple-tdd)<a href="https://agentmods.dev/skills/sylphai-inc/atskills/simple-tdd"><img src="https://agentmods.dev/badge/skills/sylphai-inc/atskills/simple-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/sylphai-inc/atskills/simple-tdd"><img src="https://agentmods.dev/badge/skills/sylphai-inc/atskills/simple-tdd.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 | $0.00022 | $0.00477 |
| Opus 5.5 | $0.00009 | $0.00191 |
| Sonnet 5.5 | $0.00004 | $0.00095 |
| Haiku 4.5 | $0.00002 | $0.00048 |
Grade A, and why
simple-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 2mo 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
Simple TDD Workflow
Follow test-driven development strictly for the task at hand. Do not write implementation code before a failing test exists for it.
Steps
-
Understand the requirement. Restate what behavior is being added or fixed, in one or two sentences, before touching any file.
-
Write a failing test first.
- Add a test that exercises the new/changed behavior.
- Run the test suite and confirm the new test fails (and fails for the expected reason — a wrong assertion or a crash from unimplemented code, not an unrelated error).
- If it doesn't fail, the test isn't testing anything new — fix the test before proceeding.
-
Write the minimum code to make it pass.
- Implement just enough to make the failing test green. Resist the urge to add extra functionality, generalization, or "while I'm here" cleanup at this stage.
- Run the full test suite. All tests — the new one and every existing one — must pass.
-
Refactor only when green.
- With all tests passing, look for duplication, unclear naming, or structural issues introduced by the minimal implementation.
- Refactor in small steps, re-running the test suite after each change to confirm nothing broke.
- Do not add new behavior during this step — refactoring changes structure, not behavior.
-
Repeat. For the next requirement or edge case, go back to step 2.
Rules
- Never write production code without a failing test that requires it.
- Never write more test code than is sufficient to fail.
- Never write more production code than is sufficient to pass the currently failing test.
- If you find yourself writing several tests before making any of them pass, stop — return to one test at a time.
When to Deviate
For pure exploration/spike work (throwaway prototyping to understand a problem), it's acceptable to skip strict TDD — but say so explicitly, and any code from the spike should be rewritten test-first before it ships.
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.
- 2mo ago First seen · 43 lines · 22 tokens per session scan A 89c4481f1a37
simple-tdd is a skill published in the GitHub repository SylphAI-Inc/atskills (87 stars, last pushed 2mo ago), licensed MIT. It adds 22 tokens to every session and 477 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 2026-08-30.
simple-tdd compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| simple-tddSylphAI-Inc/atskills | Skill | 87 | 2mo ago | MIT | A | 22 | Claude Code, Codex |
| sparc-methodologyruvnet/RuView | Skill | 103k | yesterday | MIT | A | 29 | Claude Code |
| red-green-refactorrohitg00/skillkit | Skill | 1.6k | 5mo ago | Apache-2.0 | A | 90 | Claude Code, Codex |
| superpowers-zhznlgis/opengis-skills | Skill | 76 | 10d ago | MIT | B | 45 | Claude Code, Codex |
| sparc-methodologyruvnet/agentic-flow | Skill | 838 | yesterday | none | A | 29 | Claude Code |
| tsq-bddsonature-lab/timsquad | Skill | 12 | 2mo ago | MIT | A | 62 | Claude Code |
| implementing-tasksprime-radiant-inc/iterative-development | Skill | 183 | 5mo ago | Apache-2.0 | A | 45 | Claude Code |