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 agentmods add skills/0xranx/agentbrief/tddnpx skills add 0xranx/agentbrief --skill tddgit clone --depth 1 https://github.com/0xranx/agentbriefWrote 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/0xranx/agentbrief/tdd)<a href="https://agentmods.dev/skills/0xranx/agentbrief/tdd"><img src="https://agentmods.dev/badge/skills/0xranx/agentbrief/tdd.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 | $0.00012 | $0.00470 |
| Opus 5 | $0.00006 | $0.00235 |
| Sonnet 5 | $0.00002 | $0.00094 |
| Haiku 4.5 | $0.00001 | $0.00047 |
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 4d 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
Methodology from obra/superpowers (MIT)
Test-Driven Development (TDD)
Iron law: no production code without a preceding failing test.
The RED-GREEN-REFACTOR Cycle
RED -- Write a Failing Test
- Identify the next smallest behavior to implement.
- Write a test that asserts that behavior.
- Run the test suite. Confirm the new test fails for the right reason.
- If it passes already, your test is not testing new behavior -- rewrite it.
GREEN -- Make It Pass
- Write the minimum production code to make the failing test pass.
- Do not add extra logic, handle future cases, or optimize.
- Run the test suite. All tests must be green.
- If other tests broke, fix them before moving on.
REFACTOR -- Clean Up
- Look at the code you just wrote. Remove duplication, improve naming, simplify.
- Run the test suite after every refactor step. Stay green.
- Do not add new behavior during refactor -- that requires a new RED step.
Practical Rules
- One assertion per test when possible. Focused tests give clearer failure messages.
- Name tests by behavior:
should reject expired tokens, nottest_validate_3. - Keep the cycle short: aim for minutes per iteration, not hours.
- If you are stuck making a test pass, the step is too big. Write a simpler test first.
- Commit after each GREEN or REFACTOR step. Small commits are cheap insurance.
When to Apply TDD
- New features: always.
- Bug fixes: write a test that reproduces the bug first, then fix.
- Refactoring existing untested code: add characterization tests before changing anything.
Anti-patterns to Avoid
- Writing production code first and tests after (test-last is not TDD).
- Writing multiple tests before making any of them pass.
- Skipping the REFACTOR step -- tech debt accrues silently.
- Over-mocking: if your test has more mocks than assertions, rethink the design.
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.
- 4d ago First seen · 54 lines · 12 tokens per session scan A fba2ba659338
tdd is a skill published in the GitHub repository 0xranx/agentbrief (45 stars, last pushed 5mo ago), licensed MIT. It adds 12 tokens to every session and 470 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 2026-08-30.
Other skills, from other repositories
test-driven-development
实现任何功能或修复 bug 时,在写实现代码之前使用(测试先行,RED-GREEN-REFACTOR)。.
pptx
从论文、大纲或结构化文本生成 PowerPoint (.pptx) 演示文稿。Use when 用户需要把一篇论文/文章/大纲做成幻灯片、slides、演示文稿、PPT、deck。Don't use when 只需纯文本总结、生成 Word/PDF、或修改已有 pptx 的单个像素级样式。.
ai-style
当任务是用中文撰写或改写面向读者的文案（产品发布稿、公众号文章、邮件、README 等）， 或用户反馈文字「AI 味太重」「不像人写的」时，加载本 Skill。.
curly-quote-sft
Skill "curly-quote-sft" from bojieli/ai-agent-book, covering 中文技术文档符号与引用规范, 何时加载, 符号定义, 决策优先级 and 正反例约束.
triage
你是当前任务的分诊协调者。先识别用户的全部目标、顺序依赖和验收条件，再按 “事实检索 → 计算/执行 → 写作”顺序逐步请求切换到需要的专业能力。不要替专业 能力完成它的工作，也不要在信息缺失时臆造结果。.
writing
将共享历史中的已验证事实和计算结果整理成符合受众、格式与长度约束的成稿。.