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 CCDawn/codex-skills --skill briefbound-bdd-tdd-developmentgit clone --depth 1 https://github.com/CCDawn/codex-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/ccdawn/codex-skills/briefbound-bdd-tdd-development)<a href="https://agentmods.dev/skills/ccdawn/codex-skills/briefbound-bdd-tdd-development"><img src="https://agentmods.dev/badge/skills/ccdawn/codex-skills/briefbound-bdd-tdd-development.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 5.1 | $0.00054 | $0.01120 |
| Opus 5 | $0.00027 | $0.00560 |
| Sonnet 5 | $0.00011 | $0.00224 |
| Haiku 4.5 | $0.00005 | $0.00112 |
Grade A, and why
briefbound-bdd-tdd-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 8d 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.
Briefbound 紧凑 BDD/TDD
目标
只对已明确的新行为或高风险实现契约使用最小 RED/GREEN 闭环，不承担未知根因诊断，不生成仪式性文档、逐步旁白或代理审查链。
Briefbound task contract
- Context Boundary: 已确定的预期行为、owned surface、保护边界、测试锚点和验证命令。
- Output Contract: 最小实现、RED/GREEN 证据、相关验证和剩余风险。
- Allowed Action: 只改证明当前行为所需的生产代码与测试，不扩 scope。
- Success Evidence: RED 证明缺失/回归，GREEN 证明实现，相关回归检查通过。
- Stop Condition: 预期不清、测试不能证明目标、边界冲突、需扩范围或高风险授权。
- Route Out: 当前 owner、
briefbound-score-loop、下一个已授权任务、briefbound-development-cleanup、briefbound-pr-review、briefbound-router或 BLOCKED。
统一调用契约
- 只处理 Briefbound task contract 范围；不匹配时回
briefbound-router或更具体 owner，复合任务不吞其他 owner。 - 用户可见内容默认中文；保留技术字面量；只报产出、证据与风险；Route Out 仅以 Briefbound task contract 为准，末行写
下一步建议: <一个具体动作>。
模式闸门
按子任务判断，不给整个请求贴 TDD 标签。机械替换、样式/文案、普通配置、生成代码、小适配，或已有验证足够时直接轻量实现。
Bug、异常、失败测试或构建失败由 briefbound-bug-review 主责；可测性能目标/回归由 briefbound-performance-engineering 主责。两者即使使用 RED/GREEN 也不加载本 skill。只有预期行为和 owning surface 已明确的新增/变更契约，或用户明确要求 TDD，才由本 skill 主责。
分数下降、metric 未提升、candidate reject 或 online worse 是实验结果，不是 TDD RED，返回 briefbound-score-loop。只有预期输入输出明确的 harness/parser/schema/seed/shape/NaN/打包 bug 留在这里。
强信号：确定性行为回归；状态/数据/权限/安全/迁移/公共 API 风险；失败路径易遗漏；跨模块行为只能靠自动化证明；或用户明确要求 TDD。文件多、描述长和 Superpowers always 不构成触发。
紧凑 TDD
- 一行锁定
给定/当/则；只有真实分叉才展示。 - 现有失败测试或稳定复现可直接作为 RED，不复制测试。
- 没有 RED 时写一个最小行为测试，并运行最窄命令确认失败原因正确。
- 写通过测试所需的最小实现，不顺带重构。
- 重跑得到 GREEN，再运行受影响的相关测试；全量 gate 留给集成风险。
- 只有已产生重复或复杂度时才重构，并保持 GREEN。
围绕可观察行为组织测试，不为每个函数/分支建测试，不默认创建 .feature、矩阵或长 Gherkin。优先复用 fixture/helper；测试基础设施成本过高时改用最小集成测试、结构检查或可逆 probe，并说明缺口。出现 mock/test-only API 风险时才读取 references/testing-anti-patterns.md，正式 Gherkin 才读取 references/gherkin.md。
子代理
默认不派发子代理。只有 lane 独立、写入面不重叠、可单独验证且收益明显高于上下文/审查/合并成本时才派一个紧凑实现 Agent；主 Agent 检查 diff 并重跑证据。共享文件和顺序依赖留在当前上下文。
失败与输出
RED 原因错误先修测试/环境；GREEN 未通过就在当前边界修复；测试意图与需求冲突则回 Briefbound Router；自动化不可行时报告替代证据和风险，不伪造 TDD。
开发结果:
- 模式: LIGHTWEIGHT / COMPACT_TDD
- 变更: <行为与文件>
- 证据: RED...；GREEN...；回归...
- 风险: <无或真实缺口>
下一步建议: <继续已授权任务或收口>
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.
- 8d ago First seen · 66 lines · 54 tokens per session scan A 7d8362839568
briefbound-bdd-tdd-development is a skill published in the GitHub repository CCDawn/codex-skills (4 stars, last pushed 26d ago), licensed MIT. It adds 54 tokens to every session and 1,120 once invoked, about $0.0003 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
writing-skills
A guide for creating and testing reusable instructions for AI agents, called skills. It applies test-driven development, or TDD—the practice of writing tests before implementation—to instruction documents.
test-driven-development
Test-driven development, or TDD, is a way to build software by writing a test that fails, adding the smallest code that makes it pass, and then cleaning up the code. These instructions require that process for features, bug fixes, refactors, and behavior changes.
test-driven
A test-driven development guide. TDD means writing a test for the desired behaviour first, seeing it fail, then writing the smallest implementation that makes it pass.
verification-before-completion
A checklist for verifying work before claiming that it is finished, fixed, built, tested, or ready to submit. It requires fresh command output and evidence for each claim.
test-driven-development
Use when the user explicitly requests strict or test-first TDD, or when the current conversation already contains an explicit TDD Route: strict decision from another Aegis workflow.
laravel-tdd
Test-driven development for Laravel with PHPUnit and Pest, factories, database testing, fakes, and coverage targets.