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/xonovex/platform/bdd-guidenpx skills add xonovex/platform --skill bdd-guidegit clone --depth 1 https://github.com/xonovex/platformWhat 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 | $0.00117 | $0.00876 |
| Opus 5 | $0.00059 | $0.00438 |
| Sonnet 5 | $0.00023 | $0.00175 |
| Haiku 4.5 | $0.00012 | $0.00088 |
Grade A, and why
bdd-guide 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 2d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Behaviour- and Acceptance-Driven Development
Drive software from concrete, agreed examples of behaviour. Discover them in conversation, formulate them as Given-When-Then scenarios, and keep the executable scenarios as living documentation. The acceptance layer answers "are we building the right thing?" The inner domain logic is still driven test-first by tdd-guide. ATDD and BDD are two names for this one practice.
Essentials
- Discover before you formulate - run a three-amigos conversation over real examples first, see references/discovery-three-amigos.md
- Map examples to size and split the story - yellow/blue/green/red cards expose scope and gaps, see references/discovery-three-amigos.md
- Write scenarios in Gherkin Given-When-Then - Feature, Scenario, Background, Outline; declarative steps, see references/gherkin-reference.md
- Treat scenarios as living documentation - specs and tests become one trustworthy artefact, see references/specification-by-example.md
Gotchas
- Gherkin/Cucumber is a collaboration tool that tests the team's shared UNDERSTANDING of unwritten software, not a testing tool: automation is the third practice, never the purpose, see references/appendix-discovery.md.
- "Three amigos" means three PERSPECTIVES (business / development / testing), not exactly three people: invite more; the conversation is the point.
- Driving scenarios end-to-end through the UI/browser is slow, volatile, and fails to localise the bug: stub external services/queues/DBs and drive the core domain directly.
- Given-When-Then is the recommended template, not the goal; the essential thing is concrete agreed examples, so do not over-engineer the grammar with deep nesting or imperative "click button X" steps.
- ATDD and BDD are not rival methodologies: same example-driven, acceptance-level idea; do not split the practice in two.
- A rule that needs many examples to pin down is a signal to split the rule, not to write ten scenarios, and a rule simple enough to need none needs none; the count is emergent, not a quota.
What ships with it
7 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.
- 2d ago First seen · 46 lines · 117 tokens per session scan A 8e116cb8e612
bdd-guide is a skill published in the GitHub repository xonovex/platform (5 stars, last pushed 2d ago), licensed MIT. It adds 117 tokens to every session and 876 once invoked, about $0.0006 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
pest-testing
Use this skill for Pest PHP testing in Laravel projects only. Trigger whenever any test is being written, edited, fixed, or refactored — including fixing tests that broke after a code change, adding assertions, converting PHPUnit to Pest, adding datasets, and TDD workflows. Always activate when the user asks how to…
test-guide
Test-writing guide for Backend.AI — propose success/exception/edge scenarios first, refine them with the user, then implement while reporting per-scenario verification status. Covers fixtures, withtables, mock repositories, pants test, optional TDD cadence.
代码调试
调试工作流：确认需要 → 先写失败测试复现 → 定位根因 → 修复 → 回归。含修复熔断机制（同模块 bug 打回超 3 次停止）、逐层根因分析（5 Whys）、假设管理、鱼骨图。用于 Bug 修复、测试失败、运行时错误排查。.
代码实现
编码工作流：确认需要 → 模块边界设计 → TDD 红绿循环（写失败测试、实现、重构、回归）→ 风险分级。用于新功能开发、代码修改、重构、补测试。.
创建工具
创建或修改工具时加载。内置工具创建规范：TDD 流程、命名规范、BuiltinTool 继承、ToolCategory 枚举、路径规范、代码模板要点。.
python-testing-patterns
Implement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development. Use when writing Python tests, setting up test suites, or implementing testing best practices.