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 cuongtl1992/vibe-skills --skill gherkin-to-codegit clone --depth 1 https://github.com/cuongtl1992/vibe-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/cuongtl1992/vibe-skills/gherkin-to-code)<a href="https://agentmods.dev/skills/cuongtl1992/vibe-skills/gherkin-to-code"><img src="https://agentmods.dev/badge/skills/cuongtl1992/vibe-skills/gherkin-to-code/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/cuongtl1992/vibe-skills/gherkin-to-code"><img src="https://agentmods.dev/badge/skills/cuongtl1992/vibe-skills/gherkin-to-code.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00125 | $0.02600 |
| Opus 5 | $0.00063 | $0.01300 |
| Sonnet 5 | $0.00025 | $0.00520 |
| Haiku 4.5 | $0.00013 | $0.00260 |
Grade A, and why
gherkin-to-code 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 11d 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 — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gherkin to Code — Feature Implementation
Đọc Gherkin feature file từ living docs → phân tích technical solution → gen step definitions + implementation code. Skill này là bridge từ WHAT (feature file) sang HOW (code).
Triết lý
Feature file là contract. Code phải thỏa mãn contract đó — không hơn, không kém.
Skill này KHÔNG quyết định stack, framework, hay conventions — đó là việc của CLAUDE.md và existing code trong repo. Skill này chỉ hướng dẫn process: đọc gì → phân tích gì → gen gì → verify gì.
Ngôn ngữ
- Code comments, commit messages: theo convention repo (CLAUDE.md)
- Technical solution summary: tiếng Việt (consistent với PRD và feature file)
- Code: theo ngôn ngữ lập trình của repo
Phase 1 — Technical Analysis (bắt buộc, engineer review trước khi code)
Phase này là bước architecture cho feature-level. KHÔNG skip — gen code mà không có technical analysis sẽ dẫn tới refactor.
1.1. Đọc và hiểu feature file
Input: .feature file (hoặc nhiều files nếu feature span nhiều module)
Extract:
├── Feature name + narrative → hiểu context
├── Rules → list business rules cần implement
├── Scenarios per Rule → behaviors cần thỏa mãn
├── Tags → test layer (@api/@web/@integration), priority (@p2/@future)
├── # PRD link → đọc PRD nếu cần thêm context
└── # TODO comments → decisions chưa resolve
1.2. Scan codebase hiện tại
Đọc repo qua git submodule hoặc trực tiếp:
Scan:
├── CLAUDE.md → stack, conventions, patterns
├── Existing step definitions → pattern đang dùng
├── Domain models / entities → data model hiện tại
├── API routes / controllers → endpoints hiện có
├── Database schema → tables, relationships
└── Related features code → follow existing patterns
1.3. Đề xuất Technical Solution
Output dạng summary để engineer review:
## Technical Solution: [Feature Name]
### Tổng quan
[1-2 câu: approach chính để implement feature này]
### Components cần thay đổi
| Component | Thay đổi | Lý do (Rule ID) | Impact |
|-----------|----------|-----------------|--------|
| [service/module] | [new/modify/extend] | [BR-Mxx] | [low/medium/high] |
### Data model changes
| Entity | Thay đổi | Fields | Migration? |
|--------|----------|--------|-----------|
| [entity] | [new table / add columns / modify] | [field list] | [yes/no] |
### API changes
| Endpoint | Method | Thay đổi | Guards (Rules) |
|----------|--------|----------|---------------|
| [path] | [GET/POST/...] | [new/modify] | [BR-Mxx] |
### Quyết định kỹ thuật
- [Decision 1]: [option chọn] — *lý do: [ngắn gọn]*
- [Decision 2]: [option chọn] — *lý do: [ngắn gọn]*
### Breaking changes
- [ ] [Mô tả breaking change nếu có] → *ảnh hưởng: [ai/service nào]*
### Implementation order
1. [Component/step đầu tiên] — *vì: [dependency reason]*
2. [Component/step tiếp theo]
3. ...
What ships with it
1 file 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.
- 11d ago First seen · 313 lines · 0 tokens per session scan A 9f480e0a7d73
gherkin-to-code is a skill published in the GitHub repository cuongtl1992/vibe-skills (10 stars, last pushed 5mo ago), licensed MIT. It adds 125 tokens to every session and 2,600 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
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.