gherkin-authoring

Guidance for writing and reviewing Gherkin: a plain-text format for describing software behavior as examples. It covers Cucumber scenarios, acceptance criteria, rules, examples, and related structures.

In plain words
What is it for?
Use it to draft or improve feature files, acceptance criteria, scenario outlines, backgrounds, rules, tags, data tables, and Gherkin included in Markdown.
Why use it?
It helps turn vague requirements into concrete, observable behaviors while keeping technical implementation details out of the examples.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/intent-driven-dev/intent-driven-template/gherkin-authoring
Any agent
npx skills add intent-driven-dev/intent-driven-template --skill gherkin-authoring
Clone the repo
git clone --depth 1 https://github.com/intent-driven-dev/intent-driven-template

Made for: Claude Code, Codex.

Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,250 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00054 $0.01250
Opus 5 $0.00027 $0.00625
Sonnet 5 $0.00011 $0.00250
Haiku 4.5 $0.00005 $0.00125

Measured yesterday against content hash 6be226f25e29, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gherkin-authoring 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 yesterday.

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.

.agents/skills/gherkin-authoring/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gherkin Authoring

Overview

Write Gherkin as executable examples of business behavior. Optimize for domain language, concrete examples, and observable outcomes; keep implementation and UI mechanics inside step definitions.

Scope

Use this for standalone .feature files and Gherkin embedded in Markdown or other prose. When Gherkin is inside a Markdown wrapper, review or rewrite only the Gherkin section unless the user asks for broader document edits. Preserve fences, headings, and surrounding prose. If the input includes Markdown around the Gherkin, return the Markdown wrapper with only the Gherkin block changed.

Workflow

  1. Identify the Gherkin region: whole .feature file, fenced gherkin block, indented block, quoted acceptance criteria, or inline scenario text.
  2. Preserve the surrounding wrapper unless explicitly asked to change it. For Markdown input, return the heading/prose/fence context, not just the fenced Gherkin block.
  3. Clarify the behavior as examples: initial state, event, observable outcome.
  4. Choose the smallest structure that expresses the behavior: Feature, optional Rule, Background, Scenario/Example, or Scenario Outline with Examples.
  5. Keep scenarios concrete and short, usually 3-5 steps.
  6. Review syntax and readability before returning: colons, step keywords, duplicate step text, observable outcomes, and table/doc string formatting.

Quick Reference

Construct Use for Syntax note
Feature: One high-level capability per feature document or block Requires :
Rule: Group scenarios under one business rule Requires :
Scenario: / Example: One concrete example Requires :
Background: Short shared context for following scenarios Requires :; one per Feature or Rule
Scenario Outline: Same behavior with varied data Requires Examples: and <parameter> placeholders
Examples: Data rows for an outline Requires : and a table
Given Known state or precondition No :
When Event or action No :
Then Observable outcome No :
And / But Continue the previous step type No :
* Bullet-like step list Use sparingly for list-style setup
@tag Group or filter features/scenarios Place above the item tagged
# Line comment Line comments only; no block comments
""" Doc String Passed as final step argument
` ` Data Table

Read the full file on GitHub · 96 lines

Changes

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.

  1. yesterday First seen · 96 lines · 54 tokens per session scan A 6be226f25e29

Subscribe to this mod's changes

gherkin-authoring is a skill published in the GitHub repository intent-driven-dev/intent-driven-template (121 stars, last pushed 8d ago), licensed MIT. It adds 54 tokens to every session and 1,250 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 2026-08-30.