Borrowing it
Nothing to install: this file belongs to recomposesh/recompose. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/recomposesh/recompose/main/.claude/skills/gherkin-best-practices/SKILL.mdgit clone --depth 1 https://github.com/recomposesh/recomposeWrote 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/recomposesh/recompose/gherkin-best-practices)<a href="https://agentmods.dev/skills/recomposesh/recompose/gherkin-best-practices"><img src="https://agentmods.dev/badge/skills/recomposesh/recompose/gherkin-best-practices/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/recomposesh/recompose/gherkin-best-practices"><img src="https://agentmods.dev/badge/skills/recomposesh/recompose/gherkin-best-practices.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 | $0.00046 | $0.01083 |
| Opus 5 | $0.00023 | $0.00541 |
| Sonnet 5 | $0.00009 | $0.00217 |
| Haiku 4.5 | $0.00005 | $0.00108 |
Grade A, and why
gherkin-best-practices 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 10d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gherkin best practices
Distilled from Cucumber's Writing better Gherkin, the BRIEF principle, and the Cucumber anti-patterns series.
The contract
- A
.featurefile is the maintainer's approval artifact. It states agreed behavior in language a reader understands without seeing any code. - Write the scenario before the automation. A scenario written after the code documents the code, not the agreement.
- The tdd-bdd invariant applies at this layer too: a
.featurefile changes if and only if the agreed behavior changes. Step definitions absorb every implementation change.
BRIEF
Every scenario passes all six checks:
- Business language: words come from the product domain (gateway, provider, account, virtual model), never from the DOM, the toolchain, or test infrastructure.
- Real data: concrete values (
anthropic,api-key), not vague placeholders ("some provider", "valid input"). - Intention revealing: state what the actor achieves, not the mechanics used to achieve it.
- Essential: delete any line whose removal loses no meaning. Incidental detail hides the rule the scenario illustrates.
- Focused: one scenario illustrates one rule.
- Brief: three to five steps. A longer scenario is smuggling setup that belongs in
Backgroundor inside a step definition.
Declarative, never imperative
- Describe what, not how. "When the maintainer connects an Anthropic account" beats four steps of navigating, typing, and clicking.
- Selectors, URLs, keystrokes, and button coordinates never appear in a step. They live in step definitions and page objects, governed by the playwright-best-practices skill.
- Don't over-abstract either. "Given the app works, then it works" states no behavior. Keep at least one concrete, checkable value per scenario.
Structure rules
- One When-Then pair per scenario. A second When-Then is a second scenario.
- Scenarios run in any order with the same result. A scenario that depends on another scenario's leftovers is a defect.
Backgroundholds only context that every scenario in the file needs. Setup for one scenario stays in that scenario's Given.Scenario Outlineearns its place only when the same rule holds across a table of real value combinations. Never use it to disguise unrelated cases as one rule.- Tags classify, never configure: use them for suite selection (
@smoke) and quarantine (@quarantine), not to smuggle parameters into steps.
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.
- 10d ago First seen · 54 lines · 46 tokens per session scan A a8ff55d2aa34
gherkin-best-practices is a skill published in the GitHub repository recomposesh/recompose (27 stars, last pushed 13d ago), licensed MIT. It adds 46 tokens to every session and 1,083 once invoked, about $0.0002 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
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…
pyats-dynamic-test
Generate and execute deterministic pyATS aetest validation scripts - interface state, OSPF neighbors, BGP paths, ping matrices, and custom compliance tests. Use when writing a network test, validating post-change state, running pass/fail checks, or building automated regression tests.
test-loop
Plan, generate, and heal an executable E2E test suite from approved acceptance criteria (web and mobile).
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…