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 aiocean/claude-plugins --skill aio-gherkin-refinegit clone --depth 1 https://github.com/aiocean/claude-pluginsWrote 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/aiocean/claude-plugins/aio-gherkin-refine)<a href="https://agentmods.dev/skills/aiocean/claude-plugins/aio-gherkin-refine"><img src="https://agentmods.dev/badge/skills/aiocean/claude-plugins/aio-gherkin-refine/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/aiocean/claude-plugins/aio-gherkin-refine"><img src="https://agentmods.dev/badge/skills/aiocean/claude-plugins/aio-gherkin-refine.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 | $0.00043 | $0.00827 |
| Opus 5.5 | $0.00017 | $0.00331 |
| Sonnet 5.5 | $0.00009 | $0.00165 |
| Haiku 4.5 | $0.00004 | $0.00083 |
Grade A, and why
aio-gherkin-refine 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 1mo 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
aio-gherkin-refine
Transforms vague requests into clear Gherkin scenarios and reviews existing Gherkin for quality. Serves developers, BA/QA/Product, and Claude agents.
Mode Detection
REVIEW mode — when user pastes existing Gherkin, says "review", "improve", "check my scenarios":
- Load
references/review-checklist.md - Rate each scenario: ✅ Good / ⚠️ Needs Work / ❌ Rewrite
- Show before/after for each issue with explanation
- End with quality score and top 3 improvements
WRITE mode — when request is new, ambiguous, or user says "write", "create", "draft":
- Load
references/mental-models.md— use Example Mapping to extract rules/examples/questions - Load
references/writing-guide.md— apply declarative style and naming conventions - Draft Feature file with happy path + at least one failure scenario
- Present to user for confirmation before implementing
When in doubt: default to WRITE mode, offer REVIEW as an option.
Example Mapping Quick-Start (WRITE mode)
Before writing any Gherkin, run a mini Example Mapping session:
Story: [what the user wants]
Rule 1: [business rule derived from story]
Example: [concrete example that tests this rule]
Example: [edge case]
Rule 2: [another rule]
Example: [...]
Questions: [anything unclear — ask user before proceeding]
If you have more than 4 examples for a single rule, the rule is too broad — split it.
Output Format
Always use fenced code blocks with gherkin syntax:
Feature: [noun phrase — what capability this describes]
Background: # only if ALL scenarios share this context
Given [shared precondition]
Scenario: [complete sentence describing the rule being tested]
Given [initial context — who, what state]
When [the action that triggers behavior]
Then [the observable outcome]
Scenario: [failure or alternative case]
Given [different context]
When [same or different action]
Then [different outcome]
After presenting Gherkin, always ask: "Does this capture what you need? Any scenarios to add or modify?"
What ships with it
4 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.
- 1mo ago First seen · 84 lines · 43 tokens per session scan A 62d3075f2e03
aio-gherkin-refine is a skill published in the GitHub repository aiocean/claude-plugins (4 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 827 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
plan-pipeline-execute
Execute a validated plan: worktree isolation, TDD scaffolding, level-based parallel agents, quality gate with smoke test, PR creation and merge. Handles everything through to merged PR.
test-first
Use when implementing any feature, bugfix, or refactor that has a testable outcome. Activate for keywords like "TDD", "test-first", "red-green", "write the test first", "implement ", "fix ". Enforces the red-green-refactor discipline -- write a failing test, make it pass with the smallest change, refactor with tests…
qa
Systematic QA testing of a web application: diff-aware, tiered, with fix-and-verify loop.
plan-pipeline-eng-review
Engineering architecture gate: lock architecture, diagrams, edge cases, and test matrix before writing implementation code.
ci-all
Full CI pipeline: run local tests, type check, push branch, and return the pipeline URL. The only command you need before opening a PR.
ci-tests
Run the test suite for the current repo, auto-detecting Python (pytest/uv), Node (vitest/pnpm), or Rust (cargo test).