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 SebastienDegodez/copilot-instructions --skill gherkin-gategit clone --depth 1 https://github.com/SebastienDegodez/copilot-instructionsWrote 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/sebastiendegodez/copilot-instructions/gherkin-gate)<a href="https://agentmods.dev/skills/sebastiendegodez/copilot-instructions/gherkin-gate"><img src="https://agentmods.dev/badge/skills/sebastiendegodez/copilot-instructions/gherkin-gate/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/sebastiendegodez/copilot-instructions/gherkin-gate"><img src="https://agentmods.dev/badge/skills/sebastiendegodez/copilot-instructions/gherkin-gate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00033 | $0.00503 |
| Opus 5 | $0.00016 | $0.00251 |
| Sonnet 5 | $0.00007 | $0.00101 |
| Haiku 4.5 | $0.00003 | $0.00050 |
Grade A, and why
gherkin-gate 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gherkin Gate
Overview
Capture observable behavior in business language before any test or code is written. User approval is the mandatory gate.
Hard rule: No test, no task, no implementation until scenarios are approved.
Writing Scenarios
Write 1-3 scenarios in Given/When/Then:
GIVEN [precondition in business language].
WHEN [action in business language].
THEN [observable outcome in business language].
Each scenario should be independent and verifiable in isolation. Cover the main success path and 1-2 key edge cases.
Spec-Leakage Rule (CRITICAL)
Scenarios must describe external observables only. Never reference implementation details:
| Forbidden | Allowed |
|---|---|
| Class names, method names | Business actions and actors |
| Repository, database, tables | Data in business terms |
| HTTP endpoints, status codes | Business outcomes |
| Internal state, variables | Observable system behavior |
❌ BAD: GIVEN the EligibilityPolicy has empty rules.
✅ GOOD: GIVEN no eligibility rules are configured.
❌ BAD: THEN the handler returns a 200 OK response.
✅ GOOD: THEN the request is accepted.
❌ BAD: WHEN I call POST /api/eligibility.
✅ GOOD: WHEN checking eligibility for the user.
Approval Gate
- Present scenarios clearly labeled: "Gherkin Scenarios — awaiting approval"
- WAIT for explicit user approval before proceeding
- If rejected: revise scenarios and repeat from step 1
- Only after approval: proceed to test writing or task planning
This gate is not skippable — even for "small" features.
Common Mistakes
| Mistake | Fix |
|---|---|
| Skipping scenarios for "trivial" features | Write 1 scenario minimum — even simple features benefit |
| Implementation details in scenarios | Business language only in Given/When/Then |
| Proceeding before explicit approval | "ok" or "proceed" counts, silence does not |
| More than 3 scenarios up front | Start with main success path, add edge cases after RED |
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 · 63 lines · 33 tokens per session scan A 1a4057c39a7d
gherkin-gate is a skill published in the GitHub repository SebastienDegodez/copilot-instructions (193 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 503 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
migrate-mstest-v3-to-v4
Use this skill before answering, planning, or editing any MSTest 3.x-to-4.x upgrade or post-upgrade failure. Triggers include "MSTest v4 breaking changes"; CS0507/CS0103/CS1061/CS1615; ExecuteAsync, CallerInfo, DisplayName, or custom TestMethodAttribute; ClassCleanupBehavior; ContainsKey; ThrowsExactly or…
migrate-xunit-to-mstest
Convert .NET tests from xUnit.net v2/v3 to MSTest v4 while preserving VSTest or MTP. Use for replacing xunit packages, Fact/Theory/InlineData/MemberData, assertions, IClassFixture/ICollectionFixture, ITestOutputHelper, TestContext cancellation, traits/Owner, skips, timeouts, and xUnit parallelization. Also use when a…
migrate-xunit-to-xunit-v3
Migrate .NET test projects from xUnit.net v2 to xunit.v3 and fix v3 breaks. Use for package/CPM conversion, OutputType=Exe, preserving the VSTest or MTP runner (including projects currently using YTest.MTP.XUnit2), incompatible TFMs, async void tests, string-to-Type attributes, custom Fact/Theory/BeforeAfterTest…
crap-score
Calculates CRAP (Change Risk Anti-Patterns) for a named .NET method, class, or file. USE FOR: explicit CRAP calculation or coverage-and-complexity risk within that named target, including which tests to prioritize. DO NOT USE FOR: project-wide coverage/CRAP, plateaus, or project-wide blockers/priorities…
nunit
Write, run, or repair .NET tests that use NUnit. Use when a repo uses NUnit, [Test], [TestCase], [TestFixture], or NUnit3TestAdapter for VSTest or Microsoft.Testing.Platform execution. USE FOR: writing or reviewing NUnit tests; using [Test], [TestCase], [TestFixture], [SetUp], [TearDown] attributes; configuring…
playwright-visual-testing
Add, repair, or review Playwright visual regression tests for browser-facing .NET apps, including screenshot baselines, Pixelmatch thresholds, deterministic rendering, and GitHub Actions artifacts. USE FOR: toHaveScreenshot, page.screenshot visual checks, Pixelmatch/pngjs comparison scripts, visual baseline updates…