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 agentmods add skills/onsi/ginkgo/filteringnpx skills add onsi/ginkgo --skill filteringgit clone --depth 1 https://github.com/onsi/ginkgoWrote 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/onsi/ginkgo/filtering)<a href="https://agentmods.dev/skills/onsi/ginkgo/filtering"><img src="https://agentmods.dev/badge/skills/onsi/ginkgo/filtering.svg" alt="Measured on agentmods" 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 | $0.00117 | $0.01768 |
| Opus 5 | $0.00059 | $0.00884 |
| Sonnet 5 | $0.00023 | $0.00354 |
| Haiku 4.5 | $0.00012 | $0.00177 |
Grade A, and why
filtering 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 4d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Filtering specs: running a subset
Ginkgo offers many ways to run fewer specs — ad-hoc (Pending/Skip/Focus) and structured (labels, semver, file/description filters). They combine by a strict precedence (see bottom). Decorator specifics live in ginkgo:decorators; label-driven CI in ginkgo:ci. Docs: https://onsi.github.io/ginkgo/#filtering-specs.
Pending — compile-time skip, uncoercible
Marks a spec/container as under development. Nothing can override Pending and make it run — not focus, not labels.
It("needs work", Pending, func() { ... })
It("placeholder", Pending) // pending specs need no closure
PDescribe("not ready", func() { ... }) // == Describe(..., Pending); X-prefix is identical
PIt(...) / XIt(...) / PEntry(...)
Pending specs don't fail the suite. ginkgo --fail-on-pending makes them fail CI — a policy that pending specs shouldn't be committed. Pending is compile-time only; you cannot make a spec pending at runtime — for that, use Skip.
Skip — runtime skip
Call Skip("reason") from any subject or setup node to skip during the run phase. It panics to halt the spec (like Fail) and records the reason; it does not fail the suite (even skipping every spec passes).
It("if it can", func() {
if !someCondition { Skip("special condition wasn't met") }
...
})
Scope matters: in a BeforeEach it skips the current spec; in a BeforeAll it skips all specs in the Ordered container; in a BeforeSuite it skips the entire suite. You cannot call Skip in a container body — it only applies during the run phase.
Focus — programmatic, for iterating (don't commit it)
When any spec is focused, Ginkgo runs only focused specs.
FIt("just me", func() { ... }) // or It(..., Focus, ...)
FDescribe(...) / FContext(...) / FEntry(...)
Child focus unfocuses focused ancestors. F an inner It inside an FDescribe and only that It runs — matches how you narrow while debugging.
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.
- 4d ago First seen · 119 lines · 117 tokens per session scan A 2c3e0be56fae
filtering is a skill published in the GitHub repository onsi/ginkgo (9,050 stars, last pushed 24d ago), licensed MIT. It adds 117 tokens to every session and 1,768 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 2026-08-30.
Other skills, from other repositories
nunit-testing
Use when writing or modifying tests in NUnit's own test projects, or when making a behavioral change to production code that needs test coverage. Covers test structure, attribute choice, helper visibility, platform guards, and which test projects are real.
nunit-build-infra
Use when editing .csproj, .nuspec, Directory.Build.props, Directory.Build.targets, Directory.Packages.props, the Cake build (build.cake, build.ps1, build.sh), or GitHub Actions workflows. Covers central package management, MinVer-driven versioning, the props-vs-targets split, and nuspec/csproj consistency.
nunit-code-style
Use when writing or modifying C# method bodies, type declarations, or non-trivial logic in NUnit source. Covers NUnit's taste-and-judgment conventions — exception construction, simplification, naming intent, StringComparison, non-null check form, and var usage — that aren't already caught at build time.
nunit-api-design
Use when adding or modifying public API surface in NUnit — new or changed constraints, attributes, assertions, helpers, or any type/member visibility change. Covers the conventions NUnit maintainers enforce for types that ship to consumers of the framework.
pie-testing
Start, stop, and query Play-In-Editor (PIE) sessions for runtime testing of Blueprints, gameplay logic, widgets, AI, and any in-game behavior. Use when the user asks you to "play", "test", "run", "PIE", "start/stop the game", or otherwise needs a live game world to validate changes.
review
Adversarial senior review of the spec before any code is written. Constructs a skeptical reviewer whose authority comes from the codebase, §R research, and live best-practice — then tries to REFUTE the spec, not rubber-stamp it. Every finding cites evidence (file:line or source); unverifiable ones are flagged.…