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 acolomba/pi-claude-marketplace --skill cucumbergit clone --depth 1 https://github.com/acolomba/pi-claude-marketplaceWrote 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/acolomba/pi-claude-marketplace/cucumber)<a href="https://agentmods.dev/skills/acolomba/pi-claude-marketplace/cucumber"><img src="https://agentmods.dev/badge/skills/acolomba/pi-claude-marketplace/cucumber/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/acolomba/pi-claude-marketplace/cucumber"><img src="https://agentmods.dev/badge/skills/acolomba/pi-claude-marketplace/cucumber.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 | $0.00078 | $0.00648 |
| Opus 5.5 | $0.00031 | $0.00259 |
| Sonnet 5.5 | $0.00016 | $0.00130 |
| Haiku 4.5 | $0.00008 | $0.00065 |
Grade A, and why
cucumber 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 3d 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 — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cucumber behavioral tests
Behavioral tests drive the real code through its public surface against local stand-ins for every external service. No scenario needs an account, hardware, the public network, or the user's home directory. A scenario must fail when the behavior in its title breaks: a Then that checks part of a result, or a table that lists a sample of the rows, lets a wrong implementation through.
Read before you act
| When you | Read |
|---|---|
plan features, or add, move, or name any file under features/ |
.agents/skills/cucumber/rules/layout.md |
write or change a .feature file |
.agents/skills/cucumber/rules/features.md |
| write or change a step module | .agents/skills/cucumber/rules/steps.md |
| write or change the world, a hook, a parameter type, a fake, a driver, or a fixture | .agents/skills/cucumber/rules/world-and-stand-ins.md |
Review
A review reads the rules files the change touches; a revision produces the form they describe. Two questions come first:
- Would a plausible wrong implementation still pass the scenario? A scenario that checks part of a result is the highest-value finding.
- Can a reader understand the scenario without opening a step definition? A step that hides the behavior behind an implementation name, or a scenario whose point lives only in a step's code, is a finding.
Run npm run test:cucumber and require every scenario to pass; a failing, undefined, ambiguous, or pending step is a finding. Run npm run check:features, which is part of npm run check:static, and require it to pass. It fails on an unused, undefined, or ambiguous step, and on the layout and feature-file rules it can check. Do not use the usage report of the cucumber CLI (npx cucumber-js --dry-run --format usage) instead. That report does not check the layout and feature-file rules. The gate also dry-runs every scenario, even if a future cucumber.json excludes a tag again, so a step that only excluded rows use still counts as used (D-09).
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.
- 3d ago Changed · +10 tokens per session 5acaedf62c75
- 7d ago First seen · 30 lines · 68 tokens per session scan A d09460a42982
cucumber is a skill published in the GitHub repository acolomba/pi-claude-marketplace (28 stars, last pushed today), licensed MIT. It adds 78 tokens to every session and 648 once invoked, about $0.0003 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 2026-10-23.
Other skills, from other repositories
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
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.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
critique
Adversarial design critique of the current work. Render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.