Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/trebormc/drupal-ai-agentsnpx agentmods add skills/trebormc/drupal-ai-agents/drupal-behat-testWrote 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/trebormc/drupal-ai-agents/drupal-behat-test)<a href="https://agentmods.dev/skills/trebormc/drupal-ai-agents/drupal-behat-test"><img src="https://agentmods.dev/badge/skills/trebormc/drupal-ai-agents/drupal-behat-test/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/trebormc/drupal-ai-agents/drupal-behat-test"><img src="https://agentmods.dev/badge/skills/trebormc/drupal-ai-agents/drupal-behat-test.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 | $0.00158 | $0.03528 |
| Opus 5.5 | $0.00063 | $0.01411 |
| Sonnet 5.5 | $0.00032 | $0.00706 |
| Haiku 4.5 | $0.00016 | $0.00353 |
Grade A, and why
drupal-behat-test 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 — 448 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Drupal Behat Test
What It Is
Behat is a BDD (Behavior-Driven Development) framework that uses natural language (Gherkin) to define test scenarios. The Drupal Extension provides predefined steps for interacting with Drupal: create users, nodes, terms, navigate, fill forms, etc.
When to Use
- The project already uses Behat (has
behat.yml) - Acceptance tests that the client can read are needed
- Complete E2E flows (registration, purchase, content publishing)
- Behavior tests in natural language
- When the QA team does not know PHP but needs to write/read tests
When NOT to Use
- Tests for services or internal logic -> Kernel test
- Simple form tests -> Functional test
- If the project does not have Behat and there is no reason to add it -> Playwright
- Visual regression -> Playwright
Setup -- Dependencies
ssh web composer require --dev drupal/drupal-extension behat/mink-selenium2-driver behat/mink-browserkit-driver
For Drupal 10/11, use drupal/drupal-extension:^5.
Configuration -- behat.yml
WARNING — BEFORE copying: drupal_root: 'web' is a placeholder. Check the real docroot with grep "^docroot:" .ddev/config.yaml and set drupal_root to that value ($DDEV_DOCROOT).
default:
suites:
default:
contexts:
- Drupal\DrupalExtension\Context\DrupalContext
- Drupal\DrupalExtension\Context\MinkContext
- Drupal\DrupalExtension\Context\MessageContext
- Drupal\DrupalExtension\Context\DrushContext
- FeatureContext
extensions:
Drupal\MinkExtension:
# browserkit_http is the headless driver (goutte is deprecated in Mink Extension)
browserkit_http: ~
selenium2:
wd_host: 'http://127.0.0.1:4444/wd/hub'
capabilities:
browser: chrome
extra_capabilities:
# goog:chromeOptions works on Drupal 10 and 11 (mandatory on 11)
goog:chromeOptions:
args:
- '--disable-gpu'
- '--headless'
- '--no-sandbox'
# Always HTTP in DDEV (self-signed certs break HTTPS)
base_url: 'http://localhost'
ajax_timeout: 10
Drupal\DrupalExtension:
api_driver: 'drupal'
drupal:
drupal_root: 'web'
region_map:
content: '.region-content'
header: '.region-header'
sidebar_first: '.region-sidebar-first'
selectors:
message_selector: '.messages'
error_message_selector: '.messages--error'
success_message_selector: '.messages--status'
warning_message_selector: '.messages--warning'
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 · 448 lines · 158 tokens per session scan A ad365099a173
drupal-behat-test is a skill published in the GitHub repository trebormc/drupal-ai-agents (11 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 158 tokens to every session and 3,528 once invoked, about $0.0006 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 2026-08-31.
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.