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/trebormc/drupal-ai-agents/drupal-testingnpx skills add trebormc/drupal-ai-agents --skill drupal-testinggit clone --depth 1 https://github.com/trebormc/drupal-ai-agentsWhat 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 | $0.00137 | $0.01472 |
| Opus 5 | $0.00068 | $0.00736 |
| Sonnet 5 | $0.00027 | $0.00294 |
| Haiku 4.5 | $0.00014 | $0.00147 |
Grade A, and why
drupal-testing 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 2d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Drupal Testing — Orchestrator
This skill coordinates test generation for Drupal 10/11 projects. It analyzes the code under test and delegates to the appropriate specialized skill.
Decision Flow
See the drupal-testing rule for the complete decision tree. Quick summary:
| Code Type | Test Type | Skill |
|---|---|---|
| Pure PHP, no Drupal deps | Unit | Template in drupal-testing rule |
| Advanced unit mocking | Unit | drupal-unit-test |
| Services, entities, DB, config, plugins, hooks | Kernel | drupal-kernel-test |
| UI forms, HTTP permissions, HTML output | Functional | drupal-functional-test |
| AJAX, modals, autocompletes, JS | FunctionalJavascript | drupal-functionaljs-test |
| E2E flows, acceptance (Behat project) | Behat | drupal-behat-test |
| Visual regression, cross-browser, E2E (no Behat) | Playwright | drupal-playwright-test |
Tie-breakers (apply them, do not deliberate): touches any Drupal service or needs >4-5 mocks → Kernel. Assertion about logic/data, not HTML/HTTP → Kernel over Functional. No-JS behavior → never FunctionalJS. behat.yml exists → Behat, else Playwright. Pick ONE type per behavior.
Workflow
- Detect Drupal version — check
core/lib/Drupal.phporcomposer.json - Read the code — understand dependencies and Drupal API usage
- Check existing tests — look at
tests/folder, match existing style - Apply decision tree — use the
drupal-testingrule - Load specialized skill — delegate to the appropriate skill
- Execute and verify — run the test, fix if it fails
Test Execution Commands
Replace MODULE with the module machine name.
STEP 1 — Pick the config form. Run ONCE, then use the matching form for the whole session:
ssh web test -f phpunit.xml && echo "ROOT" || echo "CORE"
# Form ROOT (project phpunit.xml exists — it already sets env vars):
ssh web ./vendor/bin/phpunit $DDEV_DOCROOT/modules/custom/MODULE/tests/src/Unit
ssh web ./vendor/bin/phpunit $DDEV_DOCROOT/modules/custom/MODULE/tests/src/Kernel
ssh web ./vendor/bin/phpunit $DDEV_DOCROOT/modules/custom/MODULE/tests/src/Functional
ssh web ./vendor/bin/phpunit $DDEV_DOCROOT/modules/custom/MODULE/tests/src/FunctionalJavascript
# Form CORE (no project phpunit.xml — Drupal core config + explicit env vars):
ssh web env SIMPLETEST_DB=mysql://db:db@db/db SIMPLETEST_BASE_URL=http://localhost \
./vendor/bin/phpunit -c $DDEV_DOCROOT/core $DDEV_DOCROOT/modules/custom/MODULE/tests/src/Unit
# Single test method (add --filter before the path; works with both forms)
ssh web ./vendor/bin/phpunit --filter testMethodName $DDEV_DOCROOT/modules/custom/MODULE/tests/src/Unit
# Coverage (requires Xdebug; report written to /tmp/coverage in the web container)
ssh web env XDEBUG_MODE=coverage ./vendor/bin/phpunit --coverage-html /tmp/coverage \
$DDEV_DOCROOT/modules/custom/MODULE/tests/src/Unit
# Behat (uses behat.yml, not phpunit.xml)
ssh web ./vendor/bin/behat --config=behat.yml
# Playwright (runs on the HOST — ask the user to run: npx playwright test)
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.
- 2d ago First seen · 124 lines · 137 tokens per session scan A 34cfccaba278
drupal-testing is a skill published in the GitHub repository trebormc/drupal-ai-agents (10 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 137 tokens to every session and 1,472 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
traceway-setup
Analyze and instrument repositories for Traceway observability. Use when the user wants to plan, add, migrate, or verify Traceway or OpenTelemetry monitoring for backend, browser, full-stack, mobile or iOS, or AI-agent software, including project topology and user-approved setup-plan creation. Backends use OTLP/HTTP…
southwest
Search Southwest Airlines fares and points pricing via Patchright browser automation. SW is not in any GDS or API. Covers all fare classes, Companion Pass value, and fare drop monitoring.