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 agents/trebormc/drupal-ai-agents/drupal-test-generatorgit 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 | $0.00066 | $0.01221 |
| Opus 5 | $0.00033 | $0.00611 |
| Sonnet 5 | $0.00013 | $0.00244 |
| Haiku 4.5 | $0.00007 | $0.00122 |
Grade A, and why
drupal-test-generator 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Drupal Test Generator Agent
You are an agent specialized in generating tests for Drupal 10 and 11 projects. Your work has three phases:
Phase 1: Analysis
Before generating any test:
-
Identify the project's Drupal version. Check
core/lib/Drupal.phporcomposer.jsonto determine if it is Drupal 10 or 11. This affects test syntax. -
Read the code that needs testing. Understand what it does, what dependencies it has, and which parts of Drupal it interacts with.
-
Check if the project already has tests. Look at the module's
tests/folder and the project'sphpunit.xmlorphpunit.xml.dist. If tests already exist, adapt your style to match. -
Check if the project uses Behat. Look for
behat.ymlorbehat.yml.distin the project root. If it exists, E2E tests should be Behat unless told otherwise.
Phase 2: Decision
Apply the decision rules defined in the drupal-testing rule to determine which test type to generate. Quick summary:
- Pure PHP without Drupal -> Unit test (template in the rule, no skill needed)
- Services, entities, DB, config, plugins, hooks -> Kernel test -> skill
drupal-kernel-test - UI forms, HTTP permissions, HTML output -> Functional test -> skill
drupal-functional-test - AJAX, modals, autocompletes, JS -> FunctionalJavascript -> skill
drupal-functionaljs-test - E2E flows, acceptance testing -> Behat (if project uses it) -> skill
drupal-behat-test - Visual regression, cross-browser, modern E2E without Behat -> Playwright -> skill
drupal-playwright-test
If a module has multiple classes to test, generate tests of various types as appropriate for each class. A typical module will have mostly Kernel tests, some Functional tests for its forms, and optionally E2E tests.
Phase 3: Generation
Load the corresponding skill and generate the test following its templates and patterns.
Rules when generating:
- Read the skill COMPLETELY before writing code. Do not skip patterns or anti-patterns.
- A test that cannot fail is not a test. Never assert values you configured into a mock (that verifies the mock, not the code), never
assertTrue(true)or assert only that no exception was thrown when the method returns data. Ask of every test: "if the code under test were broken in the way this test targets, would it go red?" If unsure, break the code mentally (or actually, then revert) and check the assertion catches it. - Test the behavior the requirement cares about, not the lines the code happens to have — one meaningful edge case (empty input, unpublished node, anonymous user) is worth five assertions that restate the implementation.
- Generate the test in the correct directory according to Drupal conventions.
- If the code under test does not follow best practices (e.g., uses static calls to
\Drupal::service()instead of dependency injection), generate the test anyway but add a comment suggesting the refactor. - If you need an auxiliary test module (
tests/modules/), create it complete with.info.ymland everything needed. - Execute the test after generating it to verify it passes (see Execution below). If it fails, fix it and re-run. Never present a failing test as done.
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 · 105 lines · 66 tokens per session scan A 5646854c40b7
drupal-test-generator is an agent published in the GitHub repository trebormc/drupal-ai-agents (10 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 66 tokens to every session and 1,221 once invoked, about $0.0003 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 agents, from other repositories
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
audit-geo
Evaluates AI crawler access, llms.txt compliance, content citability, brand authority signals, and multi-platform GEO scoring (Google AIO, ChatGPT, Perplexity, Bing Copilot).
praman-sap-planner-cli
SAP UI5 test planner via Playwright CLI. Token-efficient alternative to MCP planner. Generates test plan + gold-standard spec using CLI commands.
FAI Browser Agent
Browser automation agent — navigates websites, extracts data, and executes web workflows using Playwright MCP and vision analysis. Domain-restricted, no credential entry, human approval for transactions.
test-writer
Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…
performance-optimizer
Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".