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-test-suite-auditWrote 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-test-suite-audit)<a href="https://agentmods.dev/skills/trebormc/drupal-ai-agents/drupal-test-suite-audit"><img src="https://agentmods.dev/badge/skills/trebormc/drupal-ai-agents/drupal-test-suite-audit.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 5.1 | $0.00198 | $0.01452 |
| Opus 5 | $0.00099 | $0.00726 |
| Sonnet 5 | $0.00040 | $0.00290 |
| Haiku 4.5 | $0.00020 | $0.00145 |
Grade A, and why
drupal-test-suite-audit 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 7d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Drupal Test-Suite Audit
Refactors an existing suite for value and maintainability. Measure BEFORE touching
anything; verify (unit+kernel+functional, PHPCS, PHPStan) after EVERY batch. All commands
via ssh web.
Step 1 — Quantitative survey (no edits yet)
# Copy-paste tests: same test-method name across many files
grep -rh "public function test" $DDEV_DOCROOT/modules/custom --include=*Test.php | sort | uniq -c | sort -rn
# Anonymous-class doubles per file
grep -rln "new class" $DDEV_DOCROOT/modules/custom --include=*Test.php
Classify each new class: those that simulate DB/entity queries
(fetchAll|fetchField|->select(|StatementInterface) → convert to kernel; those that stub
binary execution → legitimate, keep. Count duplicated private helpers
(invokeProtectedMethod, setProtectedProperty) and confirm the bodies are byte-identical
before planning a shared trait.
Step 2 — Delete tautological tests (with the guard)
Candidates: per-plugin tests re-asserting BASE-class behavior already covered by a
base-class test (label/description/output-dir fallbacks, default checkRequirements(),
passthrough methods), and attribute-string assertions against copies of themselves.
GUARD (mandatory): before deleting a "default behavior" test, grep whether the class under test OVERRIDES that method. If it does, the test exercises the override's default branch — keep it.
Step 3 — Unify scaffolding
Move byte-identical reflection helpers into ONE trait in the base module's test namespace
(Drupal\Tests\<module>\Unit\...Trait); submodule tests can use it because core's bootstrap
registers every module's test namespace. Replace only exact-match bodies; leave variants
alone (a same-named method legally overrides the trait, so partial adoption is safe).
Step 4 — Kernel smoke tests: the DI-wiring gap
Unit tests that new a plugin and inject deps via reflection NEVER execute create() — a
typo'd service ID passes the whole unit suite and explodes in production. Generate an
abstract ...KernelTestBase with 4 generic tests:
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.
- 7d ago First seen · 123 lines · 198 tokens per session scan A d523ef35ff40
drupal-test-suite-audit is a skill published in the GitHub repository trebormc/drupal-ai-agents (10 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 198 tokens to every session and 1,452 once invoked, about $0.0010 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
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.