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.
git clone --depth 1 https://github.com/edutrul/drupal-aiWrote 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/commands/edutrul/drupal-ai/performance-check)<a href="https://agentmods.dev/commands/edutrul/drupal-ai/performance-check"><img src="https://agentmods.dev/badge/commands/edutrul/drupal-ai/performance-check/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/commands/edutrul/drupal-ai/performance-check"><img src="https://agentmods.dev/badge/commands/edutrul/drupal-ai/performance-check.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 | $0.00010 | $0.01536 |
| Opus 5.5 | $0.00004 | $0.00614 |
| Sonnet 5.5 | $0.00002 | $0.00307 |
| Haiku 4.5 | $0.00001 | $0.00154 |
Grade A, and why
performance-check 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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Drupal Performance Check
Analyze site performance configuration and identify optimization opportunities.
Usage: /performance-check [module_path]
If a module path is provided, focus analysis on that module's code. Otherwise, check site-wide performance settings and scan all custom modules.
Path note: Commands below use
docroot/as the web root. Adjust to match your project layout (common alternatives:web/,html/). Similarly,docroot/modules/custom/assumes the standard custom modules location — update if yours differs.
Performance Analysis Steps
1. Check Caching Configuration
# Page cache
drush config:get system.performance cache.page.max_age
# CSS/JS aggregation
drush config:get system.performance css.preprocess
drush config:get system.performance js.preprocess
# Twig cache (should NOT be disabled in production)
drush php:eval "var_dump(\$settings['cache']['bins']['render'] ?? 'default');"
Production should have:
cache.page.max_age> 0 (e.g., 3600 for 1 hour)css.preprocess= truejs.preprocess= true- No cache bins disabled
2. Check Cache Backends
# What cache backends are configured?
drush php:eval "print_r(\$settings['cache']['default'] ?? 'database');"
# List all cache bins
drush cache:list
Recommendations:
- Use Redis or Memcache for production (not database)
- Consider separate backends for different cache bins
3. Review BigPipe Status
drush pm:list --filter=big_pipe
drush config:get big_pipe.settings
BigPipe should be enabled for authenticated user performance.
4. Check Database Performance
# Show slow query log (if enabled)
drush watchdog:show --filter="type=php" --severity=warning --count=20
# Check database size
drush sql:query "SELECT table_name, round(((data_length + index_length) / 1024 / 1024), 2) AS 'Size (MB)' FROM information_schema.tables WHERE table_schema = DATABASE() ORDER BY (data_length + index_length) DESC LIMIT 10;"
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 · 226 lines · 10 tokens per session scan A d68dcc73f343
performance-check is a command published in the GitHub repository edutrul/drupal-ai (72 stars, last pushed 4mo ago), licensed MIT. It adds 10 tokens to every session and 1,536 once invoked, about $0.0000 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 2026-08-30.
Other commands, from other repositories
synthesise-reviews
Deduplicate and reconcile multiple completed review reports into one prioritised revision plan with conflicts and dependencies made explicit. Use when parallel reviewers have returned findings that need a single action sequence. Not for running the reviews; use $review-cluster.
firebase-publish
Create or reuse a Firebase project, configure Hosting, and deploy the current static site. Never deletes.
auditoria-legal
Grupo: Trabajo con el framework En una frase: Auditoría de cumplimiento legal del producto — territorio, evidencia y lo que el código no cubre. Cuándo: Antes de publicar una app o web: registro, cookies, analítica, emails, suscripciones, contenido de usuarios. Quién: Cualquier operador del repo.
prep-role
Deep prep for a specific role's interview process. The user wants to know what to expect, how to win, and what kills candidates at their level.
scan
Scan AWS account for cost optimization.
setup
Diagnose-first project setup with state machine — scans, confirms, interviews, writes.