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/abderrahimghazali/drupal-boost/drupal-securitynpx skills add abderrahimghazali/drupal-boost --skill drupal-securitygit clone --depth 1 https://github.com/abderrahimghazali/drupal-boostWhat 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 | $0.00043 | $0.01022 |
| Opus 5 | $0.00022 | $0.00511 |
| Sonnet 5 | $0.00009 | $0.00204 |
| Haiku 4.5 | $0.00004 | $0.00102 |
Grade A, and why
drupal-security 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 yesterday.
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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Drupal Security Best Practices
XSS Prevention
Twig (auto-escaping ON by default)
{{ variable }}— safe, auto-escaped{{ variable|raw }}— DANGEROUS, bypasses escaping. Only use for pre-sanitized markup{% set markup %}...{% endset %}— auto-escaped when rendered{{ variable|striptags }}— strips HTML tags
PHP
- Use
$this->t()ornew TranslatableMarkup()for user-facing strings - Use
Xss::filter()for user HTML that needs limited tags - Use
Html::escape()for plain text output - Use
#plain_textrender element for untrusted text - NEVER use
Markup::create()with user input - NEVER use
#markupwith unsanitized content
SQL Injection Prevention
// SAFE: parameterized query
$result = $connection->select('users', 'u')
->fields('u', ['name'])
->condition('status', 1)
->execute();
// SAFE: placeholder in query()
$result = $connection->query('SELECT name FROM {users} WHERE uid = :uid', [':uid' => $uid]);
// DANGEROUS: string concatenation
$result = $connection->query("SELECT * FROM {users} WHERE name = '$name'"); // NEVER DO THIS
Access Control
Route Permissions
my_route:
path: '/admin/my-page'
requirements:
_permission: 'administer my module'
Entity Access
- Always call
->accessCheck(TRUE)on entity queries - Implement
EntityAccessControlHandlerfor custom entities - Use
AccessResult::allowed(),::forbidden(),::neutral()with proper cacheability
// REQUIRED in Drupal 10+
$nodes = \Drupal::entityTypeManager()
->getStorage('node')
->getQuery()
->accessCheck(TRUE) // MANDATORY
->condition('status', 1)
->execute();
Permission Definitions
# MODULE_NAME.permissions.yml
administer my module:
title: 'Administer My Module'
description: 'Full admin access to My Module settings.'
restrict access: true # Only for permissions that allow site takeover
view my content:
title: 'View My Content'
description: 'View custom content managed by My Module.'
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 128 lines · 43 tokens per session scan A 7ca0fa6c5df1
drupal-security is a skill published in the GitHub repository abderrahimghazali/drupal-boost (1 stars, last pushed 5mo ago), licensed MIT. It adds 43 tokens to every session and 1,022 once invoked, about $0.0002 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
cms-detection
Identify CMS, frameworks, and server technology stacks on live hosts.
angular-developer
Generates Angular code and provides architectural guidance. Trigger when creating projects, components, or services, or for best practices on reactivity (signals, linkedSignal, resource), forms, dependency injection, routing, SSR, accessibility (ARIA), animations, styling (component styles, Tailwind CSS), testing, or…
drupal-htmx
HTMX in Drupal 11.3+ core — the Htmx PHP fluent builder, dynamic forms with swapOob, partial routes with htmxroute, response headers, and Drupal.behaviors integration. Use when building interactive UI without full-page reloads using Drupal's native HTMX support.
drupal-search-api
Search API — index configuration, boost processors, field types, number field boosting, engagement metrics, and reindexing workflows.
drupal-contrib-mgmt
Drupal contrib module upgrade triage — Drupal.org issue queue research, local patch creation (git diff), composer-patches workflows, Drupal 11 compatibility via coreversionrequirement, Drupal Lenient handling, and upgradestatus analysis. Not for generic Composer dependency management.
drupal-migrations
Drupal migration API — D7-to-D11 upgrades, CSV imports, JSON API imports, and custom source/process/destination plugins.