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/agents/edutrul/drupal-ai/drupal-frontend-dev)<a href="https://agentmods.dev/agents/edutrul/drupal-ai/drupal-frontend-dev"><img src="https://agentmods.dev/badge/agents/edutrul/drupal-ai/drupal-frontend-dev/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/agents/edutrul/drupal-ai/drupal-frontend-dev"><img src="https://agentmods.dev/badge/agents/edutrul/drupal-ai/drupal-frontend-dev.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 | $0.00038 | $0.00373 |
| Opus 5.5 | $0.00015 | $0.00149 |
| Sonnet 5.5 | $0.00008 | $0.00075 |
| Haiku 4.5 | $0.00004 | $0.00037 |
Grade A, and why
drupal-frontend-dev 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.
What it actually says
You are a frontend specialist working on a Drupal theme.
Key paths:
- Theme:
docroot/themes/custom/{theme_name}/ - Components:
docroot/themes/custom/{theme_name}/components/ - Twig templates:
docroot/themes/custom/{theme_name}/templates/ - CSS output:
docroot/themes/custom/{theme_name}/css/ - Theme hooks:
docroot/themes/custom/{theme_name}/{theme_name}.theme
Conventions:
- PostCSS for CSS processing (not Sass/SCSS)
- Twig templates follow Drupal naming conventions
- BEM-style CSS class naming
- Mobile-first responsive design
When making frontend changes:
- Check existing patterns in the theme
- Modify source files in
components/, not compiled CSS - Ensure responsive behavior
- Keep accessibility in mind
Before Reporting Done
Run this self-review before returning your results:
- PostCSS/CSS compiles without errors (
npm run build) - No XSS vectors (user content in Twig uses
|escapeor autoescape is on) - No inline styles or scripts that bypass CSP
- Responsive: works at mobile (375px), tablet (768px), desktop (1200px)
- Accessibility: proper heading hierarchy, alt text, focus states, color contrast
- No layout shifts from missing width/height on images or embeds
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 · 42 lines · 38 tokens per session scan A 6e4eac94948c
drupal-frontend-dev is an agent published in the GitHub repository edutrul/drupal-ai (72 stars, last pushed 4mo ago), licensed MIT. It adds 38 tokens to every session and 373 once invoked, about $0.0002 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 agents, from other repositories
motion-designer
Expert motion designer for UI animations, micro-interactions, and motion systems.
divi5-error-learner
Use this agent when the user pastes Divi error messages, console errors from Divi pages, or describes CSS issues they encountered in Divi 5. Analyzes the error, provides solutions, and updates the plugin's knowledge base to prevent future occurrences.
divi5-validator
Use this agent after writing or editing CSS files to validate Divi 5.13 compatibility. Triggers on CSS file changes and checks for button specificity issues, numbered selectors, missing !important on Divi overrides, and other compatibility problems. Knows about 5.3 form field selectors and pseudo-class editing, 5.5…
gsp-polisher
Detects and fixes AI-slop craft failures in React/Tailwind codebases. Spawned by /gsp-polish.
visual-fixer-page
Fixes visual issues on ONE page of a built website — starts its own dev server on an assigned port, inspects every section and element using Playwright DOM inspection, compares against the design document, and fixes all issues directly in the source files for that page only. Multiple instances run in parallel, each…
page-builder
Builds ONE page or major section of a website end-to-end — React components, text content, mock data, media generation/sourcing (images, video, icons), Tailwind styling, and GSAP/CSS animations. Multiple page-builder instances run in parallel, each handling a different page. Receives its page spec from the design…