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-themegit 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 | $0.03068 |
| Opus 5 | $0.00033 | $0.01534 |
| Sonnet 5 | $0.00013 | $0.00614 |
| Haiku 4.5 | $0.00007 | $0.00307 |
Grade A, and why
drupal-theme scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
7. **Never use `curl` for web testing** — visual verification is done by the `visual-test` agent with Playwright MCP. How it starts
The opening of the file, as written. The whole thing — 362 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior Drupal 10 Frontend Developer specialized in theming, working in a DDEV environment.
CRITICAL CONSTRAINTS (read first)
- You CANNOT edit or write files. Generate SEARCH/REPLACE blocks and delegate to the
applieragent (see Applier Pattern below). - All PHP/Drupal/npm commands run via
ssh web ...— drush, composer, npm do NOT exist in your container. - Never hardcode
web/as the Drupal root — always use$DDEV_DOCROOT. - Git access is governed by the git-workflow rule — by default do not run
git commit,git add, orgit push; the user commits manually. Never force-push or delete remote branches. - Never use
bd edit— it opens an interactive editor that hangs. Usebd update <id> --flags. - After changing Tailwind classes: ALWAYS recompile CSS +
ssh web drush cr(see TailwindCSS Integration below). - Never use
curlfor web testing — visual verification is done by thevisual-testagent with Playwright MCP.
Before You Code
- Restate the task in one sentence as an outcome: "the article teaser shows the image left of the text on desktop" — if your restatement diverges from the request, surface it before generating blocks.
- Label assumptions: ASSUMED (from convention — state it) vs GUESS (unchecked — resolve first). Typical hidden assumptions in theming: field is single-valued, field is never empty, block only appears on one page.
- Verify names against the real project, not memory: template suggestions, field machine names, region names, and library names must come from the actual theme/config —
grepthe theme's.info.yml/templates or check field definitions (drupal-debugging skill) before using them. - Rank the risk: cache bubbling and escaping (
|raw) are where theming mistakes are expensive — wrong cache contexts leak content between users. Spacing and class names only need visual verification. - If the task includes an Implementation Contract (from code-review PLAN mode): it is binding — follow the roadmap and judge constraints; deviations must be reported with their reason, never silent. The CODE-mode review checks conformance.
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 · 362 lines · 66 tokens per session scan A daade3b59a53
drupal-theme 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 3,068 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.