drupal-ai-agents CLAUDE.md

drupal-ai-agents CLAUDE.md is an instructions file for coding agents from trebormc/drupal-ai-agents. It costs 3,589 tokens per session, scanned A, original, Apache-2.0.

Project-specific instructions for Drupal AI Agents, software agents built for Drupal, a platform for creating and managing websites. They define language rules, development principles, containers, and model choices.

In plain words
What is it for?
Use them when developing or testing Drupal modules, running PHP and Drush commands through DDEV, tracking tasks, or using browser tests.
Why use it?
They prevent commands from being run in the wrong container and keep code, communication, and implementation choices consistent.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/trebormc/drupal-ai-agents/claude-md
Clone the repo
git clone --depth 1 https://github.com/trebormc/drupal-ai-agents

Wrote 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.

agentmods badge for drupal-ai-agents CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/trebormc/drupal-ai-agents/claude-md.svg)](https://agentmods.dev/instructions/trebormc/drupal-ai-agents/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/trebormc/drupal-ai-agents/claude-md"><img src="https://agentmods.dev/badge/instructions/trebormc/drupal-ai-agents/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,589 This file is loaded in full into every session.
When invoked 3,589 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.03589 $0.03589
Opus 5 $0.01795 $0.01795
Sonnet 5 $0.00718 $0.00718
Haiku 4.5 $0.00359 $0.00359

Measured 4d ago against content hash efe70d90e160, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

drupal-ai-agents CLAUDE.md 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 4d 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.

- **NEVER use curl** for testing Drupal pages
CLAUDE.md · 266 lines

How it starts

The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Drupal AI Agents

Language

  • User interaction: Respond in the same language the user writes in.
  • Everything else in English: All code, variables, functions, comments, docblocks, commit messages, and generated content must always be in English.
  • Skills and agents: Match the user's intent to the appropriate English-defined skill by semantic meaning, not literal keyword matching.

Design Principles

  • Simple and elegant solutions first. Always prefer the simplest, cleanest approach. Avoid over-engineering.

DDEV Environment

You run inside an AI container (OpenCode or Claude Code). The project uses multiple DDEV containers:

Container Access method Purpose
Your container Direct Agents, file access, bash
Web (web) SSH PHP, Drupal, Drush, Composer
Beads (beads) bd wrapper Git-backed task tracking
Playwright MCP ($PLAYWRIGHT_MCP_URL) HTTP MCP Chromium browser testing

All PHP/Drupal commands must use SSH:

ssh web drush cr
ssh web ./vendor/bin/phpstan analyse $DDEV_DOCROOT/modules/custom
ssh web ./vendor/bin/phpunit $DDEV_DOCROOT/modules/custom/mymodule

CRITICAL: Always use ssh web drush <command> to run Drush commands (the drush alias is available in the web container's PATH). CRITICAL: Never hardcode web/ -- use $DDEV_DOCROOT (varies per project: web/, docroot/, etc.).

Available variables: $DDEV_PRIMARY_URL (HTTPS), $DDEV_HTTP_URL (HTTP — use for browser testing), $DDEV_SITENAME, $DDEV_DOCROOT, $PLAYWRIGHT_MCP_URL

Model Strategy

Agents use model tokens that resolve to real model names at sync time:

Token Default Used for
MODEL_MAIN CHEAP (OpenCode) / NORMAL (Claude Code) The orchestrator: main conversation loop that receives prompts and delegates
MODEL_GENIUS same as SMART Hardest tasks: important code reviews, architecture decisions
MODEL_SMART Opus 4.6 Quality gates, planning, research, delegation advice
MODEL_NORMAL Sonnet 4.5 Development, review
MODEL_CHEAP Haiku 4.5 Exploration, fast tasks
MODEL_APPLIER Haiku 4.5 Mechanical code application
MODEL_VISION same as NORMAL Image/screenshot interpretation — must accept image input

Read the full file on GitHub · 266 lines

Changes

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.

  1. 4d ago First seen · 266 lines · 3,589 tokens per session scan A efe70d90e160

Subscribe to this mod's changes

drupal-ai-agents CLAUDE.md is an instructions file published in the GitHub repository trebormc/drupal-ai-agents (10 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 3,589 tokens to every session, about $0.0179 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.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens