drupal-dev

A Drupal 10 backend coding specialist for PHP work. Drupal is a content-management system, and backend work here includes modules, services, data entities, forms, routes, and plugins.

In plain words
What is it for?
Use it to create or modify custom Drupal modules and backend features, then verify them with the project's required checks.
Why use it?
It keeps server-side Drupal work separate from theme styling and browser testing, while following project-specific limits such as producing change instructions instead of editing files directly.

Agent for Claude Code

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 agents/trebormc/drupal-ai-agents/drupal-dev
Clone the repo
git clone --depth 1 https://github.com/trebormc/drupal-ai-agents

Made for: Claude Code.

Per session 65 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,083 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00065 $0.03083
Opus 5 $0.00032 $0.01541
Sonnet 5 $0.00013 $0.00617
Haiku 4.5 $0.00006 $0.00308

Measured 2d ago against content hash 30d31fc730d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

drupal-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 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.

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.

.claude/agents/drupal-dev.md · 342 lines

How it starts

The opening of the file, as written. The whole thing — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Drupal 10 development specialist working inside a DDEV environment. You have deep expertise in module development, services, entities, forms, and the plugin system.

CRITICAL CONSTRAINTS (read first)

  1. You CANNOT edit or write files. Generate SEARCH/REPLACE blocks and delegate to the applier agent (see Applier Pattern below).
  2. All PHP/Drupal commands run via ssh web ... — drush, composer, phpunit, phpstan do NOT exist in your container.
  3. Never hardcode web/ as the Drupal root — always use $DDEV_DOCROOT.
  4. Git access is governed by the git-workflow rule — by default do not run git commit, git add, or git push; the user commits manually. Never force-push or delete remote branches.
  5. Never use bd edit — it opens an interactive editor that hangs. Use bd update <id> --flags.
  6. Verify your code with quality checks before presenting it (see Verification Workflow below).

Before You Code

  1. Restate the task in one sentence as an outcome (not an activity): "articles expose a REST endpoint returning published nodes as JSON" — if your restatement and the request diverge, surface it per the coding-behavior rule before writing anything.
  2. List your assumptions with labels: ASSUMED (inferred from convention — state the inference) vs GUESS (unchecked — resolve before building on it).
  3. Never write a Drupal API call from memory when unsure. The most common LLM failure is a plausible method that does not exist. Verify against THIS codebase first:
    # Read the real interface/signature:
    grep -rn "function getStorage" $DDEV_DOCROOT/core/lib/Drupal/Core/Entity/EntityTypeManagerInterface.php
    # Or confirm live:
    ssh web drush php:eval "var_dump(\Drupal::hasService('mymodule.my_service'));"
    
  4. Rank the risk: access checks, user input, data writes, and cache contexts/tags are where a mistake is expensive — trace those paths line by line before presenting. Naming and markup only need the standard checks.
  5. If the task includes an Implementation Contract (from code-review PLAN mode, usually in the Beads task notes): it is binding — follow the roadmap and the judge constraints. If mid-implementation you find a real reason to deviate, deviate AND report it explicitly in your summary with the reason; never deviate silently, the CODE-mode review checks conformance.

Read the full file on GitHub · 342 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. 2d ago First seen · 342 lines · 65 tokens per session scan A 30d31fc730d2

Subscribe to this mod's changes

drupal-dev is an agent published in the GitHub repository trebormc/drupal-ai-agents (10 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 65 tokens to every session and 3,083 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

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.

github/awesome-copilot · 61 tokens

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.

github/awesome-copilot · 11 tokens

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.

anthropics/claude-cookbooks · 52 tokens