boost-feature

A guided seven-phase workflow for building features in Drupal 11, a major version of the Drupal content-management system.

In plain words
What is it for?
Use it to plan and build Drupal features involving existing services, entities, routes, hooks, templates, project conventions, testing, performance, or accessibility.
Why use it?
It helps clarify requirements, inspect the existing project, design the solution, and review the work before implementation is complete.

Command

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 commands/abderrahimghazali/drupal-boost/boost-feature
Clone the repo
git clone --depth 1 https://github.com/abderrahimghazali/drupal-boost
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 848 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 $0.00035 $0.00848
Opus 5 $0.00017 $0.00424
Sonnet 5 $0.00007 $0.00170
Haiku 4.5 $0.00003 $0.00085

Measured 2d ago against content hash 6dd9891b3fe1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

boost-feature 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.

commands/boost-feature.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Drupal 11 Feature Development Workflow

You are running the drupal-boost feature development workflow. Follow these 7 phases strictly. Use TodoWrite to track progress through each phase.

Phase 1: DISCOVERY

Gather requirements from the user. Ask clarifying questions:

  • What is the feature's purpose?
  • Who are the target users/roles?
  • What existing Drupal features does it interact with?
  • Are there performance requirements?
  • Are there accessibility requirements?

Do NOT proceed until you have a clear understanding of what to build.

Phase 2: EXPLORATION

Launch 2 drupal-explorer agents IN PARALLEL to analyze the codebase:

Agent 1: Explore existing code that the feature will interact with — services, entities, routes, hooks, and templates relevant to the feature area.

Agent 2: Explore existing patterns and conventions in the project — coding style, module structure, naming conventions, testing patterns, and CLAUDE.md guidelines.

Wait for both agents to complete. Synthesize their findings.

Phase 3: CLARIFYING QUESTIONS

Based on exploration findings, present what you learned and ask the user any remaining questions:

  • Technical constraints discovered
  • Existing patterns that should be followed
  • Decision points that need user input (e.g., "Should this be a config entity or content entity?")

Phase 4: ARCHITECTURE DESIGN

Launch 2-3 drupal-architect agents IN PARALLEL, each proposing a different approach:

Agent 1 — Minimal: Simplest implementation with fewest files. Trade-off: may not scale.

Agent 2 — Clean: Well-architected with proper separation of concerns. Trade-off: more files, more complexity.

Agent 3 — Pragmatic (optional): Middle ground that balances simplicity and architecture.

Present all approaches to the user with trade-offs. Let them choose or combine.

Phase 5: IMPLEMENTATION

Build the chosen approach:

  1. Create module scaffolding (.info.yml, .services.yml, .routing.yml)
  2. Implement core classes (entities, services, controllers, forms)
  3. Add configuration schema
  4. Create templates if needed
  5. Add permissions and menu links
  6. Write initial tests

Read the full file on GitHub · 101 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 · 101 lines · 35 tokens per session scan A 6dd9891b3fe1

Subscribe to this mod's changes

boost-feature is a command published in the GitHub repository abderrahimghazali/drupal-boost (1 stars, last pushed 5mo ago), licensed MIT. It adds 35 tokens to every session and 848 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.