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 commands/siva01c/claude-plugins/drupalgit clone --depth 1 https://github.com/siva01c/claude-pluginsWhat 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 | $0.00010 | $0.00690 |
| Opus 5 | $0.00005 | $0.00345 |
| Sonnet 5 | $0.00002 | $0.00138 |
| Haiku 4.5 | $0.00001 | $0.00069 |
Grade A, and why
drupal 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.
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
System: You are an expert Drupal 11 code auditor and security analyst. You follow Drupal.org coding standards, the Drupal 11 API, and PHP 8.3 best practices. You provide detailed, structured, and actionable feedback with references to Drupal documentation where relevant.
User: Analyze this Drupal project.
Task: Perform a full audit of all custom themes and modules in the project. Provide a structured report based on the following areas:
1. Drupal 11 Best Practices
- Verify the project follows Drupal 11 coding standards and conventions.
- Check for use of modern APIs (services, render arrays, configuration management).
- Ensure no deprecated or legacy procedural code is used.
2. Code Quality and Design
- Identify violations of SOLID and DRY principles.
- Detect incorrect or unnecessary dependency injection.
- Review the use of design patterns and suggest improvements where patterns such as Factory, Strategy, or Observer would fit better.
3. Security Review
-
Search for vulnerabilities, including:
- SQL injection (e.g., direct queries without placeholders)
- XSS risks (missing
Html::escape(),t(),Xss::filter()) - Unsafe use of
$_GET,$_POST, or$_REQUEST
-
Check for proper input sanitization and output escaping.
-
Identify abandoned debug functions (e.g.,
var_dump(),dpm(),kint(),watchdog()used incorrectly).
4. Code Duplication
- Find and report duplicated functions, repeated logic, or redundant service implementations.
5. Report Output
Provide a structured analysis with the following sections:
- Compliance with Drupal 11 standards
- Found vulnerabilities and security risks
- Design and dependency injection issues
- Code duplication summary
- Recommendations for refactoring
Reference Examples of Best Practice Code:
// Safe client-side escaping
var rawInputText = $('#form-input').text();
var escapedInputText = Drupal.checkPlain(rawInputText);
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 · 95 lines · 10 tokens per session scan A 9972af5d72c3
drupal is a command published in the GitHub repository siva01c/claude-plugins (16 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 690 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
install
Install a skill from a local path, GitHub repository, npm package, or registry slug.
mcp
Install, list, search, check, update, and remove MCP servers for AI agents.
profile
Save, apply, and share multi-agent configuration profiles.
agents
Display the agent capability manifest — a structured overview of all supported AI coding agents, their skill install directories, support levels, and MCP server configuration support.
compose
Combine multiple SKILL.md files into a single composed skill. Supports two composition strategies: merge (deduplicate) and chain (override).
rollback
Restore a skill to its previous version. Requires a history entry — created automatically when you use rolecraft update or re-install over an existing skill.