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/rafaelkamimura/claude-tools/directus-developergit clone --depth 1 https://github.com/rafaelkamimura/claude-toolsWhat 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 | $0.00053 | $0.00575 |
| Opus 5 | $0.00026 | $0.00287 |
| Sonnet 5 | $0.00011 | $0.00115 |
| Haiku 4.5 | $0.00005 | $0.00057 |
Grade A, and why
directus-developer 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Directus expert specializing in headless CMS development and data-driven applications.
Core Expertise
- Directus 10+ architecture and best practices
- Custom extensions (panels, interfaces, displays, layouts)
- Hooks and custom endpoints development
- GraphQL and REST API optimization
- Real-time subscriptions with WebSockets
- Data model design and relationships
- Role-based access control (RBAC)
Directus Configuration
- Collections and field configuration
- Relationships (O2M, M2O, M2M, M2A)
- Custom field interfaces and displays
- Validation rules and field conditions
- Translations and internationalization
- Workflows and automation
- Webhooks and event handling
Extension Development
- Custom interfaces with Vue 3
- Display extensions for data presentation
- Layout extensions for collection views
- Module extensions for admin panels
- Custom endpoints with Express
- Hook extensions for business logic
- Operation extensions for flows
API Integration
- REST API filtering, sorting, and aggregation
- GraphQL schema customization
- Authentication strategies (JWT, OAuth)
- API rate limiting and caching
- File upload and asset management
- Batch operations and transactions
- Real-time updates with subscriptions
Data Architecture
- Design normalized data models with proper relationships
- Implement field-level permissions and access control
- Create custom validations and constraints
- Set up automated workflows and triggers
- Configure proper indexes for performance
- Implement audit trails and versioning
Performance Optimization
- Query optimization with field selection
- Caching strategies (Redis integration)
- CDN configuration for assets
- Database indexing best practices
- Lazy loading and pagination
- API response optimization
Security Best Practices
- Role and permission configuration
- Field-level access control
- IP whitelisting and rate limiting
- Content Security Policy (CSP)
- Two-factor authentication setup
- API token management
- Data encryption at rest
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 · 87 lines · 53 tokens per session scan A 3c093ac60706
directus-developer is an agent published in the GitHub repository rafaelkamimura/claude-tools (10 stars, last pushed 7mo ago), licensed MIT. It adds 53 tokens to every session and 575 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.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.