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.
git clone --depth 1 https://github.com/sigistry/marketplaceWrote 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.
[](https://agentmods.dev/commands/sigistry/marketplace/architecture-diagram)<a href="https://agentmods.dev/commands/sigistry/marketplace/architecture-diagram"><img src="https://agentmods.dev/badge/commands/sigistry/marketplace/architecture-diagram/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/sigistry/marketplace/architecture-diagram"><img src="https://agentmods.dev/badge/commands/sigistry/marketplace/architecture-diagram.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00016 | $0.03347 |
| Opus 5 | $0.00008 | $0.01673 |
| Sonnet 5 | $0.00003 | $0.00669 |
| Haiku 4.5 | $0.00002 | $0.00335 |
Grade A, and why
architecture-diagram 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 7d 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 — 608 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Diagram Generator
You are tasked with creating comprehensive, visual architecture diagrams from the codebase using Mermaid syntax. These diagrams should help developers understand the system structure, data flow, and component relationships.
Step 1: Analyze Codebase Architecture
Scan and understand the project structure:
Identify Architecture Type:
- Monolithic: Single codebase, tightly coupled
- Microservices: Multiple independent services
- Layered: Clear separation (presentation, business, data layers)
- Event-Driven: Message queues, pub/sub patterns
- Serverless: Cloud functions, managed services
- Hybrid: Combination of patterns
Map Components:
- Frontend applications (web, mobile)
- Backend services (APIs, workers, cron jobs)
- Databases (SQL, NoSQL, cache, search engines)
- External services (third-party APIs, SaaS)
- Infrastructure (load balancers, CDN, message queues)
- Authentication/Authorization services
Identify Relationships:
- Data flow between components
- API calls and dependencies
- Event streams and messages
- Database connections
- File storage access
- External API integrations
Step 2: Generate System Architecture Diagram
Create a high-level overview using Mermaid:
graph TB
subgraph "Client Layer"
WEB[Web Application<br/>React.js]
MOBILE[Mobile App<br/>React Native]
end
subgraph "API Layer"
GATEWAY[API Gateway<br/>Express.js]
AUTH[Auth Service<br/>JWT]
end
subgraph "Business Logic Layer"
USER_SVC[User Service]
ORDER_SVC[Order Service]
PAYMENT_SVC[Payment Service]
NOTIFICATION_SVC[Notification Service]
end
subgraph "Data Layer"
POSTGRES[(PostgreSQL<br/>Primary DB)]
REDIS[(Redis<br/>Cache)]
ELASTICSEARCH[(Elasticsearch<br/>Search)]
end
subgraph "External Services"
STRIPE[Stripe API<br/>Payments]
SENDGRID[SendGrid<br/>Email]
S3[AWS S3<br/>File Storage]
end
WEB --> GATEWAY
MOBILE --> GATEWAY
GATEWAY --> AUTH
GATEWAY --> USER_SVC
GATEWAY --> ORDER_SVC
GATEWAY --> PAYMENT_SVC
USER_SVC --> POSTGRES
USER_SVC --> REDIS
ORDER_SVC --> POSTGRES
ORDER_SVC --> NOTIFICATION_SVC
PAYMENT_SVC --> STRIPE
PAYMENT_SVC --> POSTGRES
NOTIFICATION_SVC --> SENDGRID
USER_SVC --> S3
style WEB fill:#e3f2fd
style MOBILE fill:#e3f2fd
style STRIPE fill:#fff3e0
style SENDGRID fill:#fff3e0
style S3 fill:#fff3e0
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.
- 7d ago First seen · 608 lines · 16 tokens per session scan A 7820fc624a1f
architecture-diagram is a command published in the GitHub repository sigistry/marketplace (3 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 3,347 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 2026-09-03.
Other commands, from other repositories
design
Create a design direction and styleguide for a project — produces aesthetic direction, fonts, colors, imagery, and media prompts.
createuxprd
Generate the UX PRD companion document from design requirements.
sculpt-ui
Guide AI-led creation of distinctive, production-grade frontend interfaces.
qfrontdev
Autonomous frontend implementation session with designer-level quality standards.
stark-director
Use this command when the user asks Stark to go all out, raise design quality broadly, use libraries well, make a UI feel actually designed, or coordinate research, typography, motion, usability, implementation, and QA in one pass.
data-visualization-specialist
Use when a chart misleads or confuses. Wrong chart type for the data, a truncated axis, colour that encodes nothing, unreadable labels on mobile, or charts no screen reader can use.