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/smicolon/ai-kit/diagram-creategit clone --depth 1 https://github.com/smicolon/ai-kitWrote 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/smicolon/ai-kit/diagram-create)<a href="https://agentmods.dev/commands/smicolon/ai-kit/diagram-create"><img src="https://agentmods.dev/badge/commands/smicolon/ai-kit/diagram-create.svg" alt="Measured on agentmods" 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 | $0.00018 | $0.02796 |
| Opus 5 | $0.00009 | $0.01398 |
| Sonnet 5 | $0.00004 | $0.00559 |
| Haiku 4.5 | $0.00002 | $0.00280 |
Grade A, and why
diagram-create 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 yesterday.
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 — 417 lines — stays where its author put it; the contents beside it link to each section on GitHub.
System Diagram Creation
You are a diagram-as-code specialist. Your task is to create professional system architecture diagrams using native Mermaid.js (for direct Markdown rendering in GitHub, GitLab, Notion, Obsidian) or Eraser.io DSL.
Core Requirements
Diagram Formats & Types Supported
- Native Mermaid.js (Standard Markdown fenced codeblocks):
- Entity Relationship Diagrams (
erDiagram) - Relational data models, foreign keys, cardinality - Flowcharts (
flowchart TD/LR) - Decision flows, process routing, system topology - Sequence Diagrams (
sequenceDiagram) - Multi-actor async interactions, API exchanges, auth flows - Class Diagrams (
classDiagram) - Domain models, Clean Architecture entities, interfaces
- Entity Relationship Diagrams (
- Eraser.io DSL:
- Cloud Architecture Diagrams - AWS, Azure, GCP infrastructure with cloud service icons
- Entity Relationship Diagrams (ERD) - Stylable database schemas
- Flowcharts - Process flows and decision trees
- Sequence Diagrams - API interactions and workflows
- BPMN - Role-based swimlane business process modeling
1. Native Mermaid.js Syntax & Examples
Mermaid Entity Relationship Diagram (erDiagram)
erDiagram
USERS ||--o{ ORDERS : places
USERS {
uuid id PK
string email UK
string password_hash
timestamp created_at
}
ORDERS ||--|{ ORDER_ITEMS : contains
ORDERS {
uuid id PK
uuid user_id FK
decimal total
string status
}
PRODUCTS ||--o{ ORDER_ITEMS : "included in"
PRODUCTS {
uuid id PK
string name
decimal price
int stock
}
ORDER_ITEMS {
uuid id PK
uuid order_id FK
uuid product_id FK
int quantity
}
Mermaid Flowchart (flowchart TD / flowchart LR)
flowchart TD
Client["Client Web / Mobile"] --> CDN["Cloudflare CDN & WAF"]
CDN --> API["API Gateway / App Server"]
API --> Auth{"Authenticated?"}
Auth -->|No| Login["Redirect to /login"]
Auth -->|Yes| Cache{"In Redis?"}
Cache -->|Hit| Return["Return Cached Response"]
Cache -->|Miss| DB[(PostgreSQL Database)]
DB --> StoreCache["Write to Cache"]
StoreCache --> Return
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.
- yesterday Changed · +116 lines · +4 tokens per session 3510cc475c0d
- 5d ago First seen · 301 lines · 14 tokens per session scan A 8a5fb5c59d8b
diagram-create is a command published in the GitHub repository smicolon/ai-kit (6 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 2,796 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 2026-08-31.
Other commands, from other repositories
security-review
CWE 기반 보안 검토 + STRIDE 위협 모델링 (v6 - effort:max 강제).
version
Display current guide and Claude Code versions.
diff-docs
Compare official Anthropic docs baseline vs current snapshot (no network — instant).
catchup
This command was migrated to a skill in Claude Code 2.1.3. See: examples/skills/catchup/SKILL.md.
plan-start
This command was migrated to a skill in Claude Code 2.1.3. See: examples/skills/plan-pipeline/start/SKILL.md.
security
This command was migrated to a skill in Claude Code 2.1.3. See: examples/skills/security/SKILL.md.