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 skills add guoliang1114-boop/AriaAI --skill architecturegit clone --depth 1 https://github.com/guoliang1114-boop/AriaAIWrote 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/skills/guoliang1114-boop/ariaai/architecture)<a href="https://agentmods.dev/skills/guoliang1114-boop/ariaai/architecture"><img src="https://agentmods.dev/badge/skills/guoliang1114-boop/ariaai/architecture/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/skills/guoliang1114-boop/ariaai/architecture"><img src="https://agentmods.dev/badge/skills/guoliang1114-boop/ariaai/architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00035 | $0.04034 |
| Opus 5.5 | $0.00014 | $0.01614 |
| Sonnet 5.5 | $0.00007 | $0.00807 |
| Haiku 4.5 | $0.00003 | $0.00403 |
Grade A, and why
architecture 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 1mo 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 — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Diagram Generator
Quick Start: Create HTML structure with flexible layout (single/double/triple column) → Define CSS styles for layers and grids → Add content with categorized panels → Use semantic colors for different layers.
When To Use / Diagnostic Intake
适用于系统分层和依赖展示。先明确读者、部署环境、画布尺寸、信任边界，以及当前事实与规划组件；不要凭常见架构补造服务。
Workflow
选择本包的布局与样式→列出组件和连接→标注流向及协议→生成 HTML/CSS→预览窄屏与导出尺寸并修正。
Tools and Dependencies
使用本包 layouts/ 和 styles/ 资源；浏览器用于预览。远程字体和图标不可用时采用本地字体及文字标签。
Critical Rules
Rule 1: Direct HTML Embedding
IMPORTANT: Write architecture diagrams as direct HTML in Markdown. NEVER use code blocks (```html). The HTML should be embedded directly in the document without any fencing.
Rule 2: No Empty Lines in HTML Structure
CRITICAL: Do NOT add any empty lines within the HTML architecture diagram structure. Keep the entire HTML block continuous to prevent parsing errors.
Rule 3: Incremental Creation Approach
RECOMMENDED: Create architecture diagrams in multiple steps:
- First: Create the overall framework (wrapper, sidebars, main structure) and define all CSS styles
- Second: Add layer containers with titles
- Third: Fill in components layer by layer
- Fourth: Add detailed content and refinements
Rule 4: Flexible Layout Structure
Architecture diagrams can use flexible layouts based on complexity:
- Single Column: Main content only (for simple architectures)
- Two Column: Main content + one sidebar (left or right)
- Three Column: Full layout with both sidebars (for complex systems)
- Left Sidebar: Supporting systems (monitoring, operations, analytics)
- Main Content: Core architecture layers (user, application, data, infrastructure)
- Right Sidebar: Cross-cutting concerns (security, compliance, governance)
Rule 5: Layer-Based Organization
Each layer should have:
- Clear semantic meaning (User, Application, AI/Logic, Data, Infrastructure)
- Consistent color coding
- Grid-based layout for components
- Appropriate nesting for sub-components
What ships with it
27 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- examples/delivery-case.md 917 B
- layouts/banner-center.md 3.3 KB
- layouts/connectors.md 7.9 KB
- layouts/dashboard.md 3.7 KB
- layouts/grid-catalog.md 3.3 KB
- layouts/hub-spoke.md 4.6 KB
- layouts/layer-layouts.md 10 KB
- layouts/left-sidebar.md 4.3 KB
- layouts/nested-containers.md 3.5 KB
- layouts/pipeline.md 2.8 KB
- layouts/right-sidebar.md 4.3 KB
- layouts/single-stack.md 3.0 KB
- layouts/three-column.md 4.6 KB
- layouts/two-column-split.md 3.6 KB
- references/delivery-verification.md 699 B
- styles/dusk-glow.md 7.9 KB
- styles/ember-warm.md 7.8 KB
- styles/frost-clean.md 7.8 KB
- styles/indigo-deep.md 7.9 KB
- styles/neon-dark.md 7.9 KB
- styles/ocean-teal.md 7.9 KB
- styles/pastel-mix.md 7.7 KB
- styles/rose-bloom.md 7.9 KB
- styles/sage-forest.md 7.9 KB
- styles/slate-dark.md 7.7 KB
- styles/stark-block.md 7.4 KB
- styles/steel-blue.md 7.9 KB
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.
- 1mo ago Changed · +17 lines ff94904cad0a
- 1mo ago First seen · 266 lines · 35 tokens per session scan A df76425425fa
architecture is a skill published in the GitHub repository guoliang1114-boop/AriaAI (40 stars, last pushed 12d ago), licensed MIT. It adds 35 tokens to every session and 4,034 once invoked, about $0.0001 per session on Opus 5.5. 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 skills, from other repositories
design
Design workflow that creates design systems, DESIGN.md, and design tokens with anti-pattern enforcement and accessibility checks.
gsd-ui-phase
Generate UI design contract (UI-SPEC.md) for frontend phases.
gsd-ui-review
Retroactive 6-pillar visual audit of implemented frontend code.
ux-walkthrough-skill
A user-experience review process that examines a product’s screens and user journeys against its product requirements document (PRD). It checks consistency, accessibility, errors, and whether users can complete tasks clearly.
创建主题
A set of rules for creating or changing frontend visual themes through configuration. It covers colors, interface components, effects, backgrounds, naming, accessibility, and how preset themes are registered.
auto-trader-design
Use this skill to generate well-branded interfaces and assets for Auto Trader (multi-market AI-assisted trading workspace for KR / US / crypto), either for production work or throwaway prototypes, mocks, and screenshots. Contains essential design guidelines, color + type tokens, component specs, page patterns, and a…