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 skills/aaronbassett/agent-foundry/createnpx skills add aaronbassett/agent-foundry --skill creategit clone --depth 1 https://github.com/aaronbassett/agent-foundryWrote 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/aaronbassett/agent-foundry/create)<a href="https://agentmods.dev/skills/aaronbassett/agent-foundry/create"><img src="https://agentmods.dev/badge/skills/aaronbassett/agent-foundry/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 | $0.00088 | $0.01205 |
| Opus 5 | $0.00044 | $0.00602 |
| Sonnet 5 | $0.00018 | $0.00241 |
| Haiku 4.5 | $0.00009 | $0.00120 |
Grade A, and why
design-systems: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 3d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Design System
Generate a complete, opinionated DESIGN.md from a short description.
Input
The user provides a short description of the desired aesthetic direction. Examples:
- "dark editorial for a privacy-focused developer tool"
- "warm minimal for a recipe app"
- "brutalist for a crypto exchange"
If no description is provided, ask for one:
question: "Describe the design direction in a few words"
options:
- label: "Dark editorial"
description: "Moody, magazine-inspired, serif-forward"
- label: "Clean minimal"
description: "Extreme reduction, one accent color, invisible UI"
- label: "Bold brutalist"
description: "Hard edges, high contrast, raw structure"
- label: "Warm organic"
description: "Natural textures, warm palette, flowing forms"
Generation Flow
Step 1: Load References
Read these files before generating anything:
${CLAUDE_SKILL_DIR}/references/anti-slop.md— patterns to avoid${CLAUDE_SKILL_DIR}/references/aesthetic-seeds.md— non-default starting directions${CLAUDE_SKILL_DIR}/references/design-md-schema.md— strict output schema
Step 2: Select Aesthetic Seed
Based on the user's description, select the most appropriate seed from
aesthetic-seeds.md. The seed provides:
- Font pairing candidates (display + body + mono)
- Color derivation strategy
- Spatial philosophy
- Elevation approach
- Natural prohibitions
The seed is a starting direction, not a template. Adapt and build on it based on the user's specific needs. Combine elements from multiple seeds if the description warrants it.
Step 3: Generate DESIGN.md
Follow the strict schema from design-md-schema.md exactly. Generate
all 7 sections with all required subsections.
Anti-Slop Enforcement — CRITICAL:
For EVERY design decision, cross-check against anti-slop.md. This
is not optional. The following checks are mandatory:
| Section | Anti-Slop Checks |
|---|---|
| Typography | No Inter, Roboto, Open Sans, Lato, Arial as primary. Weight contrast must be extreme (not 400 vs 600). Size jumps 3x+ between levels. |
| Colors | No purple/indigo gradient defaults. No pure #000000 or #ffffff. Palette has one dominant + sharp accent, not evenly distributed. No cyan-on-dark neon default. |
| Layout | Prohibitions must ban at least one layout anti-pattern. No uniform spacing throughout. |
| Shadows | No box-shadow: 0 4px 6px rgba(0,0,0,0.1). All shadows hue-tinted or otherwise distinctive. |
| Components | No border-radius: 8-12px + generic shadow combo. No left-border accent on all cards. Button hierarchy (primary/secondary/tertiary) must be visually distinct. |
| Do's/Don'ts | Must include relevant AI Slop checklist items as Don'ts. |
What ships with it
3 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.
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.
- 3d ago First seen · 135 lines · 88 tokens per session scan A e08d3bae0998
design-systems:create is a skill published in the GitHub repository aaronbassett/agent-foundry (4 stars, last pushed 19d ago), licensed MIT. It adds 88 tokens to every session and 1,205 once invoked, about $0.0004 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 skills, from other repositories
material-ui-tailwind
Integrates Material UI with Tailwind CSS v4 using cascade layers (enableCssLayer, @layer order) and documents Tailwind v3 interoperability (preflight, important, injectFirst, portals). Use when combining MUI with Tailwind utilities, slotProps className, or theme token bridges.
hallmark
Anti-AI-slop design skill for greenfield pages, audits, redesigns, and design extraction from URLs or screenshots. Use when the user asks to build a new app or landing page, wants to redesign something, invokes Hallmark by name, or uses audit/redesign/study.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
desktop-principles
Desktop-specific UX principles - hover states, pointer precision, keyboard shortcuts, multi-window, focus management. Covers macOS, Windows, Linux, web desktop.
taiyi-ui-design
TaiyiForge 第 4 阶段 — UI/UX 契约,产出 UI-DESIGN.md。四端通用。.