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 WaterplanAI/agentic-config --skill ac-tools-human-agentic-designgit clone --depth 1 https://github.com/WaterplanAI/agentic-configWrote 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/waterplanai/agentic-config/ac-tools-human-agentic-design)<a href="https://agentmods.dev/skills/waterplanai/agentic-config/ac-tools-human-agentic-design"><img src="https://agentmods.dev/badge/skills/waterplanai/agentic-config/ac-tools-human-agentic-design/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/waterplanai/agentic-config/ac-tools-human-agentic-design"><img src="https://agentmods.dev/badge/skills/waterplanai/agentic-config/ac-tools-human-agentic-design.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 | $0.00081 | $0.02514 |
| Opus 5 | $0.00041 | $0.01257 |
| Sonnet 5 | $0.00016 | $0.00503 |
| Haiku 4.5 | $0.00008 | $0.00251 |
Grade A, and why
ac-tools-human-agentic-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Human-Agentic Design
Compatibility Note
This pi wrapper preserves the original optional Playwright preview loop, but the documented non-MCP fallback remains mandatory when preview tooling is unavailable.
Generates live, interactive prototype designs optimized for dual human+agent interaction. Every prototype is equally usable by humans (visual interaction) and AI agents (programmatic interaction via accessibility trees).
Purpose
- Generate production-quality HTML prototypes with zero setup
- Enforce semantic HTML and accessibility standards that enable AI agent navigation
- Provide iterative visual + accessibility feedback via Playwright MCP
- Support two tiers: zero-dep HTML (Tier A) and React + shadcn/ui (Tier B)
Workflow
1. Environment Probe
Detect available capabilities. Run these checks silently (no user prompting):
# Check Playwright MCP availability (tool list includes mcp__playwright__*)
# Check Node.js
if NODE_BIN=$(command -v node); then "$NODE_BIN" --version; fi
Tier Selection:
- Playwright MCP tools available -> Enable preview loop
nodebinary found in PATH -> Offer Tier B (React + shadcn/ui + Vite)- Default -> Tier A (single-file HTML + Tailwind CDN + DaisyUI CDN)
Report detected tier to user in one line:
Environment: Tier [A|B] | Playwright: [available|unavailable] | Node: [vX.Y.Z|not found]
If user explicitly requests a tier, honor that request regardless of detection.
2. Parse Request
Identify from user prompt:
- Page type: landing, dashboard, form, blog, portfolio, or custom
- Design requirements: colors, branding, content, layout preferences
- Tier preference: explicit tier request overrides auto-detection
- Multi-page: if multiple pages requested, plan linked file set
If page type matches a built-in template, use it as starting point. Read the template from templates/<type>.html within this skill directory.
3. Generate Code
Tier A (HTML + Tailwind CDN + DaisyUI CDN):
- Read
cookbook/tier-a.mdfor boilerplate and CDN URLs - Read
cookbook/agent-principles.mdfor the 8 mandatory principles - Generate single
index.html(or multiple linked HTML files for multi-page) - All CSS via Tailwind utility classes + DaisyUI component classes
- All JS vanilla, embedded in
<script>tags - If a template exists for the requested page type, read
templates/<type>.htmland customize
What ships with it
10 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.
- 10d ago First seen · 265 lines · 81 tokens per session scan A 4bb4daaa2778
ac-tools-human-agentic-design is a skill published in the GitHub repository WaterplanAI/agentic-config (30 stars, last pushed 1mo ago), licensed MIT. It adds 81 tokens to every session and 2,514 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 2026-08-30.
Other skills, from other repositories
taste-skill
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
liquid-glass
Apple Liquid Glass design system. Use when building UI with translucent, depth-aware glass morphism following Apple's design language. Provides CSS tokens, component patterns, dark/light mode, and animation specs.
adapt
Adapt designs to work across different screen sizes, devices, contexts, or platforms. Implements breakpoints, fluid layouts, and touch targets. Use when the user mentions responsive design, mobile layouts, breakpoints, viewport adaptation, or cross-device compatibility.
normalize
Audits and realigns UI to match design system standards, spacing, tokens, and patterns. Use when the user mentions consistency, design drift, mismatched styles, tokens, or wants to bring a feature back in line with the system.
extract
Extract and consolidate reusable components, design tokens, and patterns into your design system. Identifies opportunities for systematic reuse and enriches your component library. Use when the user asks to create components, refactor repeated UI patterns, build a design system, or extract tokens.
frame-flowchart-sticky
A single-file HTML template for showing a process or system as a whiteboard with coloured sticky notes, curved arrows, and optional mouse interactions.