LifeOS is an AI-assisted personal operating system that records a person’s goals, values, context, and current situation to help move them toward a desired future state. It supports work such as building applications, starting businesses, and creative projects. Its catalogue entries extend the system through skills, hooks, agents, and commands.
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/danielmiessler/lifeos/webdesignnpx skills add danielmiessler/LifeOS --skill webdesigngit clone --depth 1 https://github.com/danielmiessler/LifeOSWrote 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/danielmiessler/lifeos/webdesign)<a href="https://agentmods.dev/skills/danielmiessler/lifeos/webdesign"><img src="https://agentmods.dev/badge/skills/danielmiessler/lifeos/webdesign.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 | $0.00134 | $0.03969 |
| Opus 5 | $0.00067 | $0.01985 |
| Sonnet 5 | $0.00027 | $0.00794 |
| Haiku 4.5 | $0.00013 | $0.00397 |
Grade A, and why
Webdesign scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST http://localhost:31337/notify \ How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Voice Notification (REQUIRED FIRST ACTION)
curl -s -X POST http://localhost:31337/notify \
-H "Content-Type: application/json" \
-d '{"message": "Running the Webdesign skill", "voice_enabled": true}' > /dev/null
What It Does
Designs and integrates web interfaces via two paths. ClaudeDesign drives Anthropic's claude.ai/design product through the Interceptor skill, then folds the result into your codebase. DirectDesign writes the design inline using Anthropic's open-source frontend-design philosophy, loaded from a local reference. Default routing: short, ad-hoc, in-codebase work goes to DirectDesign; multi-page or shareable prototypes go to ClaudeDesign.
The Problem
Producing good web UI usually means either fighting a visual tool that can't touch your real codebase, or hand-coding from scratch and landing on the same generic defaults every time. The two failure modes pull in opposite directions: visual-first tools give you polish but a handoff gap, while writing code directly gives you integration but flat aesthetics. This skill gives you both routes under one roof — a visual round-trip through claude.ai/design when review matters, or inline design with a real aesthetic doctrine loaded when speed and in-codebase iteration matter — and routes to the right one based on the ask.
How It Works
Webdesign covers three paths for producing web UI. Pick the path that fits; surface options by name when intent is ambiguous. We always drive whatever version of Claude Design is live — there is no version to pin.
Path 1 — DirectDesign (default workhorse; {{DA_NAME}} writes the design inline)
{{DA_NAME}} writes the design directly with Anthropic's open-source frontend-design aesthetic doctrine loaded inline. The load-bearing prompt content is mirrored from github.com/anthropics/skills/tree/main/skills/frontend-design (MIT-licensed) into References/FrontendDesignPhilosophy.md — register list, anti-default rules, type pair recipes, motion vocabulary, color discipline. Self-contained: no runtime dependency, no browser, no auth. This is the path that has actually shipped every real design this skill has produced. Workflow: DirectDesign.
What ships with it
19 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.
- LICENSE.txt 1.1 KB
- README.md 2.5 KB
- References/ClaudeDesignCapabilities.md 6.7 KB
- References/ExportFormats.md 5.7 KB
- References/FrontendDesignPhilosophy.md 14 KB
- References/HandoffBundleSpec.md 6.8 KB
- References/InputFormats.md 7.1 KB
- Tools/DriveClaudeDesign.ts 8.0 KB runs code
- Tools/ProcessHandoffBundle.ts 6.1 KB runs code
- Tools/VerifyDesign.ts 6.6 KB runs code
- Workflows/CreatePrototype.md 4.0 KB
- Workflows/DeployDesign.md 3.4 KB
- Workflows/DirectDesign.md 6.7 KB
- Workflows/ExportToCode.md 4.8 KB
- Workflows/ExtractDesignSystem.md 5.4 KB
- Workflows/IntegrateIntoApp.md 6.9 KB
- Workflows/NativeDesignSync.md 4.0 KB
- Workflows/RefinePrototype.md 4.0 KB
- Workflows/WebsiteToRedesign.md 4.1 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.
- yesterday First seen · 199 lines · 134 tokens per session scan A 73c201e3f912
Webdesign is a skill published in the GitHub repository danielmiessler/LifeOS (18,885 stars, last pushed yesterday), licensed MIT. It adds 134 tokens to every session and 3,969 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
cmux
Controls the cmux macOS terminal app (Ghostty-based, AI-agent-aware) via its CLI socket API. Use this skill to: open browser preview panes when a dev server starts or an HTML file is created; spin up named workspaces for parallel subagents; show live sidebar progress/status during long tasks; open utility splits on…
ui-ux-pro-max
Use when planning, building, designing, code review, refactor, fixing, improving, optimizing, enhancing, or checking UI/UX work. Covers product patterns, landing pages, chart choices, visual styles, palettes, typography, UX rules, and 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind…
ui-design-system
Use when creating or maintaining UI design systems, design tokens, component documentation, responsive calculations, quality checks, or design-dev handoff materials.
maaslalani-cli-style
Build CLIs and terminal tools in the style of maaslalani (slides, nap, sheets, gambit, typer, invoice, gum). Use when designing or building a new CLI/TUI tool, restructuring an existing one, or reviewing a terminal tool's UX, layout, keybindings, or README.
i-have-adhd
Action-first, zero-filler replies for a reader who loses the thread in prose. Use when the user asks for terse or direct answers, says too long, get to the point, tldr, stop rambling, or when replies keep getting cut off or ignored.
frontend-perfection
Audit and polish frontend (static HTML/CSS/JS or built SPA) to measurable perfection: real-Chrome Lighthouse >=13 runs (mobile+desktop, no Playwright internals), SEO meta layer, WCAG contrast by computed luminance, heading order, a11y checks (axe-core subset), back-to-top navigation, design tokens (zero raw hex)…