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/onewave-ai/open-agent-stack/new-appnpx skills add OneWave-AI/open-agent-stack --skill new-appgit clone --depth 1 https://github.com/OneWave-AI/open-agent-stackWrote 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/onewave-ai/open-agent-stack/new-app)<a href="https://agentmods.dev/skills/onewave-ai/open-agent-stack/new-app"><img src="https://agentmods.dev/badge/skills/onewave-ai/open-agent-stack/new-app.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 | $0.00057 | $0.00598 |
| Opus 5 | $0.00028 | $0.00299 |
| Sonnet 5 | $0.00011 | $0.00120 |
| Haiku 4.5 | $0.00006 | $0.00060 |
Grade A, and why
new-app 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 4d 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 — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.
New App
The first hour sets the ceiling: apps that start as default-Tailwind boilerplate stay looking like it. Scaffold with the design system already in, the structure already opinionated, and the lies already removed (no fake data wired to nothing).
Workflow
- One question round, maximum. From the idea sentence, infer the app shape (marketing site, dashboard, tool, storefront) and confirm only what changes the scaffold: does it need auth, does it need a database, who is it for. Everything else gets a sensible default now and a refactor later.
- Pick the skin. Choose (or let the user choose) a theme from the Open Agent Stack
design-styles/collection -- aurora-mesh, cirrus, liquid-glass, mono-brutalist, neo-terminal, sand-terra, tidal -- and wire its tokens into Tailwind before writing any component. House rules apply regardless of theme: no purple, no emoji in UI, icons from Lucide. - Scaffold. Next.js App Router + TypeScript + Tailwind. Structure: route groups by audience,
components/uifor primitives consuming tokens only,libfor real logic. Auth slot (middleware + provider stub wired to real session shape) and data slot (typed client, one real example query) if needed -- stubs that state what they are, never mock data pretending to be live. - Set the motion language. Run
motion-systembefore the first animated component -- three durations, three easings, and the reduced-motion policy go into the theme alongside the color tokens. Ten minutes here is what stops the app accumulating fourteen different hover durations by week two. - First real screen. Build the landing/home screen properly against the theme -- type scale, spacing, one signature motion -- so every screen after has a quality bar to match, not a placeholder to excuse.
- Boot it.
npm run dev, verify it renders, commit. The scaffold is done when it runs, not when the files exist.
Rules
- Never ship hardcoded/mock data wired to look live -- if a real backend exists, query it; if not, the empty state is the honest UI.
- Tokens from minute one: no raw hex in components, ever, so the theme swap stays a one-file change.
- Opinionated beats configurable at this stage -- one good default now, options when the app earns them.
- The README the scaffold writes says what is real, what is stubbed, and what the next three build steps are.
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.
- 4d ago First seen · 25 lines · 57 tokens per session scan A 2c9bcf572866
new-app is a skill published in the GitHub repository OneWave-AI/open-agent-stack (2 stars, last pushed 24d ago), licensed MIT. It adds 57 tokens to every session and 598 once invoked, about $0.0003 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
html-email
Send-ready single-file email.
a11y-review
Static analysis pass over JSX/HTML/CSS source for WCAG 2.2 AA failure patterns. Does NOT run axe-core, does NOT measure real contrast, does NOT test runtime behavior — pair with a11y-testing for that. Use when the user asks for an accessibility review, a11y check, WCAG review, "is this accessible?", "does my site meet…
colors
Color systems for web interfaces — OKLCH conversion and palette generation, contrast measurement (APCA/WCAG), gamut and P3 fallbacks, theming, one meaning per color. INVOKE PROACTIVELY when converting color values, building or extending a palette or token set, checking or reporting contrast, or theming light and dark…
a11y-keyboard-focus
Use this skill when the user asks about keyboard navigation, keyboard accessibility, focus management, focus trapping, focus ring, focus indicator, ":focus-visible", skip links, "tabindex", "Tab key navigation", "focus order", "focus returns", "orphaned focus", "focus lost", "modal focus trap", "focus after close"…
a11y-semantic-html
Use this skill when the user asks about semantic HTML structure, heading hierarchy, landmark regions, div soup, divitis, "which HTML element should I use", "semantic markup", "HTML accessibility", "ARIA landmarks", "page structure", "section vs div", "article vs section", "when to use aside", or is writing HTML…
typography
Web typography — typeface choice and pairing, variable fonts and OpenType features, type scales, line-height, letter-spacing, measure, wrapping, truncation, underlines, tabular numbers, iOS input zoom. INVOKE PROACTIVELY when styling or reviewing anything that renders text. The words themselves: [[ux-writing]]…