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 hachej/boring-ui --skill boring-design-systemgit clone --depth 1 https://github.com/hachej/boring-uiWrote 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/hachej/boring-ui/boring-design-system)<a href="https://agentmods.dev/skills/hachej/boring-ui/boring-design-system"><img src="https://agentmods.dev/badge/skills/hachej/boring-ui/boring-design-system/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/hachej/boring-ui/boring-design-system"><img src="https://agentmods.dev/badge/skills/hachej/boring-ui/boring-design-system.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 | $0.00000 | $0.03415 |
| Opus 5.5 | $0.00000 | $0.01366 |
| Sonnet 5.5 | $0.00000 | $0.00683 |
| Haiku 4.5 | $0.00000 | $0.00342 |
Grade A, and why
boring-design-system 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 today.
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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Boring design system
The rule. An app writes theme tokens and its own components, and its components are built from kit primitives and blocks; it never copies or restyles a kit part.
Everything below follows from it. The kit (@hachej/boring-ui-kit, shadcn
components under @boring/ui/shadcn/*, blocks under @boring/ui/blocks/*)
owns how parts look and behave. The app owns its values and its screens.
The four files an app owns for its look
| File | What goes in it |
|---|---|
web/src/index.css |
The imports, in this order, and nothing visual: @import "tailwindcss"; @import "@hachej/boring-ui-kit/app.css"; @import "@hachej/boring-ui-kit/theme.derived.css"; @import "./theme.core.css"; Core comes last, so its roles and its EXCEPTIONS win. |
web/src/theme.core.css |
The core roles (below), light in :root, dark in .dark; the app's own tokens; then an === EXCEPTIONS === block for the rare derived token that must differ. |
DESIGN.md (repo root) |
The values as the designer states them, an exceptions: list (one reason per pinned token) and at most 5 lines of brand intent: the Do/Don't tokens cannot say ("lime only for the one primary action of a screen"). |
web/src/design.exceptions.json (optional; it lives in the directory the check scans) |
The app's frozen check hits. It only shrinks; when empty, delete it. |
An app never keeps its own theme.derived.css or a copy of app.css: the kit
ships both, and a copy drifts.
Core roles: what an app may set
Colours (set in :root and in .dark): --background (canvas),
--foreground (ink), --card, --primary, --primary-foreground,
--accent (hover wash), --muted (soft band), --border, --ring,
--destructive, --success, --warning, --info, --chart-series-1..5.
Shape and type (set once): --radius, --border-width, --font-sans,
--font-display, --font-mono, --text-body, --text-title, --text-chat (the assistant's reading size, 0.9375rem),
--shadow-xs, --shadow-sm, --shadow-md, --shadow-lg.
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.
- today Changed · +2 lines 70ca68159602
- yesterday First seen · 173 lines · 0 tokens per session scan A bbe2ea5545c8
boring-design-system is a skill published in the GitHub repository hachej/boring-ui (49 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,415 tokens. 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 2026-11-08.
boring-design-system compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| boring-design-systemhachej/boring-ui | Skill | 49 | today | MIT | A | 0 | Claude Code, Codex |
| anti-slop-designsickn33/agentic-awesome-skills | Skill | 49k | today | MIT | A | 34 | Claude Code |
| chakra-ui-builderchakra-ui/chakra-ui | Skill | 41k | today | MIT | A | 214 | Claude Code, Codex |
| visual-ralphYeachan-Heo/oh-my-codex | Skill | 34k | today | MIT | A | 52 | Codex |
| open-design-setupcompozy/compozy | Skill | 2.9k | today | MIT | A | 67 | Claude Code, Codex |
| prototype-webnexu-io/html-anything | Skill | 9.5k | today | Apache-2.0 | A | 24 | Claude Code, Codex |
| frontend-visual-qadaymade/claude-code-skills | Skill | 1.5k | today | MIT | A | 125 | Claude Code, Codex |