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/paperclipai/paperclip/design-guidenpx skills add paperclipai/paperclip --skill design-guidegit clone --depth 1 https://github.com/paperclipai/paperclipWhat 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 | $0.00105 | $0.03017 |
| Opus 5 | $0.00053 | $0.01509 |
| Sonnet 5 | $0.00021 | $0.00603 |
| Haiku 4.5 | $0.00011 | $0.00302 |
Grade A, and why
design-guide 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 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.
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.
Copies of this mod
2 near-identical copies found in the catalogue:
- design-guide — 100% identical, 0 lines differ
- design-guide — 98% identical, 8 lines differ
How it starts
The opening of the file, as written. The whole thing — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paperclip Design Guide
Paperclip's UI is a professional-grade control plane — dense, keyboard-driven, dark-themed by default. Every pixel earns its place.
Always use with: frontend-design (visual polish) and web-design-guidelines (web best practices).
1. Design Principles
- Dense but scannable. Maximum information without clicks to reveal. Whitespace separates, not pads.
- Keyboard-first. Global shortcuts (Cmd+K, C, [, ]). Power users rarely touch the mouse.
- Contextual, not modal. Inline editing over dialog boxes. Dropdowns over page navigations.
- Dark theme default. Neutral grays (OKLCH), not pure black. Accent colors for status/priority only. Text is the primary visual element.
- Component-driven. Prefer reusable components that capture style conventions. Build at the right abstraction — not too granular, not too monolithic.
2. Tech Stack
- React 19 + TypeScript + Vite
- Tailwind CSS v4 with CSS variables (OKLCH color space)
- shadcn/ui (new-york style, neutral base, CSS variables enabled)
- Radix UI primitives (accessibility, focus management)
- Lucide React icons (16px nav, 14px inline)
- class-variance-authority (CVA) for component variants
- clsx + tailwind-merge via
cn()utility
Config: ui/components.json (aliases: @/components, @/components/ui, @/lib, @/hooks)
3. Design Tokens
All tokens defined as CSS variables in ui/src/index.css. Both light and dark themes use OKLCH.
Colors
Use semantic token names, never raw color values:
| Token | Usage |
|---|---|
--background / --foreground |
Page background and primary text |
--card / --card-foreground |
Card surfaces |
--primary / --primary-foreground |
Primary actions, emphasis |
--secondary / --secondary-foreground |
Secondary surfaces |
--muted / --muted-foreground |
Subdued text, labels |
--accent / --accent-foreground |
Hover states, active nav items |
--destructive |
Destructive actions |
--border |
All borders |
--ring |
Focus rings |
--sidebar-* |
Sidebar-specific variants |
--chart-1 through --chart-5 |
Data visualization |
What ships with it
1 file 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.
- yesterday First seen · 352 lines · 105 tokens per session scan A 07781469e7a3
design-guide is a skill published in the GitHub repository paperclipai/paperclip (79,688 stars, last pushed yesterday), licensed MIT. It adds 105 tokens to every session and 3,017 once invoked, about $0.0005 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…