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/var-gg/pindoc/design-systemnpx skills add var-gg/pindoc --skill design-systemgit clone --depth 1 https://github.com/var-gg/pindocWrote 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/var-gg/pindoc/design-system)<a href="https://agentmods.dev/skills/var-gg/pindoc/design-system"><img src="https://agentmods.dev/badge/skills/var-gg/pindoc/design-system.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 5.1 | $0.00000 | $0.00774 |
| Opus 5 | $0.00000 | $0.00387 |
| Sonnet 5 | $0.00000 | $0.00155 |
| Haiku 4.5 | $0.00000 | $0.00077 |
Grade A, and why
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 6d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pindoc · Design Skill
When asked to design anything inside Pindoc — the agent-writable, human-approvable project wiki — follow these rules. This file is the compact, agent-invocable version of README.md. Read both before starting.
Product in one line
Pindoc is a typed, graph-linked project wiki that humans never edit directly. Agents (Claude Code, Cursor, Codex) write over MCP; humans review, approve, reject, and read.
Design DNA (in priority order)
- Developer tool at rest. Linear-density lists. Obsidian-spacious reader. GitHub-PR review flow.
- Dark mode is Day 1. Light mode is
:root.theme-light, retuned from the same tokens. - Borders define surfaces, not shadows. Shadows appear only on floating UI (⌘K, menus, modals, toasts).
- Status color is the only saturated color.
draftamber ·liveemerald ·stalerose ·archivedzinc ·rejectedred. Accent indigo is restrained — focus, selection, one primary action per view. - Monospace is a signal. JetBrains Mono marks the typed/code-adjacent: artifact IDs, type chips (
ADR,FEATURE), area labels (platform/auth), agent names.
Do NOT design
- WYSIWYG editors, rich-text toolbars, inline edit pencils. Humans do not write.
- Decorative illustrations, marketing hero art, gradient-heavy cards.
- Bluish-purple SaaS gradients. Capsule pills (
9999px). Emoji in chrome. - Welcoming/cheerful copy (
Welcome!,Let's get started ✨,Awesome!).
Tokens
Import colors_and_type.css. Use the variables — never hard-code hex or px from the palette. Spacing scale 4 · 8 · 12 · 16 · 20 · 24 · 32 · 48 · 64. Radii 2 · 4 · 6 · 8.
Density rule
Two densities, by surface: compact (lists, sidebar, queue, graph inspector — 32px rows, 13px text) and spacious (reader body — 16px / 1.6). Never mix within one pane.
Voice
Technical, direct, lowercase by default for status/actions (draft, promote, approve). Title Case only for proper nouns, primary buttons, and headings. No exclamation marks. No adjectives that sell.
What ships with it
20 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.
- assets/logo.svg 910 B
- assets/wordmark.svg 967 B
- colors_and_type.css 21 KB
- fonts/Inter-Medium.woff2 74 KB
- fonts/Inter-Regular.woff2 47 KB
- fonts/Inter-SemiBold.woff2 61 KB
- fonts/JetBrainsMono-Variable.woff2 31 KB
- preview/agent-avatars.html 3.7 KB
- preview/colors-neutral.html 5.2 KB
- preview/colors-status.html 4.2 KB
- preview/components.html 9.8 KB
- preview/iconography.html 4.4 KB
- preview/logo.html 7.3 KB
- preview/spacing.html 3.8 KB
- preview/task-pills.html 4.3 KB
- preview/type.html 2.8 KB
- README.md 14 KB
- ui_kits/reader/chrome.html 31 KB
- ui_kits/reader/reader.html 44 KB
- ui_kits/reader/tasks.html 34 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.
- 6d ago First seen · 43 lines · 0 tokens per session scan A bf01857eba27
design-system is a skill published in the GitHub repository var-gg/pindoc (12 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 774 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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…