micrographic

micrographic is a skill for Cursor from albegosu/micrographic-skill. It costs 143 tokens per session (15,453 once invoked), scanned A, original, MIT.

A visual design system for building compact interface components such as cards, panels, dashboards, data displays, settings blocks, and modals. It uses dense information, small metadata text, grids, and an industrial-label collage style.

In plain words
What is it for?
Use it to create dense dashboards, detail views, metric grids, data panels, and other interactive UI components with this specific visual style.
Why use it?
It provides a defined visual language for interfaces that need to show a lot of information in a small space. This avoids having to invent the component style and layout from scratch.

Skill for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use it to create dense dashboards, detail views, metric grids, data panels, and other interactive UI components with this specific visual style.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/albegosu/micrographic-skill/micrographic
Install

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.

Any agent
npx skills add albegosu/micrographic-skill --skill micrographic
Clone the repo
git clone --depth 1 https://github.com/albegosu/micrographic-skill

Made for: Cursor.

Wrote 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.

agentmods badge for micrographic

README.md
[![agentmods](https://agentmods.dev/badge/skills/albegosu/micrographic-skill/micrographic/github.svg)](https://agentmods.dev/skills/albegosu/micrographic-skill/micrographic)
Your own site
<a href="https://agentmods.dev/skills/albegosu/micrographic-skill/micrographic"><img src="https://agentmods.dev/badge/skills/albegosu/micrographic-skill/micrographic/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.

agentmods 80×15 button for micrographic

Your own site · 80×15
<a href="https://agentmods.dev/skills/albegosu/micrographic-skill/micrographic"><img src="https://agentmods.dev/badge/skills/albegosu/micrographic-skill/micrographic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 143 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 15,453 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00143 $0.15453
Opus 5.5 $0.00057 $0.06181
Sonnet 5.5 $0.00029 $0.03091
Haiku 4.5 $0.00014 $0.01545

Measured 27d ago against content hash 70ee1e018dd4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

micrographic 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 27d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.cursor/skills/micrographic/SKILL.md · 1,365 lines

How it starts

The opening of the file, as written. The whole thing — 1,365 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Micrographic Design System

Scope — components and views

Use this skill to implement UI components and views: SpecCard, DataPanel, DisplayHero, MetricGrid, Chip, settings blocks, dashboard tiles, detail panels, modals. The visual language comes from industrial labels and spec plates (examples/reference-collage.png), but the deliverable is interface code — not a printable document, shipping tag, or page mockup built from semantic HTML landmarks.

Vocabulary: component and region names (MetaStrip, DisplayHero, TexturePanel), not document anatomy (<header>, <footer>, "tags" as a layout section). Metadata strings (REF codes, serials) are content inside components, not separate page sections.

The aesthetic still reads like a physical label compressed onto a screen — maximum density, two type scales, hairline grids — applied to interactive UI.

North Star — The Collage Feeling

Visual reference: examples/reference-collage.png — the sensory target for every output.

Every output should match an industrial information collage: disparate printed artifacts — care tags, shipping labels, customs forms, spec sheets, box dielines, price stickers, poster/index panels, regulatory marks, wireframe schematics, utilitarian logo treatments — sharing one visual logic on a neutral ground. Not one template repeated; a family of label types that all compress information the same way.

Essence (use as a generation brief):

Industrial product-label collage — extreme type scale (huge display vs 7–11px micro), visible grids and hairline borders, schematic wireframes and dimension lines, barcodes/QR and regulatory metadata as decoration. Near-monochrome with signal accents only (safety orange, red, yellow). Ordered chaos: dense but grid-locked. Utilitarian, compressed, Swiss-technical — not minimal, not friendly UI.

What the collage feels like:

  • Compression, not minimalism — minimalism removes; micrographic packs. Density is intentional; every pixel carries a job.
  • Ordered chaos — maximum information density, but locked to a visible grid. It feels archival and accumulated, not randomly cluttered.
  • Function over decoration — the piece reads like documentation, packaging, or equipment marking, not a marketing layout.
  • Metadata is the ornament — REF codes, SKUs, serial strips, CE marks, barcodes, QR codes, dimensions, version numbers, and "Made in" stamps are visual texture and information.
  • Texture at distance, data up close — zoomed out: gray zones, grid rhythm, signal-color bands, photocopy grain. Zoomed in: every line parseable.
  • Archival photocopy quality — high contrast, slight grain or halftone texture; reads like a scan or duplicate of a physical document, not a glossy screen mockup.
  • Near-monochrome + signal color — black, white, warm paper, ink grays; accent colors are warnings and priorities (safety orange, FRAGIL red, caution yellow), never a decorative palette. Orange and red are collage-default signals; blue is the HUD/screen variant.
  • Swiss objectivity + industrial labeling — asymmetric grids, condensed type, objective layout — the reference is a warehouse shelf of labels and spec plates, not a SaaS marketing page.
  • Tech-wear graphic adjacency — utilitarian, technical, slightly retro-futuristic; functional marks over brand expression. Optional retro-futurism panels (space diagram, wireframe globe) are valid minor collage members, not the default output.
  • Heterogeneous views — compose different patterns (SpecCard, PosterView, FormView, TicketView, GalleryView) so screens feel like distinct artifacts, not one repeated template.

Read the full file on GitHub · 1,365 lines

Changes

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.

  1. 27d ago Changed · +2 lines 70ee1e018dd4
  2. 1mo ago First seen · 1,363 lines · 143 tokens per session scan A 9d938d2c7715

Subscribe to this mod's changes

micrographic is a skill published in the GitHub repository albegosu/micrographic-skill (6 stars, last pushed 28d ago), licensed MIT. It adds 143 tokens to every session and 15,453 once invoked, about $0.0006 per session on Opus 5.5. 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.

Related

Other skills, from other repositories

openclaw-carapace

Build or modify OpenClaw application UI using canonical semantic tokens, themes, shared CSS foundations, consumer adapters, and established local primitives. Use for product interfaces, component styling, theme work, or design-token integration.

openclaw/clawhub · 50 tokens

web-design-analyzer

A web-design analysis helper that extracts colours, typography, and component patterns from a webpage screenshot, then produces structured design-system data and a coding prompt.

anbeime/skill · 66 tokens

frontend-design

A front-end coding tool for building distinctive web pages and interface components. It focuses on unusual layouts, visual styling, animations, and production-ready code rather than generic-looking screens.

anbeime/skill · 79 tokens

frontend-design

Use when building, redesigning, or fixing a web interface. Combines distinctive visual direction with expected interaction behavior, accessible controls, complete user flows, failure recovery, and verification. Infer ordinary usability requirements without inventing product features.

Firstp1ck/pi-coding-agent-forge · 49 tokens

variant-design-system

Design System mode — tokens → components → pages three-layer workflow. Generate a complete token set (palette/type/spacing/motion/elevation/radius), confirm it, then all downstream outputs are visually consistent. Triggers on: ds, design system, tokens, create token set, define palette, define tokens, set up tokens…

YuqingNicole/variant-design-skill · 74 tokens

variant-analyze

Audit existing sites, extract design tokens, generate style-matched pages. Runs consistency checks and Visual Quality Audit (40-item anti-slop checklist, Quality Score XX/100). Triggers on: analyze my site, audit this, match this style, extract tokens, what's wrong with this design, migrate, add a page to my site…

YuqingNicole/variant-design-skill · 75 tokens