agentmods.dev

hallmark

hallmark is a skill for Claude Code, Codex from oyi77/1ai-skills. It costs 60 tokens per session (5,154 once invoked), scanned A, original, MIT.

A web design system for building and reviewing interfaces with deliberate visual rules rather than common generated templates. It defines design constraints, theme materials, page structure based on user jobs, and checks rendered pages for unwanted patterns.

In plain words
What is it for?
Use it to design, build, redesign, or review websites and web pages, including their layout, visual tokens, accessibility, and rendered output.
Why use it?
It helps identify repetitive interface choices such as generic gradients, copied card layouts, weak typography, and fabricated metrics. The checks give an agent concrete standards to follow while designing or auditing a page.

Skill for Claude CodeCodex

Written for Claude Code and Codex: argument-hint in frontmatter, but also agents/openai.yaml present. Also seen: mentions subagents; mentions Claude Code; mentions Codex.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node skills/hallmark/scripts/sloplint.mjs ./src/app --render.

Part of the 1ai-skills plugin — 216 skills, 4 commands shipped together

not rated 17repo +1 today A scan 60 tokens original MIT

Good fit Use it to design, build, redesign, or review websites and web pages, including their layout, visual tokens, accessibility, and rendered output.

Compare 6 skills from other repositories ↓
View source ↗ oyi77/1ai-skills oyi77.github.io
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/oyi77/1ai-skills
agentmods
npx agentmods add skills/oyi77/1ai-skills/hallmark

Made for: Claude Code, Codex.

Or install 1ai-skills, the plugin that ships this one along with the rest of its 216 skills, 4 commands.

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 hallmark

README.md
[![agentmods](https://agentmods.dev/badge/skills/oyi77/1ai-skills/hallmark/github.svg)](https://agentmods.dev/skills/oyi77/1ai-skills/hallmark)
Your own site
<a href="https://agentmods.dev/skills/oyi77/1ai-skills/hallmark"><img src="https://agentmods.dev/badge/skills/oyi77/1ai-skills/hallmark/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 hallmark

Your own site · 80×15
<a href="https://agentmods.dev/skills/oyi77/1ai-skills/hallmark"><img src="https://agentmods.dev/badge/skills/oyi77/1ai-skills/hallmark.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,154 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 $0.00060 $0.05154
Opus 5.5 $0.00024 $0.02062
Sonnet 5.5 $0.00012 $0.01031
Haiku 4.5 $0.00006 $0.00515

Measured today against content hash 35654908746d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hallmark 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.

content/hallmark/SKILL.md · 390 lines

How it starts

The opening of the file, as written. The whole thing — 390 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hallmark — Anti-AI-Slop Web Design Engine

Hallmark is an anti-AI-slop design system created by Nutlope and Together AI for Claude Code, Cursor, Codex, and autonomous web engineering agents. It enforces a strict, non-waivable floor against machine-generated defaults, provides a catalog of forty-eight material themes across four genres, aligns layout anatomy to user jobs, and validates rendered output through automated sloplint verification and fresh-context reviews.

Overview

AI-generated web interfaces suffer from recognizable algorithmic tropes: purple-to-blue linear gradients, tracked-capital labels, eyebrows stacked above headings, three identical feature cards, cards nested inside cards, middle-dot punctuation (A · B · C), arrows glued to button copy (Get Started →), unearned floating blur orbs, and fabricated metrics.

Hallmark halts these defaults. It treats design as material selection rather than decorative templating:

  • The Floor: Non-waivable baseline rules governing color tokens, typography scales, accessibility, viewport boundaries, and layout integrity.
  • Job-Driven Anatomy: Pages built around their primary functional purpose (a booking page books, a SaaS console operates, a publication reads).
  • Material Themes: 48 distinct palettes, typography hierarchies, and surface textures categorized into Modern Minimal, Editorial, Atmospheric, and Playful genres.
  • Multi-Width Viewport Discipline: Specific constraints across 320px, 375px, 1280px, 1440px, and 1920px viewports with an 80-word visual budget per screen.
  • Sloplint & Verification: Static and rendered linting catching visual clichés, coupled with cold-context subagent reviews.

Companion Design Framework: Impeccable

For a full-lifecycle design operating system with a 24-verb command vocabulary (shape, init, critique, audit, polish, bolder, quieter, distill, harden) and dual-truth separation (PRODUCT.md for business intent, DESIGN.md for visual tokens), pair this skill with impeccable. Hallmark enforces the uncompromising material refusal floor; Impeccable coordinates the complete UX shaping and refinement lifecycle.

Read the full file on GitHub · 390 lines

Files

What ships with it

60 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.

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. today First seen · 390 lines · 60 tokens per session scan A 35654908746d

Subscribe to this mod's changes

hallmark is a skill published in the GitHub repository oyi77/1ai-skills (17 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 5,154 once invoked, about $0.0002 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 2026-10-26.

CSS and stylingDesign and UXFrontendagentai-agentai-automationai-skillsanti-slopcontentcssthemesuiweb-design
Related

Other skills, from other repositories

popular-web-designs

54 production-quality design systems extracted from real websites. Load a template to generate HTML/CSS that matches the visual identity of sites like Stripe, Linear, Vercel, Notion, Airbnb, and more. Each template includes colors, typography, components, layout rules, and ready-to-use CSS values.

graniet/kheish · 61 tokens

popular-web-designs

54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.

davidtoby/agent-skills · 23 tokens

popular-web-designs

54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.

StarryCod/cogitum · 23 tokens

popular-web-designs

54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.

john-data-chen/hermes-agent-backup · 23 tokens

popular-web-designs

54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.

NousResearch/hermes-agent · 23 tokens

web-design-engineer

Build or redesign polished browser-rendered visual artifacts with HTML/CSS/JavaScript/React: pages, dashboards, prototypes, slide decks, animations, UI mockups, and data visualizations. Use for visual front-end creation, design-system exploration, design critique, or explicit browser acceptance / QA of a web artifact.…

ConardLi/garden-skills · 96 tokens