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/psd401/psd-claude-plugins/hallmarknpx skills add psd401/psd-claude-plugins --skill hallmarkgit clone --depth 1 https://github.com/psd401/psd-claude-pluginsWrote 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/psd401/psd-claude-plugins/hallmark)<a href="https://agentmods.dev/skills/psd401/psd-claude-plugins/hallmark"><img src="https://agentmods.dev/badge/skills/psd401/psd-claude-plugins/hallmark.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 | $0.00258 | $0.16644 |
| Opus 5 | $0.00129 | $0.08322 |
| Sonnet 5 | $0.00052 | $0.03329 |
| Haiku 4.5 | $0.00026 | $0.01664 |
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 4d 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.
This is a copy
94% identical to hallmark — 41 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 590 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hallmark
Attribution. Vendored from
nutlope/hallmark— authored by Hassan El Mghari (nutlope), made by Together AI, copyright "Hallmark contributors". Upstream v1.1.0, commit13ac0ec(2026-08-06), vendored 2026-08-22. Upstream is MIT licensed; the license text travels with this copy asLICENSE.upstream, which satisfies the MIT attribution requirement.PSD adaptations (rule-set text is unmodified):
- Frontmatter rewritten for the PSD plugin standard (
model/effort/extended-thinking, narrowed description so it doesn't collide with/lfg, addedargument-hint).site/css/tokens.cssvendored toreferences/tokens.css— a functional dependency, not a doc link: 16 of the 21 themes exist only as token blocks in that file.docs/recipes.mdanddocs/study-examples.mdvendored toreferences/.- Links to upstream
site/examples/andsite/_tests/builds repointed at GitHub (not vendored).
A design skill for AI coding assistants. Makes the UIs they generate look made, not generated.
Hallmark is opinionated, short, and boring on purpose. It encodes a tight set of rules — drawn from the consensus of the anti-AI-slop design field (Anthropic's frontend-design skill, the Claude cookbook on frontend aesthetics, and the 2026 "tactile rebellion" movement) — and refuses to let the model fall back to the defaults every LLM was trained on.
The differentiator: Hallmark insists on structural variety, not just visual variety. Two pages by Hallmark for two different briefs should not share the same hero → 3-feature → CTA → footer rhythm. They should feel like different sites, not different colour-swaps of the same template. See references/structure.md.
Powered by Together AI.
How to use this skill
Hallmark has one default behaviour and three explicit verbs.
| Invocation | What it does |
|---|---|
| (default) | The user asked you to design or build something new. Follow the Design flow below. |
hallmark audit <target> |
Read the target, score it against the anti-pattern list, return a ranked punch list. Do not edit. |
hallmark redesign <target> [--mood <name>] |
Take the target's content and intent, then redesign the visual structure inside the existing implementation boundaries unless the user explicitly confirms a full rebuild. New section rhythm, new heading placement, new component voice. Preserve existing routes, component ownership, copy intent, brand, and information architecture; replace only the visual/interaction layer needed for the requested scope. |
hallmark study <screenshot | URL> |
The user pasted or attached an image of a design they admire, or pasted a URL to a live page. Extract the DNA — macrostructure, archetypes, type-pairing, colour anchor — and produce a diagnosis report, then optionally rebuild the user's content using the extracted DNA or emit a portable design.md of the DNA. Detection is automatic: a URL (http:// / https:// prefix) routes to URL mode; anything else routes to image mode. URL mode reads the page's HTML and CSS via WebFetch — it can name exact fonts and exact colour values, but can't judge rhythm. After the diagnosis, the user has three follow-ups: build with the DNA (handoff to default), lock the DNA into a portable design.md (opt-in via "lock the DNA" / "give me a design.md"), or stop at the diagnosis. Never copies pixels. Refuses template-marketplace URLs. Tighter refusal layer for design.md emission than for the diagnosis itself — URL-mode emission requires attestation that the source is the user's own or a public reference for their own brand. Falls back to asking for a screenshot if the URL is auth-walled, a JS-only SPA shell, or otherwise un-readable. Load references/study.md before this verb runs. |
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.
- LICENSE.upstream 1.1 KB
- references/anti-patterns.md 25 KB
- references/assets.md 25 KB
- references/color.md 4.2 KB
- references/component-cookbook.md 30 KB
- references/components/c1-outlined-chip.md 464 B
- references/components/c2-inline-form-as-cta.md 672 B
- references/components/c3-typographic-link.md 280 B
- references/components/c4-sticky-bottom-bar.md 671 B
- references/components/f1-bento-grid.md 782 B
- references/components/f2-sticky-scroll-stack.md 899 B
- references/components/f3-tabular-spec-sheet.md 419 B
- references/components/f4-step-sequence.md 448 B
- references/components/f5-annotated-screenshot.md 410 B
- references/components/f6-product-card-grid.md 2.7 KB
- references/components/ft1-mast-headed.md 501 B
- references/components/ft2-inline-rule-single-line.md 362 B
- references/components/ft3-index-style-category-list.md 483 B
- references/components/ft4-dense-typographic.md 501 B
- references/components/ft5-statement.md 1.3 KB
- references/components/ft6-letter-close.md 1.1 KB
- references/components/ft7-newsletter-first.md 1.7 KB
- references/components/ft8-marquee-scroll.md 1.5 KB
- references/components/h1-marquee.md 507 B
- references/components/h2-split-diptych.md 600 B
- references/components/h3-quote-led.md 420 B
- references/components/h4-stat-led.md 509 B
- references/components/h5-letter-hero.md 361 B
- references/components/h6-photographic-fold.md 586 B
- references/components/h7-demo-video-clipped-by-viewport-edge.md 1.6 KB
- references/components/h8-mockup-split-browser-framed.md 1.3 KB
- references/components/h9-custom-illustration-centerpiece.md 1.4 KB
- references/components/n1-wordmark-2-links.md 388 B
- references/components/n10-floating-on-scroll-morph.md 1.4 KB
- references/components/n11-mega-menu.md 3.1 KB
- references/components/n12-banner-retract.md 2.8 KB
- references/components/n13-inline-cmdk-pill.md 3.2 KB
- references/components/n1b-saas-three-section.md 3.0 KB
- references/components/n2-floating-chip.md 617 B
- references/components/n3-side-rail.md 536 B
- references/components/n4-hidden-behind-k.md 373 B
- references/components/n5-floating-pill.md 1.4 KB
- references/components/n6-newspaper-masthead.md 1.6 KB
- references/components/n7-brutal-slab.md 1.3 KB
- references/components/n8-terminal-command.md 1.6 KB
- references/components/n9-edge-aligned-minimal.md 868 B
- references/components/s1-left-margin-numbered.md 495 B
- references/components/s2-hanging.md 357 B
- references/components/s3-sticky-pinned.md 1.2 KB
- references/components/s4-inline-no-break.md 438 B
- references/components/s5-bottom-anchored.md 358 B
- references/components/t1-pull-quote-with-marginalia.md 465 B
- references/components/t2-logo-wall-hairline.md 733 B
- references/components/t3-single-huge-quote.md 490 B
- references/components/t4-numbered-stat-strip.md 470 B
- references/contract.md 2.0 KB
- references/copy.md 12 KB
- references/custom-craft.md 33 KB
- references/custom-theme.md 23 KB
- references/design-md.md 6.7 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.
- 4d ago First seen · 590 lines · 258 tokens per session scan A d55d5e4678b8
hallmark is a skill published in the GitHub repository psd401/psd-claude-plugins (2 stars, last pushed 3d ago), licensed MIT. It adds 258 tokens to every session and 16,644 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to hallmark, differing in 41 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…