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 skills add Green-PT/honey-for-devs --skill honey-designgit clone --depth 1 https://github.com/Green-PT/honey-for-devsWrote 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/green-pt/honey-for-devs/honey-design)<a href="https://agentmods.dev/skills/green-pt/honey-for-devs/honey-design"><img src="https://agentmods.dev/badge/skills/green-pt/honey-for-devs/honey-design/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.
<a href="https://agentmods.dev/skills/green-pt/honey-for-devs/honey-design"><img src="https://agentmods.dev/badge/skills/green-pt/honey-for-devs/honey-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00017 | $0.00956 |
| Opus 5 | $0.00009 | $0.00478 |
| Sonnet 5 | $0.00003 | $0.00191 |
| Haiku 4.5 | $0.00002 | $0.00096 |
Grade A, and why
honey-design 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 11d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Honey Design (same pixels, fewer tokens)
For user-facing deliverables — landing pages, marketing sites, UI components — polish is the spec. A bare, valid-but-ugly page is a fail, not a saving.
So the token lever here is not "emit less design." It's "express the same design densely." Compress the code, never the rendered result. If a cut would change a single pixel of the finished page, it's the wrong cut.
Apply reflexively, as a writing style — don't deliberate which rule fires or spend reasoning tokens on the skill itself. Build the polished thing; write its markup and CSS the dense way by habit.
Hold the line on polish (the judged axis)
Never trade these for tokens — they are the deliverable:
- Visual depth — considered layout, spacing rhythm, real visual hierarchy, on-brand color and type. Not unstyled scaffolding.
- Every requested section, fully fleshed — nav, hero, features, pricing, footer, etc. A stubbed-out section is incomplete, not minimal.
- Interaction & motion — hover/focus states, transitions, the small touches that read as "finished."
- Responsive richness — genuinely good on mobile and desktop, not a desktop page that merely doesn't break.
- Accessibility — labelled controls,
alton every image, semantic landmarks, visible focus, sufficient contrast, keyboard paths. - Anything the user explicitly asked for.
The token lever — dense expression, identical render
Produce the same finished page with fewer tokens by removing repetition and verbosity in the code, never richness from the design:
CSS
- Custom properties for anything used more than once — palette, spacing scale,
radius, shadow, transition. Define in
:rootonce, reference everywhere. The single biggest saver: a repeated#1a1a2e/24px/box-shadow:…becomesvar(--…). - Shared classes over repeated blocks. Three feature cards = one
.cardrule, not three near-identical declaration blocks. Style by class, never inline. - Shorthand properties —
margin,padding,inset,font,flex,background,border,gridshorthands over their longhand expansions. - Fluid sizing to collapse media queries —
clamp()/min()/max()and%/fr/vwfor type and spacing, plusgrid-template-columns:repeat(auto-fit, minmax(…,1fr))andflex-wrap. One fluid rule often replaces a base rule plus two@mediaoverrides. Keep an@mediaonly where layout genuinely must change. - Group selectors that share rules (
h1,h2,h3{…}); one concise reset, not a verbose normalize; short hex (#fff), no units on0, no trailing-zero noise. - No dead, duplicated, or commented-out CSS.
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.
- 11d ago First seen · 82 lines · 17 tokens per session scan A ef92eab2046a
honey-design is a skill published in the GitHub repository Green-PT/honey-for-devs (294 stars, last pushed 3d ago), licensed MIT. It adds 17 tokens to every session and 956 once invoked, about $0.0001 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
brand-landingpage
Brand-first landing page designer — runs a brand-identity interview (colors, typography, shape language), then generates and iterates on a polished landing page via Stitch with deployment-ready HTML. Use when the user asks to create, design, or build a landing page, homepage, or marketing page and has no established…
pn-gsap
Deep GSAP API reference — timelines, easing, ScrollTrigger, plugins (SplitText, Flip, DrawSVG, MorphSVG, MotionPath), framework integrations (React useGSAP, Vue, Svelte), and performance patterns. Use when implementing GSAP-powered animations; load alongside pn-animation for motion role taxonomy and budgets.
pn-animation
Motion philosophy and governance for web interfaces. Covers the motion role taxonomy (Reveal/Orient/Confirm/Delight), library selection guide, motion budgets by page mode, prefers-reduced-motion compliance, and motion map output format. Use when designing a motion system, auditing animations, or choosing libraries.…
pn-color-system
Color system design and implementation: OKLCH color space, tinted neutrals, palette structure, contrast, dark mode architecture, and token hierarchy. Use when establishing color tokens, theming, dark mode, or reviewing color choices.
pn-design-system
Establishes or maintains a design system: tokens, CSS variables, spacing/type scales, theming, and consistency auditing. Use when defining tokens or auditing components. The pn-design-system rule enforces token usage when editing CSS/SCSS files.
pn-html-preview
Save self-contained HTML from a fenced html block, open in browser, optional screenshot evidence. Use for static UI aesthetic iteration.