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 zenitheditor/zenith --skill htmlgit clone --depth 1 https://github.com/zenitheditor/zenithWrote 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/zenitheditor/zenith/html)<a href="https://agentmods.dev/skills/zenitheditor/zenith/html"><img src="https://agentmods.dev/badge/skills/zenitheditor/zenith/html/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/zenitheditor/zenith/html"><img src="https://agentmods.dev/badge/skills/zenitheditor/zenith/html.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00054 | $0.00243 |
| Opus 5.5 | $0.00022 | $0.00097 |
| Sonnet 5.5 | $0.00011 | $0.00049 |
| Haiku 4.5 | $0.00005 | $0.00024 |
Grade A, and why
html-design-revision 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 5d 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.
What it actually says
HTML design revision
Revise the design file in place. Change only what the request names. Every other element keeps its position, size, color and text.
Read references/revising.md before the first edit.
- Read the whole file first. Find the rule or element the request names.
- Make the smallest edit that does it. Prefer
edit_fileover rewriting the file. - Reuse existing classes, variables and values. Never rename or reorder unrelated rules.
- Keep the layout model of the file. If the file uses flex, stay on flex. Never mix in absolute positioning to fix one element.
- Render with
viewafter the edit and compare against the request. - Check that nothing else moved: text did not rewrap, boxes did not shift, nothing overflows the canvas.
- Reply with one short sentence when done.
What ships with it
1 file 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.
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.
- 5d ago First seen · 19 lines · 54 tokens per session scan A 0bbb7b230fd1
html-design-revision is a skill published in the GitHub repository zenitheditor/zenith (22 stars, last pushed 4d ago), licensed Apache-2.0. It adds 54 tokens to every session and 243 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 2026-10-11.
Other skills, from other repositories
design-taste-frontend
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
design-taste-frontend-v1
The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is design-taste-frontend (v2 experimental), which is a substantial rewrite. Use this v1 install name only if you need exact backward compatibility.
high-end-visual-design
Teaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, and animations that make a website feel expensive. Blocks all the common defaults that make AI designs look cheap or generic.
gpt-taste
Elite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.
site-header
Design and build the site-wide header (logo, menu, language switcher, cart, call to action) yourself, then have the site save it in the right places and check it. Activate whenever the user asks to create, fix, redesign, modernise, tidy or "make professional" a header or top navigation, or complains that the menu…
block-theme
Change a block theme's look and structure the way the site editor does - Global Styles (colours, fonts, spacing), templates and template parts (header, footer, single, page), patterns and navigation menus - with undo. Activate when the user asks to change site-wide colours or fonts, edit the header, footer or a page…