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 alexagriffith/agent-skills --skill visual-style-lawsgit clone --depth 1 https://github.com/alexagriffith/agent-skillsWrote 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/alexagriffith/agent-skills/visual-style-laws)<a href="https://agentmods.dev/skills/alexagriffith/agent-skills/visual-style-laws"><img src="https://agentmods.dev/badge/skills/alexagriffith/agent-skills/visual-style-laws/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/alexagriffith/agent-skills/visual-style-laws"><img src="https://agentmods.dev/badge/skills/alexagriffith/agent-skills/visual-style-laws.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 | $0.00057 | $0.01024 |
| Opus 5 | $0.00028 | $0.00512 |
| Sonnet 5 | $0.00011 | $0.00205 |
| Haiku 4.5 | $0.00006 | $0.00102 |
Grade A, and why
visual-style-laws 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 12d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual style laws
Rules for anything visual (walkthrough HTML, slides, interactive explainers, data-viz). Prose voice lives in the voice guide; this governs the visual layer.
Principles, not templates. Examples illustrate a rule, they are not the only right phrasing. Apply the principle in the author's voice — don't pattern-match the example.
1. Headings name the subject, plainly
A heading names what the section IS — the concept or the move — in the fewest plain words. It reads like a nav label. It does not moralize: no "don't", no "before you trust X", no problem framing that makes the reader parse a warning before they learn the topic.
- Good: "Establish baseline", "Find the operating point", "Verify".
- Wrong, same sections: "Check the cluster before trusting any prior number", "Sweep to the knee, don't guess it", "One run is not a result".
- Test: could it be a tab label, and does it say the topic, not the pitfall?
2. Page-topic lines command; feature verbs come from the source
The hero line introducing a page is a command or a question, never a limp verb. "Measuring flow control under pressure" — not "Flow control keeps…", "…lets…". When you say what a feature does, use the verb its own docs use ("flow control enables intelligent request queuing"), not a softer invented one.
3. Name a real contrast; never the rhetorical not-Y
If a section is genuinely a two-sided comparison, name it ("Separation vs SLO"). Banned everywhere — headings, labels, sentences — is the not-Y flourish: "it's not just A, it's B", "what it is and what it is not". State the thing.
4. No eyebrow kickers
No small uppercase kicker above a heading — no "SECTION · LABEL", no numbered "① STEP NAME", no per-slide tag. The heading leads. A kicker is a second type level repeating the title; if you want one for orientation, fix the title.
5. Visuals carry the evidence, not paragraphs
A visual unit is title + one takeaway line (≤ 15 words) + the visual. The chart or number cards carry the evidence. Longer explanation goes to notes or a collapsible, never the face — a paragraph on a visual unit is a blog.
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.
- 12d ago First seen · 91 lines · 57 tokens per session scan A 2a01fc3d0391
visual-style-laws is a skill published in the GitHub repository alexagriffith/agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 1,024 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.