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 xbklairith/kisune --skill explain-in-htmlgit clone --depth 1 https://github.com/xbklairith/kisuneWrote 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/xbklairith/kisune/explain-in-html)<a href="https://agentmods.dev/skills/xbklairith/kisune/explain-in-html"><img src="https://agentmods.dev/badge/skills/xbklairith/kisune/explain-in-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/xbklairith/kisune/explain-in-html"><img src="https://agentmods.dev/badge/skills/xbklairith/kisune/explain-in-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 | $0.00100 | $0.01091 |
| Opus 5.5 | $0.00040 | $0.00436 |
| Sonnet 5.5 | $0.00020 | $0.00218 |
| Haiku 4.5 | $0.00010 | $0.00109 |
Grade A, and why
explain-in-html 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 18d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explain in HTML
A terminal is a poor renderer for anything with a shape. This skill moves that output to a page.
It owns the medium, not the decision. grilling decides what to interrogate, brainstorming decides what to elicit, scrutinize decides what to review — each keeps that job and hands the rendering here. When one of them owns the decision, it runs first and calls this. Never publish a page to sidestep deciding who should be asking.
Two modes, inferred from content
| Content | Mode | Output |
|---|---|---|
| Something to understand — architecture, schema, state machine, a comparison | explain | A page with diagrams and tables |
| Something to answer — a question round, a set of choices | interact | A page with the questions answerable in-browser |
Do not ask which mode. Read the content. Mixed content is one page — a short explainer above the questions, never two deliverables.
Default to the page
Use the page whenever the content has structure worth seeing. Fall back to terminal text only for a trivial confirm — a yes/no, a single pick from two obvious options. One question is a sentence; three are a page; at two, use the page if the choices interact.
How to build it
Artifact quickstartwithintent: "other"— it returns the page-design contract. Do not also loadartifact-design.- Figures — delegate, never improvise. Both of these are built-in skills that own their own rules; do not restate them here, load them.
- Mechanism — how it works, what talks to what, before/after →
artifact-diagramming - Quantities — magnitude, distribution, change over time →
dataviz, which has hard requirements of its own (run its palette validator; never a dual-axis chart) - Within a diagram: Mermaid (
<pre class="mermaid">, rendered natively — no CDN) for sequence, state, ER and flow; hand-authored inline SVG for before/after and side-by-side, which Mermaid renders badly.
- Mechanism — how it works, what talks to what, before/after →
- Publish via
Artifact. Interact pages followgrilling's rule — every question carries a recommended answer, so a user who agrees can say "yes to all" and move on. For interact mode declarecapabilities: {db: {}, user: {}}— that is what makes answers savable and readable back. Adddownloads: trueonly if the user wants a file too. Explain mode needs none.
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.
- 18d ago First seen · 65 lines · 100 tokens per session scan A 6d822c8dc991
explain-in-html is a skill published in the GitHub repository xbklairith/kisune (3 stars, last pushed 8d ago), licensed MIT. It adds 100 tokens to every session and 1,091 once invoked, about $0.0004 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 2026-09-30.
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.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
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.