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 cyberAlchemyAI/Arcanum --skill html-preview-servergit clone --depth 1 https://github.com/cyberAlchemyAI/ArcanumWrote 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/cyberalchemyai/arcanum/html-preview-server)<a href="https://agentmods.dev/skills/cyberalchemyai/arcanum/html-preview-server"><img src="https://agentmods.dev/badge/skills/cyberalchemyai/arcanum/html-preview-server/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/cyberalchemyai/arcanum/html-preview-server"><img src="https://agentmods.dev/badge/skills/cyberalchemyai/arcanum/html-preview-server.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 | $0.00032 | $0.02697 |
| Opus 5.5 | $0.00013 | $0.01079 |
| Sonnet 5.5 | $0.00006 | $0.00539 |
| Haiku 4.5 | $0.00003 | $0.00270 |
Grade A, and why
html-preview-server 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 1mo 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
39 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.
- development/.gitignore 221 B
- development/example-outputs/.gitkeep 1 B
- development/example-prompts/sigil-harness-validation-complex.md 733 B
- development/example-prompts/sigil-new-low.md 758 B
- development/example-prompts/sigil-observe-medium.md 711 B
- development/example-prompts/sigil-reflect-complex.md 740 B
- development/example-prompts/sigil-update-medium.md 728 B
- development/example-runs/.gitkeep 1 B
- development/experiment-loops/.gitkeep 1 B
- development/EXPERIMENT-PROFILE.md 1.1 KB
- development/fixtures/sigil-harness-validation-complex.expected.md 397 B
- development/fixtures/sigil-harness-validation-complex.md 443 B
- development/fixtures/sigil-new-low.expected.md 397 B
- development/fixtures/sigil-new-low.md 462 B
- development/fixtures/sigil-observe-medium.expected.md 360 B
- development/fixtures/sigil-observe-medium.md 431 B
- development/fixtures/sigil-reflect-complex.expected.md 411 B
- development/fixtures/sigil-reflect-complex.md 448 B
- development/fixtures/sigil-update-medium.expected.md 335 B
- development/fixtures/sigil-update-medium.md 418 B
- development/observe-experiment-report.sh 227 B runs code
- development/regimes/LIVE-SIGIL-HARNESS-VALIDATION-001.md 1013 B
- development/regimes/LIVE-SIGIL-NEW-001.md 974 B
- development/regimes/LIVE-SIGIL-OBSERVE-001.md 985 B
- development/regimes/LIVE-SIGIL-REFLECT-001.md 976 B
- development/regimes/LIVE-SIGIL-UPDATE-001.md 980 B
- development/run-example-with-codex.sh 226 B runs code
- development/run-experiment-loop.sh 224 B runs code
- development/run-validation-fixtures.sh 223 B runs code
- development/runs/.gitkeep 1 B
- development/select-example-prompt.sh 225 B runs code
- development/TASK-MATRIX.md 1.2 KB
- development/test-html-preview-server.mjs 16 KB runs code
- development/VALIDATION-EXPERIMENT.md 1.4 KB
- development/VALIDATION.md 1.9 KB
- development/write-experiment-report.sh 221 B runs code
- README.md 4.7 KB
- scripts/html-preview-server.mjs 38 KB runs code
- templates/usage-telemetry.md 1.9 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.
- 1mo ago First seen · 283 lines · 32 tokens per session scan A 32f081e96ee4
html-preview-server is a skill published in the GitHub repository cyberAlchemyAI/Arcanum (24 stars, last pushed 1mo ago), with no licence file. It adds 32 tokens to every session and 2,697 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
webui-code
Use this skill when generating or reviewing WebUI code. This skill contains knowledge on WebUI code following Chrome's Lit-element architecture and styling guidelines.
figma-to-webui
Recreate Figma design frames as production-level Chromium WebUI code following Chrome's Lit-element architecture and styling guidelines. Use when asked to create WebUI code from a Figma frame URL.
responsiveness-check
Test website responsiveness across viewport widths using browser automation. Resizes a single session through breakpoints, screenshots each width, and detects layout transitions (column changes, nav switches, overflow). Produces comparison reports showing exactly where layouts break. Trigger with 'responsiveness…
agent-canvas-edrouhardmicrosoft-agent-canvas-skills
This page used to hold an archived copy of this skill. The archive now lives in the registry's data repository.
metis-browser
Control Metis Desktop Inspector built-in browser for local preview (HTML/SVG/file paths), page interaction, accessibility snapshots, and screenshots. Use when the user asks to open, show, preview, inspect, click, type, or verify UI in the in-app/built-in browser. Prefer browsernavigate over bash…
browser-81345ecd
A browser-rendering skill for distinguishing reflow from repaint. Reflow recalculates the positions and sizes of page elements; repaint redraws their appearance.