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 agentmods add skills/duyet/oma/generate-htmlnpx skills add duyet/oma --skill generate-htmlgit clone --depth 1 https://github.com/duyet/omaWhat 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 | $0.00085 | $0.00878 |
| Opus 5 | $0.00043 | $0.00439 |
| Sonnet 5 | $0.00017 | $0.00176 |
| Haiku 4.5 | $0.00009 | $0.00088 |
Grade A, and why
generate-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 2d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
generate-html
Produce one .html file that renders correctly with no network access.
Everything inlined: CSS in <style>, JS in <script>, images as data: URIs,
fonts as system stacks. The test: rename the file, disconnect from the network,
open it — it must look identical.
Start from template.html and fill it in rather than writing a
page from scratch.
Hard requirements
- Self-contained. No
<link href="https://…">, no<script src="//cdn…">, no@import url(...), no remote images. If you need a chart lib or icons, inline the source. A page that fetches on load is not done. - Responsive. Fluid layout (flexbox/grid,
max-widthcontainer, relative units). Include<meta name="viewport" content="width=device-width,initial-scale=1">. Wide tables/code go in anoverflow-x:autowrapper so the body never scrolls sideways on mobile. - Dark and light. Drive all colors from CSS custom properties and provide a
@media (prefers-color-scheme: dark)override. Never hardcode#fffbackgrounds or#000text on elements. - Valid + accessible. One
<h1>, then a sane heading order; semantic tags (<header> <main> <section> <table> <figure>);alton images; labels on any inputs; text contrast >= 4.5:1.
Layout defaults that look good
- Constrain reading width:
main{ max-width: 72ch; margin-inline:auto; }for prose;max-width: 1100pxfor dashboards. - Type scale: body
16px/1.6, system font stack, headings ~1.25 step ratio. - Spacing on a consistent scale (e.g. 4/8/16/24/32px). Generous whitespace beats borders everywhere.
- Cards/tables: subtle border (
1px solid var(--border)) + small radius, not heavy shadows. Zebra-stripe long tables withtbody tr:nth-child(even). - Numbers in tables: right-align and use
font-variant-numeric: tabular-nums.
Reports specifically
- Open with a title, a one-line summary/date, then the key finding — don't bury the lede below setup.
- Section with
<h2>; each section leads with its conclusion, evidence follows. - Data → a
<table>or an inline SVG chart (see thedata-vizskill for chart rules); never paste a screenshot of a table you could render as HTML. - Add a small footer with generation date and source.
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.
- 2d ago First seen · 68 lines · 85 tokens per session scan A f30d86065929
generate-html is a skill published in the GitHub repository duyet/oma (5 stars, last pushed 13d ago), licensed Apache-2.0. It adds 85 tokens to every session and 878 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.