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 minorun365/html-share --skill create-htmlgit clone --depth 1 https://github.com/minorun365/html-shareWrote 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/minorun365/html-share/create-html)<a href="https://agentmods.dev/skills/minorun365/html-share/create-html"><img src="https://agentmods.dev/badge/skills/minorun365/html-share/create-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/minorun365/html-share/create-html"><img src="https://agentmods.dev/badge/skills/minorun365/html-share/create-html.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00075 | $0.01824 |
| Opus 5.5 | $0.00030 | $0.00730 |
| Sonnet 5.5 | $0.00015 | $0.00365 |
| Haiku 4.5 | $0.00007 | $0.00182 |
Grade A, and why
create-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 19d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create HTML
Turn the user's content into one complete HTML file that is calm, readable, and ready to share. Keep the information primary; styling should make the structure easier to scan.
Workflow
- Confirm the source material, audience, and purpose from the conversation and local files. Do not invent facts to fill empty sections.
- Decide the information structure before styling. Prefer a short narrative, comparison table, timeline, or paired layout over a grid of generic cards. Read layout-patterns.md when the page has multiple content types, a schedule, a revision, or a decision to request.
- Copy brief-template.html as the starting point. Keep its stylesheet whole and add only the parts this content needs; do not write a new stylesheet and then patch in the template's tokens. Remove unused components and replace every
{{PLACEHOLDER}}. design-rules.md explains why each rule in the stylesheet exists. - Write a single self-contained
.htmlfile. Keep CSS and small SVG illustrations inline. Do not require a build step, JavaScript framework, CDN, external font, or analytics. - Run the checks below and fix every NG line.
- When the page uses a mechanism the template does not have (a calendar, a new grid, content in the hero), render it at desktop width and around 390 px and run render-checks.md. Look at one screenshot yourself; passing numbers are not the same as having seen the page.
Design contract
- Light mode. One deep-blue gradient as the base, neutral text and lines, gold as the only accent, used as points rather than surfaces. Do not color-code sections with extra hues.
- The gradient appears in five places only: the full-width hero, the 72 px bar on each section divider, the section numbers, the table header, and card header bands. Bands never nest: a table or Before/After inside a card uses a white header with a small pill label.
- Main content about 940 px wide, body text at least 15 px, line height around 1.85.
- Use Japanese system fonts first:
-apple-system,BlinkMacSystemFont,"Hiragino Sans","Yu Gothic UI",sans-serif. - Tables have no vertical rules and no
min-width. On phones the delivered page folds narrow tables into stacked cards, so avoidwhite-space: nowrapon long cells and never shrink text to make a table fit. - Use semantic headings in order, visible focus styles, sufficient color contrast, and descriptive link text.
- Keep decorative icons minimal. Prefer CSS shapes or inline SVG to emoji-heavy decoration.
What ships with it
6 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.
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.
- 19d ago Changed · +42 lines eed91ac20706
- 1mo ago First seen · 41 lines · 75 tokens per session scan A 9d746b3ff1ec
create-html is a skill published in the GitHub repository minorun365/html-share (110 stars, last pushed 19d ago), licensed Apache-2.0. It adds 75 tokens to every session and 1,824 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
agent-squad-swift
Use when building or modifying a Swift app that uses the AgentSquad Swift framework — on-device multi-agent orchestration for iOS 16+ / macOS 14+: orchestrator, agents (Agent, GroundedAgent), classifier routing, LLM clients (OpenAI-compatible), tools (native + MCP), tool UIs/widgets, on-device storage, tracing, and…
location-skill
Get Android device GPS location - latitude, longitude, accuracy, speed, and provider information.
wifi-skill
Control Android WiFi - enable, disable, get status, scan for networks, and get current connection info.
app-launcher-skill
Launch Android applications by package name. Open any installed app programmatically.
app-list-skill
Get list of installed Android applications with package names, versions, and metadata.
audio-skill
Control Android audio - get/set volume, mute/unmute for media, ringtone, notification, and call volumes.