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/minorun365/html-share/create-htmlnpx skills add minorun365/html-share --skill create-htmlgit clone --depth 1 https://github.com/minorun365/html-shareWhat 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 | $0.00075 | $0.00693 |
| Opus 5 | $0.00037 | $0.00347 |
| Sonnet 5 | $0.00015 | $0.00139 |
| Haiku 4.5 | $0.00007 | $0.00069 |
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 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 — 41 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 question-and-answer layout over a grid of generic cards. Read layout-patterns.md when the page has multiple content types.
- Copy brief-template.html as the starting point. Remove unused components and replace every
{{PLACEHOLDER}}. - Write a single self-contained
.htmlfile. Keep CSS and any small SVG illustrations inline. Do not require a build step, JavaScript framework, CDN, external font, or analytics. - Verify the content and public-safety boundary before presenting or publishing it.
- Check the rendered page at desktop width and around 390 px. Fix overflow, awkward wrapping, tiny text, and excessive empty space.
Design contract
- Use light mode with deep blue as the base, neutral white surfaces, and gold as the only accent.
- Reserve the blue gradient for the hero, section markers, and table headers. Do not fill every component with gradients.
- Keep the main content at about 940 px, body text at least 16 px, and line height around 1.8.
- Use Japanese system fonts first:
-apple-system,BlinkMacSystemFont,"Hiragino Sans","Yu Gothic UI",sans-serif. - Give each section one clear message. Use cards only for genuinely independent facts or metrics.
- Make tables horizontally scrollable inside their own container; never let the page itself scroll sideways.
- 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
3 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.
- 2d 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 (85 stars, last pushed 5d ago), licensed Apache-2.0. It adds 75 tokens to every session and 693 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 2026-08-30.
Other skills, from other repositories
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
hyperframes-registry
Install, discover, and wire registry blocks and components into HyperFrames compositions. Use when running hyperframes add or hyperframes catalog, installing one item or every block matching a tag, wiring an installed item into index.html, or working with hyperframes.json. Covers discovery, install locations, block…
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
hyperpod-version-checker
Check and compare software component versions on SageMaker HyperPod cluster nodes - NVIDIA drivers, CUDA toolkit, cuDNN, NCCL, EFA, AWS OFI NCCL, GDRCopy, MPI, Neuron SDK (Trainium/Inferentia), Python, and PyTorch. Use when checking component versions, verifying CUDA/driver compatibility, detecting version mismatches…
github
Interact with GitHub (issues, PRs, repos, releases) using the gh CLI. Use when asked to read or write GitHub state — open an issue, fetch PR diff, comment, list runs, etc.
post-build-flow
Handles workflow verification and setup after build-workflow succeeds, or when the message contains workflow-verification-follow-up or workflow-setup-required. Load after direct builds, when verificationReadiness requires action, or on orchestrator verify/setup follow-up turns.