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/sniko/agent-skills/html-artifactsnpx skills add SNIKO/agent-skills --skill html-artifactsgit clone --depth 1 https://github.com/SNIKO/agent-skillsWrote 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/sniko/agent-skills/html-artifacts)<a href="https://agentmods.dev/skills/sniko/agent-skills/html-artifacts"><img src="https://agentmods.dev/badge/skills/sniko/agent-skills/html-artifacts.svg" alt="Measured on agentmods" 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 | $0.00045 | $0.02131 |
| Opus 5 | $0.00023 | $0.01066 |
| Sonnet 5 | $0.00009 | $0.00426 |
| Haiku 4.5 | $0.00005 | $0.00213 |
Grade A, and why
html-artifacts 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 3d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Create a static, human-readable HTML document from the material the user provides or authorizes. Use html.template.html as the visual and structural starting point. The default deliverable opens directly from disk: embed CSS, use system fonts, and require no server, build step, JavaScript, or external network resource.
This skill is document-type neutral. It presents supplied content clearly; it does not prescribe a software workflow, a canonical source format, or a particular artifact type.
Workflow
- Read the requested source material and any directly linked local assets. Identify the audience, document purpose, required sections, output path, and whether an existing source is authoritative.
- Ask only when a missing choice materially changes content, audience, or output location. If the supplied material is incomplete, label gaps or use placeholders rather than inventing facts, commitments, data, or decisions.
- Choose a scannable hierarchy suited to the content: a concise header and summary, then logical sections. Use visual structure to improve comprehension rather than mechanically reproducing source formatting.
- Start from the template and write a complete semantic HTML document. Include only elements that serve the document; remove unused template examples and placeholders.
- Apply the element guidance below whenever the document contains that content.
- Open the local file when practical and check it at desktop and narrow viewport widths. Confirm links and local assets resolve, text is legible, and the page has no horizontal overflow outside intentionally scrollable code, diagrams, or tables.
- When revising, preserve content that remains valid, apply the requested change, and update the displayed date only when the document itself says it was updated.
Document design
- Use semantic HTML:
header,main,section, headings in order,navonly for real navigation,figure/figcaption,table,pre/code, andasidefor supplementary notes. - Use the template's calm, neutral technical-document style: restrained color, generous whitespace, clear hierarchy, readable line lengths, and accessible contrast. Do not apply an organization or product brand unless requested.
- Give the document a useful
<title>, a single clear<h1>, and a short summary when the source supports one. - Keep content width comfortable for reading. Use
minmax(0, ...)for grid tracks. Long paths, identifiers, URLs, and code must wrap or scroll inside their own container rather than overflowing the page. - Use cards only to group distinct, short items. Prefer normal sections for narrative. Use callouts for decisions, assumptions, warnings, risks, or blockers; do not rely on color alone.
- Use relative links for local files and assets. Give meaningful
alttext to informative images. Do not add forms, hidden content, fabricated status, analytics, editing controls, or decorative illustrations unless requested.
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.
- 3d ago First seen · 95 lines · 45 tokens per session scan A 17ab699a46d5
html-artifacts is a skill published in the GitHub repository SNIKO/agent-skills (2 stars, last pushed 11d ago), licensed MIT. It adds 45 tokens to every session and 2,131 once invoked, about $0.0002 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
html-artifacts
Author the HTML for a plan artifact, dashboard iframe, or Slack attachment — structure, design plan, available runtime, theming, and craft. Read this before writing HTML for saveplan, outputiframe, or slackattachhtml.
bootstrap-repo-analysis
First-time analysis of a repository with no prior reviewer outcomes. Crawl historical merged-PR review feedback with the gh CLI (plus any preloaded samples), extract the team's review norms, and synthesize the initial per-repo review-style prompt. Use this for a cold-start repo; use continual-learning instead once the…
csv-workbench
Analyze CSV files in /mnt/data and return concise numeric summaries.
baby-sit
Monitor a GitHub pull request until CI is green, diagnose failures, and rerun only evidence-backed flaky GitHub Actions jobs.
continual-learning
Nightly refinement of an existing per-repo review-style prompt using this reviewer's own finding outcomes. Read confirmed (resolved-by-commit / thumbs-up) and dismissed (thumbs-down) findings, promote the bug patterns the team actually fixes, demote the false-positive patterns, reconcile against the current prompt…
opik-integrations
Build, update, test, and document Opik SDK integrations (Python & TypeScript). Use when adding a new framework/provider integration under sdks/python/src/opik/integrations or sdks/typescript/src/opik/integrations, updating an existing one, or verifying that an integration logs traces correctly.