Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add atman-33/workhub/plugin install visualsWrote 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/atman-33/workhub/html-doc)<a href="https://agentmods.dev/skills/atman-33/workhub/html-doc"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/html-doc.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 5.1 | $0.00095 | $0.01494 |
| Opus 5 | $0.00048 | $0.00747 |
| Sonnet 5 | $0.00019 | $0.00299 |
| Haiku 4.5 | $0.00010 | $0.00149 |
Grade A, and why
html-doc 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HTML doc
One .html file with inline CSS and JS. It opens in any browser, works
offline, and travels as an attachment or a PDF.
Source: visualize. See the
plugin's NOTICE.md.
When it is worth it
HTML costs more to produce than Markdown. It earns that back when the document would run past roughly 100 lines, or needs a table, a diagram, a side-by-side comparison, colour coding, or an interaction. Below that, write the Markdown.
Two more cases where Markdown wins even when it is long: a document that is reviewed as text in a pull request, and one that has to diff cleanly in version control.
Non-negotiables
- Start from
${CLAUDE_PLUGIN_ROOT}/shared/html-skeleton.md. Copy the whole skeleton, then add content. It carries the themes, the utility menu, the print rules and the accessibility scaffolding. - Read
${CLAUDE_PLUGIN_ROOT}/shared/design-system.mdbefore choosing type or colour. Keep the eleven token names exactly. - Never fabricate. No lorem ipsum, no invented figures, no placeholder chart data. If a number was not read from a real source, it does not go in. Where the source matters, cite it in the document.
- One file. Inline CSS and JS. A CDN script is allowed when it does real work — a chart library — and not for a CSS framework.
1. Pick the shape
| Shape | For | Spine |
|---|---|---|
| Explainer | Answering an enquiry, walking someone through a decision or a mechanism | The question at the top, the answer, then the reasoning |
| One-pager | A single proposal, feature or offer | A hero line, three or four sections, one conclusion |
| Report | Research, status, an investigation | Findings first, method after |
| Dashboard | Numbers people check | KPI row, then charts and tables |
| Comparison | Choosing between options | A matrix, with the recommendation marked |
Read references/doc-types.md for the layout grammar of the one you picked.
If nothing fits cleanly, write a report.
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 · 139 lines · 95 tokens per session scan A a8dc6ab5c21c
html-doc is a skill published in the GitHub repository atman-33/workhub (2 stars, last pushed yesterday), licensed MIT. It adds 95 tokens to every session and 1,494 once invoked, about $0.0005 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 2026-09-05.
Other skills, from other repositories
researcher
Use when asked to create research documents, generate PDFs, make one-pagers, or create cheatsheets. Triggers: "research document", "generate PDF", "one-pager", "cheatsheet", "distinctive design". Provides HTML/Markdown/PDF with Terminal, Editorial, Corporate, Industrial, Fresh aesthetic presets.
gemini-file-analysis
Analyze files (PDFs, images, audio, video, large source files) via Gemini's multi-modal file analysis. Use when a file is too large for Claude's context or when the file is a non-text format requiring visual/audio understanding.
pdf-processor
A workflow for working with PDF files, a document format that preserves page layout across devices.
export-pdf
Convert a markdown file to PDF using mdpdf. Use when exporting proposals, SOPs, or any markdown document to PDF.
learn
Ingests an external data source into the Second Brain. Fetches content from Confluence, Google Docs, GitHub repositories, remote URLs, or any local file format supported by docling (DOCX, PPTX, XLSX, PDF, HTML, EPUB, images, Markdown, CSV, and more), converts non-markdown formats to markdown via docling, runs the…
paddleocr-doc-parsing
PaddleOCR document parsing guidance for PDFs and images hosted on Baidu AI Studio. Use when the user wants to extract text or structured markdown from scans, screenshots, photos, tables, or PDFs and needs help choosing PaddleOCR options such as fileType, orientation correction, unwarping, layout detection, chart…