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 raunaqbn/html-docs-skill --skill html-docsgit clone --depth 1 https://github.com/raunaqbn/html-docs-skillWrote 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/raunaqbn/html-docs-skill/html-docs)<a href="https://agentmods.dev/skills/raunaqbn/html-docs-skill/html-docs"><img src="https://agentmods.dev/badge/skills/raunaqbn/html-docs-skill/html-docs/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/raunaqbn/html-docs-skill/html-docs"><img src="https://agentmods.dev/badge/skills/raunaqbn/html-docs-skill/html-docs.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00107 | $0.02325 |
| Opus 5.5 | $0.00043 | $0.00930 |
| Sonnet 5.5 | $0.00021 | $0.00465 |
| Haiku 4.5 | $0.00011 | $0.00232 |
Grade A, and why
html-docs scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Anonymous documents can be published with `curl` or the CLI. How it starts
The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HTML Docs
Create the clearest useful explanation of the user’s source. Use the active Codex or Claude session to research, write, design, and author the artifacts. Use the local CLI only to normalize sources, compile, validate, render, synchronize, and publish. Never invoke a hidden authoring model.
Choose the output
Resolve an explicit user request first. Otherwise use auto:
| Mode | Choose when | Deliver |
|---|---|---|
document |
Detail, scanning, reference, data, or collaboration matters | Designed responsive HTML document |
video |
Motion, sequence, mechanism, or narration is the main value | Captioned deterministic HTML video |
document-video |
A focused subject benefits from both explanation and reference | Rich document with embedded live video |
course |
The source has several learning outcomes or the user asks for training | Learning site with modules, lesson pages, videos, checks, and progress |
auto |
The user leaves the format open | document-video for one focused outcome; course for several cumulative outcomes |
State the chosen mode in one short working update, then continue. Do not stop for storyboard or voice approval unless the user requests an approval gate. Finish automatic work as a private preview. Publish publicly or unlisted only after explicit instruction.
Start from any source
Classify the input before authoring:
- HTML Docs document or folder: read it through the API.
- Local document, PDF, HTML, Markdown, or text: recover its structure and facts.
- Directory or Git repository: respect ignore rules; exclude credentials, dependencies, build output, binaries, and VCS internals.
- URL: capture the requested page. For a site-level request, crawl same-origin links to depth two and at most 100 pages unless the user sets another bound.
- Research topic: perform deep research with primary and authoritative sources. Freeze a source manifest before writing.
- Pasted material: preserve it as a source record rather than treating it as unsupported background knowledge.
What ships with it
17 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.
- agents/openai.yaml 400 B
- references/anti-slop.md 10 KB
- references/api.md 12 KB
- references/course-specification.md 5.1 KB
- references/design-commands.md 5.1 KB
- references/design-dna.md 6.2 KB
- references/design-system.md 29 KB
- references/effects.md 5.6 KB
- references/html-course.md 5.6 KB
- references/html-video.md 6.6 KB
- references/learning-design.md 5.4 KB
- references/NOTICE 4.4 KB
- references/pdf.md 9.1 KB
- references/source-grounding.md 3.1 KB
- references/video-scene-craft.md 4.2 KB
- scripts/publish.sh 5.7 KB runs code
- scripts/video.sh 2.0 KB runs code
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.
- 1mo ago First seen · 248 lines · 107 tokens per session scan A 00a9b772dc48
html-docs is a skill published in the GitHub repository raunaqbn/html-docs-skill (5 stars, last pushed 3mo ago), licensed MIT. It adds 107 tokens to every session and 2,325 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
anything-to-course
Turn any source material — documents, notes, books, articles, transcripts, slides, codebases, or just a topic — into a complete self-study course built on evidence-based learning science (retrieval practice, spaced repetition, interleaving, faded scaffolding, confidence calibration). Use whenever the user wants to…
manim
This skill should be used when the user asks to "make a math animation", "animate an equation", "use Manim", "make a 3Blue1Brown-style video", "plot or animate a graph/function", "visualize a math/physics/CS concept", "morph one formula into another", "animate a geometric proof", or "render a math explainer". Covers…
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
exam-forecast
Analyze past exams from the same professor to surface patterns — subject weighting, recurring issue-spot traps, favored hypo types, policy-vs-doctrine mix — and forecast likely emphases for the upcoming exam. Use when the user says "what's on the exam", "analyze past exams", "predict the exam", or shares past exams.
lean-formalize
Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific…