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 Elumenotion/GuideAnts --skill html-craftgit clone --depth 1 https://github.com/Elumenotion/GuideAntsWrote 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/elumenotion/guideants/html-craft)<a href="https://agentmods.dev/skills/elumenotion/guideants/html-craft"><img src="https://agentmods.dev/badge/skills/elumenotion/guideants/html-craft/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/elumenotion/guideants/html-craft"><img src="https://agentmods.dev/badge/skills/elumenotion/guideants/html-craft.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 | $0.00084 | $0.02464 |
| Opus 5.5 | $0.00034 | $0.00986 |
| Sonnet 5.5 | $0.00017 | $0.00493 |
| Haiku 4.5 | $0.00008 | $0.00246 |
Grade A, and why
html-craft 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 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.
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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
html-craft
Paths - fixed layout, do not probe or re-derive. The sandbox CWD is the
notebook's output directory. This skill's scripts live under
Skills/html-craft/scripts/ relative to it, so run the commands in this file
exactly as written. Write every deliverable to the CWD with a bare filename
(e.g. -o page.png): never prefix an output path with Output/ - the CWD is
the output directory, so Output/... would create a nested Output/ folder.
Builds single-file HTML artifacts (inline CSS + JS, no build step, no
network) and verifies them the way a user would see them: a real headless
Chromium loads the file, drives it (key presses, clicks, waits), screenshots
the moments that matter, and asserts on the DOM. Everything runs inside the
sandbox: sandbox-venv Python + playwright + openai SDK + the Chromium binary already in
the image.
Preflight (cheap; once per session)
python3 Skills/html-craft/scripts/preflight.py
Prints one JSON verdict: {"scenario", "open": bool, "blockers": [...], "warnings": [...], "evidence": {...}} after a live 320x200 render.
open: false - stop and report the blockers; do not guess browser paths.
Commands
python3 Skills/html-craft/scripts/html_craft.py probe PAGE
python3 Skills/html-craft/scripts/html_craft.py shot PAGE -o name.png
python3 Skills/html-craft/scripts/html_craft.py text PAGE --sel "#el" [--sel "#el2"]
python3 Skills/html-craft/scripts/html_craft.py eval PAGE "document.title"
python3 Skills/html-craft/scripts/html_craft.py compare A.png B.png -o cmp.png
python3 Skills/html-craft/scripts/vision_qa.py NAME.png --ask "1) ... 2) ..." --label "..."
Drive flags shared by probe / shot / text / eval:
| Flag | Meaning |
|---|---|
--action "press:Space" |
repeatable, applied in order: press:KEY, click:SELECTOR, wait:MS |
--wait MS |
settle after page load (default 700) |
--settle MS |
wait after each action (default 1200) |
--viewport WxH |
default 1280x800 |
--full-page |
shot: capture the full scrollable page |
--timeout MS |
navigation timeout (default 60000) |
--browser PATH |
chromium binary; else $HTML_CRAFT_BROWSER; else auto-find |
What ships with it
7 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.
- 1mo ago First seen · 175 lines · 84 tokens per session scan A 5640e13295a9
html-craft is a skill published in the GitHub repository Elumenotion/GuideAnts (64 stars, last pushed 2d ago), licensed Apache-2.0. It adds 84 tokens to every session and 2,464 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 2026-09-03.
Other skills, from other repositories
stealth-browser-mcp
Use this skill when operating stealth-browser-mcp from an AI agent or MCP client for browser automation, page inspection, element interaction, screenshots, file uploads, CDP commands, network debugging, cookies/storage, stealth setup, or reliable multi-step browser workflows. It provides the correct tool order, state…
accessibility-a11y
WCAG 2.2 compliance, ARIA patterns, keyboard navigation, screen readers, automated testing.
flutter-development
Cross-platform development with Flutter and Dart for iOS, Android, Web, Desktop, and embedded. Use when building Flutter apps, implementing Material/Cupertino design, or optimizing Dart code.
agent-e2e-test-specialist
Specialist subagent: Playwright, Cypress, and visual regression testing specialist. Use only when the user explicitly asks for E2E tests, browser test automation, or visual regression testing. Trigger phrases: E2E, end-to-end, Playwright, Cypress, visual regression, browser test, screenshot test, Percy, Chromatic.
frontend-enhancer
Enhance the visual design of web apps: modern UI components, layout, responsive design, color palettes, animations. Use for styling and UI polish; pair with ui-research first for new design directions.
generic-design-system
Complete design system reference for any project - colors, typography, spacing, components, animations. Adapts to project theme and tech stack. Use when implementing UI, choosing colors, creating animations, or ensuring brand consistency. For new design systems, use ui-research skill first.