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/elumenotion/guideants/html-craftnpx 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.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 | $0.00084 | $0.02464 |
| Opus 5 | $0.00042 | $0.01232 |
| Sonnet 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 yesterday.
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.
- yesterday First seen · 175 lines · 84 tokens per session scan A 5640e13295a9
html-craft is a skill published in the GitHub repository Elumenotion/GuideAnts (56 stars, last pushed yesterday), licensed Apache-2.0. It adds 84 tokens to every session and 2,464 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 2026-09-03.
Other skills, from other repositories
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
opencli-autofix
Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.
generate-token-map
Maps all Figma design tokens from figma-variables.md to their equivalent C++ (Views) identifiers, CSS (WebUI) variables, and Clank (Android) resource attributes/macros/methods in Chromium, and saves the formatted mapping table to the assets directory of the Chrome Design System project. Use this skill when asked to…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
opencli-browser-sitemap
Use when driving a website with opencli browser and sitemap context is available, requested, or needed to avoid blind navigation. Guides agents to consume site sitemap files lazily, choose adapter/browser fallback paths, resume from state signatures, and mark stale sitemap entries without trusting them over live…
playwright-screen-recording
Record browser test videos with Playwright for PR review and bug fix verification.