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 yogasw/wick --skill wick-html-widgetgit clone --depth 1 https://github.com/yogasw/wickWrote 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/yogasw/wick/wick-html-widget)<a href="https://agentmods.dev/skills/yogasw/wick/wick-html-widget"><img src="https://agentmods.dev/badge/skills/yogasw/wick/wick-html-widget/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/yogasw/wick/wick-html-widget"><img src="https://agentmods.dev/badge/skills/yogasw/wick/wick-html-widget.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 | $0.00179 | $0.01903 |
| Opus 5.5 | $0.00072 | $0.00761 |
| Sonnet 5.5 | $0.00036 | $0.00381 |
| Haiku 4.5 | $0.00018 | $0.00190 |
Grade A, and why
wick-html-widget 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HTML artifacts and widgets in wick
wick-rich-output covers WHICH fence to write. This file is for when the
preview is already misbehaving, or when you are about to build something that
needs more than plain inline markup.
The one-file rule
An artifact preview renders exactly one self-contained file. A page that
pulls a sibling .css, .js, or image by URL cannot work — not because it is
forbidden, but because it breaks in two independent layers, and opening the
security policy only addresses one of them.
Layer 1 — there is no base URL. The preview injects the markup as an
iframe srcdoc, and a srcdoc document has no URL of its own. A relative
href="deck.css" therefore resolves against the PARENT page's route, not
against the folder the file lives in:
Loading the stylesheet 'https://<host>/tools/agents/sessions/deck.css'
violates ... "style-src 'unsafe-inline'"
about:srcdoc:1 Loading the script '.../tools/agents/sessions/deck-stage.js' ...
/tools/agents/sessions/deck.css is nowhere near the file. Even with every
directive wide open that URL is a 404. And <base href> cannot rescue it: the
session-file endpoints are query-style (?path=…), and a relative path cannot
attach to a query string.
Layer 2 — the default policy has no host source at all (below).
So: inline everything into one file. Base64 the images and fonts. If a build
step produces both a multi-file index.html and a bundled standalone, point
the ```htmlfile fence at the standalone — they usually sit in the same
folder one name apart, which is exactly how the wrong one gets previewed.
The default CSP, directive by directive
Built by artifactCSP and injected as a <meta http-equiv> inside the
srcdoc. Under the default (secure) preset:
default-src 'none' style-src 'unsafe-inline' form-action 'none'
script-src 'unsafe-inline' img-src data: object-src 'none'
font-src data: media-src data: base-uri 'none'
connect-src (empty — no network at all)
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 · 153 lines · 179 tokens per session scan A 139460da46af
wick-html-widget is a skill published in the GitHub repository yogasw/wick (3 stars, last pushed 3d ago), licensed MIT. It adds 179 tokens to every session and 1,903 once invoked, about $0.0007 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 2026-09-10.
Other skills, from other repositories
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.
chrome-devtools
Use Chrome DevTools MCP to control and inspect a live Chrome instance for network, console, performance, rendering, and Deep debugging. Pairs with playwright-cli (deterministic interaction/E2E) — complements, not duplicates.
playwright-cli
Drive a real browser from the terminal using the Playwright CLI (snapshot, click, fill, screenshots, traces). Use when the task is CLI-first browser automation (data extraction, UI debugging, form fills, multi-tab work). For Playwright test specs, use e2e-runner instead.
browser-debugger-cli
Inspect and debug live web pages using the Chrome DevTools Protocol via the bdg CLI. Use for targeted DOM queries, computed style checks, layout debugging, and CDP method calls without loading a full page snapshot. Prefer over chrome-devtools-mcp for token efficiency. Trigger on: "inspect element", "check computed…
browser-testing-with-devtools
Verify browser behavior with runtime evidence from DOM, console, network, and performance signals.
a11y-debugging
Uses Chrome DevTools MCP for accessibility (a11y) debugging and auditing based on web.dev guidelines. Use when testing semantic HTML, ARIA labels, focus states, keyboard navigation, tap targets, and color contrast.