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 cogni-work/insight-wave --skill website-previewgit clone --depth 1 https://github.com/cogni-work/insight-waveWrote 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/cogni-work/insight-wave/website-preview)<a href="https://agentmods.dev/skills/cogni-work/insight-wave/website-preview"><img src="https://agentmods.dev/badge/skills/cogni-work/insight-wave/website-preview/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/cogni-work/insight-wave/website-preview"><img src="https://agentmods.dev/badge/skills/cogni-work/insight-wave/website-preview.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 | $0.00116 | $0.00643 |
| Opus 5.5 | $0.00046 | $0.00257 |
| Sonnet 5.5 | $0.00023 | $0.00129 |
| Haiku 4.5 | $0.00012 | $0.00064 |
Grade A, and why
website-preview 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.
What it actually says
Website Preview
Open the generated static website in a browser and validate its structure.
Prerequisites
The output/website/index.html must exist (from website-build). If not found, redirect to the build skill.
Workflow
1. Validate Site Structure
Check that the expected files exist:
output/website/index.htmloutput/website/css/style.cssoutput/website/sitemap.xml- All pages referenced in
website-plan.json
Report missing files.
2. Validate Internal Links
Scan all .html files in output/website/ for local links (href not starting with http). Check each resolves to an existing file. Report broken links with the page and target.
3. Open in Browser
Open the homepage in the default browser:
# macOS
open output/website/index.html
# Linux
xdg-open output/website/index.html
4. Suggest Local Server
For full navigation testing (relative paths work best with a server):
Für vollständige Navigation empfehle ich einen lokalen Testserver:
python3 -m http.server -d output/website 8080
Dann öffnen Sie http://localhost:8080 im Browser.
5. Present Validation Report
Website-Vorschau:
Dateien: {N} HTML-Seiten, 1 CSS, {M} Bilder
Gesamtgröße: {size} KB
Defekte Links: {count} ({details if any})
Fehlende Seiten: {count} ({details if any})
✓ Website im Browser geöffnet
Optional: Browser Review
If claude-in-chrome is available, offer to open each page in the user's browser for live review. Use mcp__claude-in-chrome__tabs_create_mcp to open a new tab, mcp__claude-in-chrome__navigate to visit each page, and mcp__claude-in-chrome__read_page to validate rendered content. The user can see the pages directly in their Chrome browser.
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 · 78 lines · 116 tokens per session scan A def712e795d5
website-preview is a skill published in the GitHub repository cogni-work/insight-wave (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 116 tokens to every session and 643 once invoked, about $0.0005 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 2026-09-04.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
interactive-login
Log a CLI in with a browser/device-code flow (aws sso, gh, glab, gcloud, …) and save the result to the keychain so later commands can request it through execute.credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
open-design-browser
Inspect and exercise local HTML design artifacts and library prototype previews with the existing agent-browser CLI, including screenshots, interaction checks, and rendered DOM snapshots. Use when rendered evidence helps author or review a design; excludes browser installation, remote services, and unrelated browser…