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.
git clone --depth 1 https://github.com/ruchit-p/macwrightWrote 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/plugins/ruchit-p/macwright/macwright-skills)<a href="https://agentmods.dev/plugins/ruchit-p/macwright/macwright-skills"><img src="https://agentmods.dev/badge/plugins/ruchit-p/macwright/macwright-skills/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/plugins/ruchit-p/macwright/macwright-skills"><img src="https://agentmods.dev/badge/plugins/ruchit-p/macwright/macwright-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
macwright-skills 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
{
"name": "macwright-skills",
"description": "Project-specific skills for the MacWright MCP server — Safari automation, screen coordinate system, tool development patterns, and workflows discovered during iterative testing.",
"author": {
"name": "MacWright"
}
}
What it installs
The manifest is a name and a version. 3 skills travel with it, and installing the plugin installs all of them — 276 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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 · 8 lines scan A ec3dc745dc22
macwright-skills is a plugin published in the GitHub repository ruchit-p/macwright (0 stars, last pushed 2mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-31.
Other plugins, from other repositories
web-quality-skills
Measurement-first Agent Skills for Lighthouse, Chrome DevTools, Core Web Vitals, WCAG 2.2, SEO, and agentic browsing.
swift-auto-gui
Control macOS GUI applications and Chromium pages using the sagui CLI.
audio-recap
Hear what Claude Code did without watching the screen. After each turn, your Mac's voice speaks a one-sentence recap of what Claude did, then its reply (long replies summarized). Claude Haiku writes the recaps and summaries through your own Claude Code (claude -p), which adds a little model usage. macOS only. Off by…
toolpiper
Connects Claude Code to ToolPiper, the on-device AI platform for macOS: local LLM inference, speech to text, vision and OCR, browser automation, video editing, and system control through one loopback MCP server.
browserjack
Use OpenAI's locally installed Codex browser runtime from Claude Code (macOS).
axstream
Fast, verified computer use for coding agents: read the screen as text (200ms), execute batched verified actions, and compile any task done once into a macro that replays in seconds with zero model calls.