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.
/plugin marketplace add AmrDab/clawdcursornpx agentmods add plugins/amrdab/clawdcursor/marketplacegit clone --depth 1 https://github.com/AmrDab/clawdcursorGrade A, and why
clawdcursor 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 2d 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": "clawdcursor",
"owner": {
"name": "Amr Dabbas",
"url": "https://github.com/AmrDab"
},
"metadata": {
"description": "Safe cross-OS desktop & browser control for AI agents — the fallback execution layer for when APIs, CLIs, and direct integrations aren't available.",
"version": "1.0.0"
},
"plugins": [
{
"name": "clawdcursor",
"source": "./",
"description": "Safe cross-OS desktop & browser control — the fallback execution layer for when APIs, CLIs, and direct integrations aren't available. Registers the clawdcursor MCP server (compact tool surface) and bundles its usage skill. Launches via npx, so no separate install step is required.",
"version": "1.5.9",
"homepage": "https://clawdcursor.com",
"license": "MIT",
"keywords": [
"mcp",
"desktop-automation",
"computer-use",
"gui-automation",
"accessibility",
"fallback"
]
}
]
}
What ships with it
1 file beside marketplace.json 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.
- 2d ago First seen · 30 lines scan A 77d5ce6ce318
clawdcursor is a plugin published in the GitHub repository AmrDab/clawdcursor (399 stars, last pushed 2d 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 2026-08-30.
Other plugins, from other repositories
screenhand
Desktop and browser automation for Claude Code. Control any macOS/Windows app, automate social media, run QA tests, edit video, design in Figma/Canva, scrape the web, and orchestrate multi-agent workflows — 111 MCP tools.
humanizer
Remove signs of AI-generated writing from text, making it sound more natural and human. Based on Wikipedia's "Signs of AI writing" guide.
browserjack
Use OpenAI's locally installed Codex browser runtime from Claude Code (macOS).
clipboard-mcp-server
Read, write, and inspect the system clipboard across macOS, Linux (X11/Wayland), and Windows via MCP. STDIO or Streamable HTTP.
draft-strategy
Fantasy football draft decision support: tiered draft boards built from your rankings, value-based drafting adjusted for your league's roster settings, live best-available guidance, and keeper cost math.
fantasy-league-setup
League configuration via settings-page read or interview. Writes a leagues.md file to your project that every other fantasy-football-skills skill reads for scoring, roster, waiver, playoff context, and Preferred browser.