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/robzilla1738/roberts-skillsWrote 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/robzilla1738/roberts-skills/macos-sandbox)<a href="https://agentmods.dev/plugins/robzilla1738/roberts-skills/macos-sandbox"><img src="https://agentmods.dev/badge/plugins/robzilla1738/roberts-skills/macos-sandbox/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/robzilla1738/roberts-skills/macos-sandbox"><img src="https://agentmods.dev/badge/plugins/robzilla1738/roberts-skills/macos-sandbox.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
macos-sandbox 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
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "macos-sandbox",
"displayName": "macOS Sandbox",
"version": "1.0.0",
"description": "Smoke-test macOS .app/.pkg in disposable Tart VMs via the macbox CLI or MCP.",
"author": {
"name": "Robert Courson",
"url": "https://robertcourson.com"
},
"homepage": "https://github.com/robzilla1738/roberts-skills/tree/main/plugins/macos-sandbox",
"repository": "https://github.com/robzilla1738/roberts-skills",
"license": "MIT",
"keywords": ["macos", "tart", "vm", "sandbox", "smoke-test", "macbox"]
}
What it installs
The manifest is a name and a version. 1 skill, 1 command travel with it, and installing the plugin installs all of them — 83 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 · 16 lines scan A 6ad4df9572df
macos-sandbox is a plugin published in the GitHub repository robzilla1738/roberts-skills (4 stars, last pushed 4mo 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
nxtg-forge
Governance-native AI development — 33 agents, 24 commands, 27 skills, 27 hooks (4 blocking security guards, an opt-in enforced-task test guard and Stop gate, a Stop check on required command output, and Semgrep scanning), drift detection (needs a configured model), an optional CRUCIBLE test-review prompt, and shared…
god-prompt-mcp
GodPrompt engineering workflows for task routing, TDD, debugging, verification, and progressive disclosure through MCP.
god-prompt-mcp
GodPrompt engineering workflows for task routing, TDD, debugging, verification, and progressive disclosure.
devops-skills
CI/CD pipelines, GitOps workflows, testing strategies, platform engineering, and containerization.
figma-design-skills
Two composable skills for design-to-code fidelity: figma-design-extract pulls exact specs from Figma into a build-ready spec table; design-fidelity-verify proves the running web or mobile app matches them by measuring rendered values.
llm-testing-expert
Evaluation strategies, prompt engineering, red teaming, and regression testing for LLMs.