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 agentmods add settings/omarshahine/homeclaw/settingsgit clone --depth 1 https://github.com/omarshahine/HomeClawGrade A, and why
HomeClaw 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
{
"enabledPlugins": {
"code-review@claude-plugins-official": true,
"code-simplifier@claude-plugins-official": true,
"context7@claude-plugins-official": true,
"feature-dev@claude-plugins-official": true,
"frontend-design@claude-plugins-official": true,
"greptile@claude-plugins-official": true,
"plugin-dev@claude-plugins-official": true,
"pr-review-toolkit@claude-plugins-official": true,
"security-guidance@claude-plugins-official": true,
"swift-lsp@claude-plugins-official": true,
"typescript-lsp@claude-plugins-official": true,
"swiftui-skills@dpearson2699/swift-ios-skills": true,
"swift-core-skills@dpearson2699/swift-ios-skills": true,
"ios-app-framework-skills@dpearson2699/swift-ios-skills": true,
"ios-data-framework-skills@dpearson2699/swift-ios-skills": true,
"ios-ai-ml-skills@dpearson2699/swift-ios-skills": true,
"ios-engineering-skills@dpearson2699/swift-ios-skills": true,
"ios-hardware-skills@dpearson2699/swift-ios-skills": true,
"ios-platform-skills@dpearson2699/swift-ios-skills": true,
"all-ios-skills@dpearson2699/swift-ios-skills": true
}
}
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 · 25 lines scan A 2263f320875a
HomeClaw is a settings file published in the GitHub repository omarshahine/HomeClaw (164 stars, last pushed 9d 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 settings, from other repositories
SwiftAutoGUI
Agent settings configuring enabledPlugins, extraKnownMarketplaces.
Remarc
An empty agent settings file, from a project described as: Your feedback layer for AI collaboration. Point at anything on your Mac - text, screenshots, web elements, or voice - and your agent reads and resolves your comments over MCP.
settings
Agent settings declaring 3 hook events (PreToolUse, SessionStart, Stop).
apple-mail-fast-mcp
Agent settings declaring 3 hook events (PreToolUse, PostToolUse, SessionStart).
cctop
Agent settings declaring 1 hook event (PostToolUse).
mcp-fantastical
Agent settings declaring 7 allowed tools.