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/MSApps-Mobile/claude-pluginsWrote 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/msapps-mobile/claude-plugins/mac-agent-hygiene)<a href="https://agentmods.dev/plugins/msapps-mobile/claude-plugins/mac-agent-hygiene"><img src="https://agentmods.dev/badge/plugins/msapps-mobile/claude-plugins/mac-agent-hygiene/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/msapps-mobile/claude-plugins/mac-agent-hygiene"><img src="https://agentmods.dev/badge/plugins/msapps-mobile/claude-plugins/mac-agent-hygiene.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
mac-agent-hygiene 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "mac-agent-hygiene",
"description": "Keeps a Mac that runs Claude Code agents from filling its disk: a daily LaunchAgent plus an MCP server that clears regenerable caches (Xcode DerivedData, leftover plugin clones, browser-profile caches) and reaps stale git worktrees that are clean and already pushed. Plan first, apply on confirm.",
"version": "0.1.2",
"author": {
"name": "MSApps",
"url": "https://claudeservices.ai"
},
"license": "MIT",
"homepage": "https://claudeservices.ai/plugins#mac-agent-hygiene",
"repository": "https://github.com/MSApps-Mobile/claude-plugins",
"privacy_policy": "https://opsagents.agency/privacy",
"terms_of_service": "https://opsagents.agency/terms",
"keywords": [
"mac",
"macos",
"disk",
"cleanup",
"worktree",
"launchd",
"mcp",
"claude-code",
"agents",
"sosa-agents"
],
"platforms": [
"claude-code",
"cowork"
],
"sosa": {
"compliant": true,
"level": 2,
"impact": "medium",
"methodology": "https://github.com/MSApps-Mobile/claude-plugins/blob/main/docs/SOSA.md",
"whitepaper": "https://github.com/MSApps-Mobile/claude-plugins/blob/main/docs/sosa-whitepaper.pdf",
"pillars": {
"supervised": "Every removal is planned first (dry run with per-item reasons) and applied only with an explicit plan_id + confirm; the scheduled run deletes only regenerable caches and worktrees that are clean, pushed and untouched for a week",
"orchestrated": "status → plan → re-check → apply → log; one shell script decides eligibility in both plan and apply so nothing slips between them",
"secured": "Local filesystem only, no network except an optional read-only gh query for merged PRs; never sudo; never login state inside browser profiles; never dirty or unpushed worktrees; paths outside $HOME refused",
"agents": "R=mac-hygiene, T=bash+launchd+git+gh(read), M=30-min plan cache + append-only log, P=status-plan-confirm-apply"
}
},
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 — 139 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.
- today Changed 5b9b79212de3
- 4d ago First seen · 47 lines scan A e5186597b9ee
mac-agent-hygiene is a plugin published in the GitHub repository MSApps-Mobile/claude-plugins (9 stars, last pushed yesterday), 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 2026-10-08.
Other plugins, from other repositories
pwdev-statusline
Configure and manage Claude Code status line — installs a rich, configurable bash status bar (single-jq-pass, dynamic colors, formatted tokens, truncated paths) showing model, git branch, context usage, rate limits, and token counts.
merge-pr
Merge PRs matching repo history conventions. Includes readiness checks, CI watching, stack detection, and automated rebasing.
research
Research topics and assess decisions with pinned, captured sources in dated folders. Resume, re-verify, report. Clones dependencies at pinned versions.
disk
Safely reclaim disk space. Classifies consumers as cache, redundant copy, or history, deleting only what is proven safe.
vibe-extras
Standalone utilities for codebase exploration, web research, git operations, and code maintenance.
commit-commands
A plugin providing simple commands for common Git tasks. Git is a tool for tracking code changes, and the listed tasks include committing, pushing, and creating pull requests.