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/fernando-bertholdo/4-successful-AI-lifeWrote 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/fernando-bertholdo/4-successful-ai-life/cmux-hibernate)<a href="https://agentmods.dev/plugins/fernando-bertholdo/4-successful-ai-life/cmux-hibernate"><img src="https://agentmods.dev/badge/plugins/fernando-bertholdo/4-successful-ai-life/cmux-hibernate/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/fernando-bertholdo/4-successful-ai-life/cmux-hibernate"><img src="https://agentmods.dev/badge/plugins/fernando-bertholdo/4-successful-ai-life/cmux-hibernate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
cmux-hibernate 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 11d 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": "cmux-hibernate",
"version": "0.1.0",
"description": "Hibernate and restore Claude Code sessions across cmux workspaces, freeing memory without losing your environment",
"author": {
"name": "Fernando Bertholdo",
"url": "https://github.com/fernando-bertholdo"
},
"repository": "https://github.com/fernando-bertholdo/4-successful-AI-life",
"license": "MIT",
"keywords": ["cmux", "session", "restore", "hibernate", "memory", "workspace"],
"skills": "./skills/"
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 75 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.
- 11d ago First seen · 14 lines scan A 25648aa512f6
cmux-hibernate is a plugin published in the GitHub repository fernando-bertholdo/4-successful-AI-life (2 stars, last pushed today), 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
macro-keyboard
Configure cheap 3-key USB-C/Bluetooth macro pads on macOS with Karabiner-Elements: emit real Fn, remap per-device, diagnose mystery keycodes. Includes worked example: Jieli/Free3-P (VID 0x4c4a USB / 0x04E8 BT).
notes-commander
macOS Notes organizer + human-in-the-loop drafts. Inventory every account/folder, export all notes to local markdown+manifest snapshots, reorganize safely (folderize/move/merge, dry-run first, no delete verb), audit-and-propose taxonomy, and the draft-park human-in-the-loop draft skill - all on one hardened…
ralph-wiggum
Implementation of the Ralph Wiggum technique - continuous self-referential AI loops for interactive iterative development. Run Claude in a while-true loop with the same prompt until task completion.
asciinema-tools
Terminal recording automation: asciinema capture, launchd daemon for background chunking, Keychain PAT storage, Pushover notifications, cast conversion, and semantic analysis.
calcom-commander
Cal.com + Telegram bot lifecycle - booking management, interactive commands, scheduled sync, Agent SDK routing, 1Password API key.
floating-clock
Always-on-top floating desktop clock for macOS — borderless NSPanel with persistent positioning, timer-driven updates, persistent position via NSUserDefaults.