cmux-hibernate

cmux-hibernate is a skill for Claude Code from fernando-bertholdo/4-successful-AI-life. It costs 75 tokens per session (560 once invoked), scanned A, original, MIT.

A tool for saving and restoring open Claude Code sessions when closing cmux, a terminal workspace manager, or restarting a computer.

In plain words
What is it for?
Use it before closing cmux and afterward to check, wake, or rebuild sessions.
Why use it?
It helps preserve session bindings and prevents open work from being lost while freeing memory.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the cmux-hibernate plugin — 1 skill shipped together

Good fit Use it before closing cmux and afterward to check, wake, or rebuild sessions.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add fernando-bertholdo/4-successful-AI-life
Claude Code
/plugin install cmux-hibernate

Made for: Claude Code.

Or install cmux-hibernate, the plugin that ships this one along with the rest of its 1 skill.

Wrote 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.

agentmods badge for cmux-hibernate

README.md
[![agentmods](https://agentmods.dev/badge/skills/fernando-bertholdo/4-successful-ai-life/cmux-hibernate/github.svg)](https://agentmods.dev/skills/fernando-bertholdo/4-successful-ai-life/cmux-hibernate)
Your own site
<a href="https://agentmods.dev/skills/fernando-bertholdo/4-successful-ai-life/cmux-hibernate"><img src="https://agentmods.dev/badge/skills/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.

agentmods 80×15 button for cmux-hibernate

Your own site · 80×15
<a href="https://agentmods.dev/skills/fernando-bertholdo/4-successful-ai-life/cmux-hibernate"><img src="https://agentmods.dev/badge/skills/fernando-bertholdo/4-successful-ai-life/cmux-hibernate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 560 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00075 $0.00560
Opus 5 $0.00037 $0.00280
Sonnet 5 $0.00015 $0.00112
Haiku 4.5 $0.00007 $0.00056

Measured 12d ago against content hash c162262f2dfb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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 12d 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.

plugins/cmux-hibernate/skills/cmux-hibernate/SKILL.md · 49 lines

What it actually says

cmux-hibernate

Hiberna as sessões Claude Code espalhadas pelos workspaces do cmux e as traz de volta, sem recriar o consumo de memória que motivou o fechamento.

Antes de fechar o cmux

python3 "${CLAUDE_PLUGIN_ROOT}/scripts/hibernate.py"          # dry-run
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/hibernate.py" --apply  # desarma e grava

Rode o dry-run primeiro e mostre o resultado ao usuário. O --apply muta os bindings do cmux — só use depois que ele confirmar.

A aba de onde o comando roda é preservada: é a única sessão que sobe quando o cmux reabre, e de onde a conferência pode ser pedida. Use --all apenas se o usuário quiser zero sessões vivas.

Depois de reabrir

python3 "${CLAUDE_PLUGIN_ROOT}/scripts/wake.py"              # confere
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/wake.py" --up all     # sobe tudo
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/wake.py" --rebuild    # recria o que sumiu

No caminho normal nada é necessário: cada aba acorda quando o usuário a abre.

Ao interpretar a saída

  • dormindo é o estado saudável depois de hibernar, não um problema. Não sugira --up por reflexo — só se o usuário pedir tudo de volta.
  • ausentes significa que a aba não existe mais na estrutura. É o caso de --rebuild.
  • sem transcript não é recuperável: o histórico não existe mais em disco. Diga isso com todas as letras em vez de sugerir tentativas.
  • anomalia: sessão em mais de uma aba é pulada de propósito. Reporte, não contorne.

O que não fazer

Não invente um "registro de sessões" paralelo nem tente conciliar snapshots antigos: o snapshot é um retrato datado de uso único e os 5 últimos bastam. Se o usuário pedir histórico, o que existe são os transcripts em ~/.claude/projects/.

Changes

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.

  1. 12d ago First seen · 49 lines · 75 tokens per session scan A c162262f2dfb

Subscribe to this mod's changes

cmux-hibernate is a skill published in the GitHub repository fernando-bertholdo/4-successful-AI-life (2 stars, last pushed yesterday), licensed MIT. It adds 75 tokens to every session and 560 once invoked, about $0.0004 per session on Opus 5. 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.