CMUX
CMUX is an Agent runtime & coordination infrastructure skill for AI agents, published by danielmiessler in the LifeOS repository on GitHub. Skillspace rates CMUX B (81/100) and it passed the safety scan; a judge model has also reviewed it.
Drives cmux as an agent cockpit to boot, race, and monitor visible agent teams. Mac-only. USE WHEN cmux, agent cockpit, boot an agent team, orchestrate agents, three-tier orchestration, agent race, needle-in-haystack hotfix, agent fleet, 2x2 fleet, watch/monitor my agents, scale compute to scale impact, send a prompt to a running agent, multiplexer, terminal cockpit, orchestrator lead worker. NOT FOR one-shot in-harness subagents with no terminal to watch (use Delegation/Agent/Workflow), the Pulse dashboard itself (cmux feeds it, use Pulse), browser deploy-verification (use Interceptor), or Linux/Windows (cmux is Mac-only — use tmux).
- Grade
- B
- Quality
- 81 / 100
- Safety
- Passed
- GitHub stars
- 16,717
Placed #2 of 6 in the judged category final for Agent runtime & coordination infrastructure.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 97 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- Low-risk patterns
- License
- MIT
- Adoption
- Adopted by 0 other repositories, in 0 collections
- Scope
- Vendor-specific: built around one product. Drives cmux, a specific external agent-orchestration tool.
Judge review
Placed #2 of 6 in the judged category final for Agent runtime & coordination infrastructure.
- Trigger
90 90 - Instructions
90 90 - Specificity
92 92 - Safety
75 75 - Disclosure
88 88 - Maintenance
90 90
Unusually honest about its own unproven live-driving path and states its socket-password risk outright, though the capability itself is broad fleet-wide control gated by a shared secret.
What the scanner flagged
- mentions secrets in text
Not checked yet
- No blind task eval yet
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.