Stats
Actions
Available In
Tags
Help us improve
Share bugs, ideas, or general feedback.
Plugin
maos
MAOS (Multi-Agent OS) - Coordination Framework for AI Agents with Orchestration, Sentinel Protocol, Worktree Governance, Status Maps, Forge Meta-Agent, Governance Protocols
$
npx claudepluginhub ekson73/multi-agent-os --plugin multi-agent-osPopularity
Stars
Med: 0·Avg: 285
Installs
Med: 0·Avg: 1
Forks
Med: 0·Avg: 38
Health & Quality
Maintenance
Excellent10.0/10
Med: 7/10·Avg: 7.3/10
Community
Med: 42%·Avg: 41.6%
Confidence
47/100
PromisingAdoption5
Popularity0
Maintenance100
Documentation
What's Inside
Slash Commands18
Multi-Agent OS Commands
/README
Slash commands for the multi-agent-os plugin. Commands are auto-discovered by Claude Code from this directory.
agentic-status
/agentic-status
Display human-readable status of the agentic system (git + agents + sentinel + locks) using Status Map templates. Renamed from `status` (v1.5.1) to avoid collision with Claude Code built-in `/status`.
Quick Web Research
/quick-web-research
Ultra-fast parallel web research using sub-agents for 5-10x speedup
audit
/audit
On-demand audit of agent sessions, tasks, and orchestration flows
auto-pilot
/auto-pilot
Drive an operator goal end-to-end across one or more sub-agents using the existing GaaS/GaaC framework, with hard-bounded autonomy levels.
Agents37
Multi-Agent OS Agents
/README
Agent definitions for the multi-agent-os plugin. These define specialized personas that can be spawned by the orchestrator.
code-reviewer
/code-reviewer
Expert code review specialist focusing on best practices and security
consolidator
/consolidator
Agent specialized in merging and synthesizing outputs from multiple sub-agents
alexandr-wang
/alexandr-wang
Alexandr Wang thinking archetype — Scale AI founder. Use when you need data quality thinking, AI infrastructure strategy, data labeling pipeline design, or enterprise AI deployment reasoning.
amodei-siblings
/amodei-siblings
Dario & Daniela Amodei thinking archetype — Anthropic founders. Use when you need safety-first AI reasoning, responsible scaling, alignment-aware design, or balancing capability with safety in AI systems.
Skills25
agent-select
/agent-select
Analyze tasks and recommend optimal sub-agent(s) for execution
agentic-delegation
/agentic-delegation
Use when about to spawn a subagent/skill/task (Task tool, Agent tool, /command). Defines 6 decision criteria (decomposable/specialist-exists/audit-capacity/score≥MEDIUM/not-HUMAN-DOMAIN/time-budget), 10 mandatory briefing components (context/scope/motivation/purpose/objective/DoR/DoD/deliverables/feedback-loops/constraints), accountability preservation (parent NEVER delegates accountability — only execution; "delegating does not waive the responsibility received"), recursion ≤2, parallel ≤3. Harmonizes the agentic-inheritance principle (tree-returns-to-root · subordinate-is-parent's-full-responsibility · audit-output · zero-drift). Cross-vendor AAIF.
anti-conflict
/anti-conflict
Prevent file conflicts between multiple AI agents working in parallel
audit
/audit
On-demand audit and analysis of agent orchestration flows via Sentinel Protocol
auto-pilot
/auto-pilot
Autonomous unattended orchestration entry point. Delegates an entire operator goal across one or more sub-agents using the existing GaaS/GaaC delegation framework, with hard-bounded autonomy levels and depth-capped recursion. Use when the operator wants the assistant to drive a multi-step goal without per-step approval, while still respecting Sentinel anomaly thresholds, Anti-Conflict worktree discipline, and the 6-attempt escalation rule. Triggers: "auto-pilot", "unattended orchestration", "delegate the whole goal", "run autonomously", "drive this end to end", "piloto automático".
Stats
Version1.5.2
LanguagePython
Stars0
Copy clicks1
MaintenanceExcellent
LicenseMIT
Last Commit
Added
Available In
Safety Signals
Caution
Executes bash commands
Hook triggers when Bash tool is used
Uses power tools
Uses Bash, Write, or Edit tools
Runs pre-commands
Contains inline bash commands via ! syntax
Tags
Categories
Help us improve
Share bugs, ideas, or general feedback.
