Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By Emasoft
User's right hand - sole interlocutor with user, directs other roles. Requires AI Maestro for inter-agent messaging.
npx claudepluginhub emasoft/ai-maestro-assistant-manager-agentApprove the plan and transition from Plan Phase to Orchestration Phase
View Orchestration Phase progress - modules, agents, assignments, verification status
View Plan Phase progress - requirements completion, modules defined, exit criteria status
Respond to pending AMCOS approval requests with approve, deny, or defer decision
Assistant Manager main agent - user's right hand, sole interlocutor with user. Governance title MANAGER. Requires AI Maestro installed.
Generates status reports and project summaries. Requires AI Maestro installed.
Use when coordinating with COS for approvals and delegation. Trigger with COS coordination requests. Loaded by ai-maestro-assistant-manager-agent-main-agent
Use when handling governance approvals via GovernanceRequest API for team, agent lifecycle, and COS decisions. Trigger with approval requests.
Use when an approval request arrives from a peer agent and the user is unavailable. Trigger with inbound AMP approvals from COS, AUTONOMOUS, or MAINTAINER. Returns approve-autonomously / defer / escalate-to-user.
Use when routing GitHub operations (issues, PRs, projects, releases) to specialists via team labels. Trigger with GitHub requests. Loaded by ai-maestro-assistant-manager-agent-main-agent
Use when managing GitHub issue labels or priorities. Trigger with label or triage requests. Loaded by ai-maestro-assistant-manager-agent-main-agent.
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Task distribution, agent coordination, progress monitoring - executes plans via subagents. Requires AI Maestro for inter-agent messaging.
AI Agent Team Operating System for Claude Code — persistent team management, meetings, task wall, company loop engine, and real-time dashboard
AI team role and worker manager for multi-agent development workflows.
Markdown-only Agent Team workflow for Claude Code without requiring a Mexus server.
Graph-first governance workflow guard for Aming Claw. Bundles the core governance skill, launcher skill, Project Inbox capture skill, HN challenge/demo skills, everyday AI coding demo skills, and the project MCP server (.mcp.json) so Claude Code sessions start with backlog/MF discipline, core runtime checks, and dashboard governance context.
Multi-agent coordination with agent-swarm MCP
Task distribution, agent coordination, progress monitoring - executes plans via subagents. Requires AI Maestro for inter-agent messaging.
Portable utility tools for Claude Code plugin marketplaces. Includes release automation and markdown TOC generation.
GHE (GitHub-Elements) - Automated project management for Claude Code using GitHub Issues as persistent memory with orchestrated DEV/TEST/REVIEW workflow.
Exports current session segment (since last compaction) with system-reminder stripping -- main conversation, subagent transcripts, sidechains, and debug logs in structured markdown
Comprehensive validation, management, and standardization suite for Claude Code plugins and marketplaces. Includes 190+ validation rules, plugin lifecycle management, marketplace operations, health checks, security auditing, GitHub repo validation, plugin/marketplace repo scaffolding, and standardization tooling. Features severity hierarchy, --strict mode, language-aware token estimation, and universal plugin/marketplace templates.
Version: 2.6.7
Part of the AI Maestro ecosystem. See also: AI Maestro Plugins Marketplace.
The AI Maestro Assistant Manager Agent (AMAMA) is the user's right hand -- the sole interlocutor with the user. It receives user requests, clarifies requirements, routes work to appropriate specialist agents via the Chief-of-Staff (AMCOS), and presents results back to the user.
Requires AI Maestro >= 0.26.0 for inter-agent messaging, governance APIs, and team management.
USER <-> AMAMA (manager) <-> AMCOS (chief-of-staff) <-> Specialist Agents (member)
<-> AMAA (architect skills)
<-> AMOA (orchestrator skills)
<-> AMIA (integrator skills)
Key principle: AMAMA never communicates directly with specialist agents. All specialist routing goes through AMCOS.
AI Maestro defines exactly 3 governance titles:
| Role | Agent | Purpose |
|---|---|---|
manager | AMAMA | Team manager, sole user contact, full admin authority |
chief-of-staff | AMCOS | Agent lifecycle, permissions, failure recovery |
member | AMAA, AMOA, AMIA | All specialist agents (specialization via skills/tags, NOT the role field) |
COS Assignment Model: AMAMA does NOT spawn new AMCOS instances. Instead, AMAMA assigns the chief-of-staff governance title to an already-running registered agent via PATCH /api/teams/{id}/chief-of-staff.
| Track | Scope | Mechanism | Skill |
|---|---|---|---|
| Governance approvals | Team membership, COS assignment, agent lifecycle, transfers | GovernanceRequest API | amama-approval-workflows |
| Operational approvals | Deployments, merges, test runs, routine AMCOS operations | Message-based flow (approval_request / approval_decision) | amama-amcos-coordination |
| Agent | File | Description |
|---|---|---|
| Assistant Manager | agents/ai-maestro-assistant-manager-agent-main-agent.md | Main AMAMA agent -- user communication, routing, approvals, team management |
| Report Generator | agents/amama-report-generator.md | Generates formatted status reports for user |
| Command | File | Description |
|---|---|---|
/amama-planning-status | commands/amama-planning-status.md | Show planning phase status |
/amama-orchestration-status | commands/amama-orchestration-status.md | Show orchestration phase status |
/amama-approve-plan | commands/amama-approve-plan.md | Approve plan for orchestration |
/amama-respond-to-amcos | commands/amama-respond-to-amcos.md | Respond to AMCOS approval requests (approve/deny/defer) |
| Skill | Refs | Description |
|---|---|---|
amama-user-communication | 6 | Communicating with users: clarification, options, approval, reporting |
amama-status-reporting | 4 | Generating status reports via AI Maestro APIs (sessions, health, teams, tasks) |
amama-approval-workflows | 11 | Governance approvals via GovernanceRequest API (team, agent lifecycle, COS) |
amama-role-routing | 4 | Routing user requests to specialist agents based on intent |
amama-amcos-coordination | 16 | COS coordination: approvals, delegation, health checks, completions |
amama-github-routing | 7 | Routing GitHub operations (issues, PRs, projects, releases) via team labels |
amama-label-taxonomy | 2 | GitHub label taxonomy management and triage |
amama-session-memory | 5 | CozoDB-backed session memory, preferences, handoff tracking |
| Hook ID | Event | Script | Description |
|---|---|---|---|
amama-memory-load | SessionStart | scripts/amama_session_start.py | Load session memory at startup |
amama-memory-save | SessionEnd | scripts/amama_session_end.py | Save session memory on exit |
amama-stop-check | Stop | scripts/amama_stop_check.py | Block exit until coordination work is complete |
| File | Description |
|---|---|
shared/handoff_template.md | Standard handoff document format with YAML front-matter |
shared/message_templates.md | Generic message templates for inter-agent communication |
shared/thresholds.py | Governance thresholds, valid roles, valid specializations |