
hermes-agent-mission-control
Mission control Kanban interface for managing autonomous Hermes Agent tasks, routines, and workflows
- Installs
- 201
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/reason-machines/hermes-skills --skill hermes-agent-mission-control- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads hermes-agent-mission-control automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Hermes Agent Mission Control
Skill by ara.so — Hermes Skills collection
Minions is a mission control interface for Hermes Agent that provides a Kanban board to create, supervise, and review autonomous work. It solves the problem of juggling multiple terminal sessions and losing track of long-running tasks by providing a visual board with task status (in progress, in review, done), live streaming of agent work, and human-in-the-loop verification.
Installation
Prerequisites: Node.js 18+ and Hermes Agent
Quick start with npx (no installation required):
npx minionsai
Or install globally:
npm install -g minionsai
Then run:
minions
The server starts on http://localhost:6969 by default.
Data Storage
Minions creates a local SQLite database on first run:
- Database and state stored in
~/.minions/ - Chat transcripts live in Hermes's session database
- Task metadata, status, and settings stored in Minions SQLite DB
- Completely local-first by default (no cloud dependency)
CLI Commands
# Start the server
minions
# Check version
minions --version
# Compare with latest NPM version
npm view minionsai version
Key Features & Usage
Task Management
Each task in Minions is a persistent Hermes root session:
- Create tasks: Describe what you want in chat
- Autonomous execution: Agent decides how to get it done
- Live streaming: Watch tool calls, reasoning, and responses in real-time
- Completion judge: Lightweight LLM evaluates whether task is done after each turn
- Human verification: Review agent's proposed completion before moving to "Done"
Kanban Board States
- In Progress: Tasks actively being worked on
- In Review: Tasks completed by agent, awaiting human verification
- Done: Verified and closed tasks
Per-Task Configuration
Override model and reasoning settings on individual tasks:
// Task metadata structure
interface Task {
id: string;
title: string;
description: string;
status: 'in_progress' | 'in_review' | 'done';
sessionId: string; // Hermes session ID
model?: string; // Override default model
reasoningEffort?: number; // Override reasoning effort
createdAt: string;
updatedAt: string;
}
Routines
Create and manage recurring Hermes jobs:
- Schedule regular agent tasks
- Track execution history
- Review output from each run
- Useful for monitoring, data collection, reporting
File Browser
View files created by agents in the workspace directory without leaving the interface.
Configuration
Check settings in the web UI Settings page:
- View running Minions server version
- Configure Hermes Agent connection
- Set default model and reasoning effort
- Manage workspace directory path
Architecture
Minions is built with TypeScript and uses:
- SQLite for local task metadata storage
- Hermes Agent sessions for chat transcripts
- Real-time WebSocket connections for live streaming
- Kanban board UI for task visualization
// Example: Task state transitions
// 1. User creates task → status: 'in_progress'
// 2. Agent completes work → status: 'in_review'
// 3. Human verifies → status: 'done'
// The completion judge runs after each agent turn
interface CompletionCheck {
isComplete: boolean;
reasoning: string;
confidence: number;
}
Common Patterns
Delegating Long-Running Work
# Start Minions
npx minionsai
# In the web UI:
# 1. Create new task: "Research top 10 AI tools launched this month"
# 2. Walk away - agent executes autonomously
# 3. Return later to review in "In Review" column
# 4. Verify and move to "Done"
Managing Multiple Projects
// Each task is independent:
// - Separate Hermes session
// - Independent model/effort settings
// - Parallel execution supported
// Example workflow:
// Task 1: "Write blog post about TypeScript 5.4 features"
// Task 2: "Analyze competitor pricing pages"
// Task 3: "Generate test data for user onboarding flow"
// All run concurrently, visible on one board
Routine Monitoring
# Set up daily routine:
# "Check GitHub stars and create summary report"
# Minions will:
# 1. Execute on schedule
# 2. Store execution history
# 3. Make output reviewable
# 4. Alert if intervention needed (roadmap feature)
Integration with Hermes Agent
Minions acts as a control layer over Hermes:
// Minions doesn't replace Hermes CLI usage
// It complements it by providing:
// - Visual task organization
// - Persistent session management
// - Completion detection
// - Human review workflow
// You can still use Hermes directly:
hermes chat "quick question"
// Or use Minions for longer work:
// Create task in UI → Minions manages Hermes session
Troubleshooting
Port Already in Use
# Default port is 6969
# If occupied, check for existing Minions process:
lsof -i :6969
kill -9 <PID>
# Then restart
npx minionsai
Database Issues
# Database location
ls -la ~/.minions/
# Reset database (WARNING: deletes all tasks)
rm -rf ~/.minions/
npx minionsai # Creates fresh database
Connection to Hermes Agent
Ensure Hermes Agent is properly installed and accessible:
# Verify Hermes installation
which hermes
hermes --version
# Check Hermes can start sessions
hermes chat "test"
Task Stuck in "In Progress"
- Check Hermes session logs for errors
- Review agent's last output in live stream
- Manually intervene in chat
- Adjust model/reasoning effort settings
- Close and recreate task if necessary
Hosted Option
Self-hosting is recommended for privacy, but a hosted option is available at Agent37.
Limitations
- Currently Hermes-only (OpenClaw adapter planned)
- Notifications not yet implemented (roadmap)
- Skills library not yet available (roadmap)
FAQ
What does the hermes-agent-mission-control skill do?
Mission control Kanban interface for managing autonomous Hermes Agent tasks, routines, and workflows
How do I install hermes-agent-mission-control?
Run npx skills add https://github.com/reason-machines/hermes-skills --skill hermes-agent-mission-control in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/hermes-agent-mission-control/ (personal) or .claude/skills/hermes-agent-mission-control/ (project).
Which AI agents can use hermes-agent-mission-control?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is hermes-agent-mission-control safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains hermes-agent-mission-control?
It is published by reason-machines in reason-machines/hermes-skills. It has 201 recorded installs.
More from reason-machines/hermes-skills
hermes-agent-self-evolution
reason-machines/hermes-skills
Evolutionary self-improvement for Hermes Agent using DSPy + GEPA to optimize skills, prompts, and code
hermes-webui-agent
reason-machines/hermes-skills
Expert in deploying, configuring, and using Hermes WebUI—a web interface for Hermes Agent with persistent memory, scheduled jobs, and multi-platform messaging.
awesome-hermes-agent-ecosystem
reason-machines/hermes-skills
Expert knowledge of the Hermes Agent ecosystem, skills, plugins, tools, integrations, and deployment patterns for building and extending AI agents
hermes-agent-framework
reason-machines/hermes-skills
Hermes Agent framework by Nous Research - self-improving AI agent with built-in learning loop, three-layer memory, and automatic skill evolution
hermes-workspace-ai-agent-ui
reason-machines/hermes-skills
Native web workspace for Hermes Agent with chat, terminal, memory, skills, inspector, and multi-agent orchestration
hermes-web-ui-dashboard
reason-machines/hermes-skills
Web dashboard for managing Hermes Agent multi-platform AI chat sessions, analytics, scheduled jobs, and platform channels
Popular other skills
hyperframes-cli
heygen-com/hyperframes
The HyperFrames CLI by job - scaffold, check, look at frames, edit the timeline, preview, render locally or in the cloud, publish, project history - plus reading its JSON and recovering from build or render failures.
triage
mattpocock/skills
Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.
ask-matt
mattpocock/skills
Ask which skill or flow fits your situation. A router over the skills in this repo.
to-questionnaire
mattpocock/skills
Turn a decision you can't fully answer into a questionnaire for someone else to fill in.
loop-me
mattpocock/skills
Grill me about specs for the workflows I want to build, within this workspace.