Nomadterm agent messaging
Skill OpenTech-Lab/NomadTerm-server/skills/nomadterm-agent-messaging
Let AI agents message, watch, and spawn each other across terminals. Claude Code, Gemini CLI, Codex, OpenCode. Use this skill when the human user needs help, status, or reference about nomadterm - when user asks questions like "how to setup nomadterm", "nomadterm not working", "explain nomadterm", or any nomadterm troubleshooting.From its SKILL.md
npx -y skills add OpenTech-Lab/NomadTerm-server --skill nomadterm-agent-messagingAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
4.1 KB, as published. Nobody here has run it
nomadterm — Let AI agents message, watch, and spawn each other across terminals. Claude Code, Gemini CLI, Codex, OpenCode.
AI agents running in separate terminals are isolated from each other. Context doesn't transfer, decisions get repeated, file edits collide. nomadterm connects them.
pip install nomadterm
nomadterm claude
nomadterm gemini
nomadterm codex
nomadterm opencode
nomadterm # TUI dashboard
What humans can do
Tell any agent:
send a message to claude
when codex goes idle send it the next task
watch gemini's file edits, review each and send feedback if any bugs
fork yourself to investigate the bug and report back
find which agent worked on terminal_id code, resume them and ask why it sucks
What agents can do
- Message each other (@mentions, intents, threads, broadcast)
- Read each other's transcripts (ranges, detail levels)
- View agent terminal screens, inject text/enter for approvals
- Query event history (file edits, commands, status, lifecycle)
- Subscribe and react to each other's activity in real-time
- Spawn, fork, resume, kill agents in new terminal panes
- Build context bundles (files, transcript, events) for handoffs
- Collision detection — 2 agents edit same file within 20s, both notified
- Cross-device — connect agents across machines via MQTT relay
Setup
If the user invokes this skill without arguments:
- Run
nomadterm status— if "command not found", runpip install nomadtermfirst - Tell user to run
nomadterm claudeornomadterm geminiornomadterm codexornomadterm opencodein a new terminal (auto installs hooks on first run)
| Status Output | Meaning | Action |
|---|---|---|
| command not found | nomadterm not installed | pip install nomadterm |
[~] claude | Tool exists, hooks not installed | nomadterm hooks add then restart tool (or just nomadterm claude) |
[✓] claude | Hooks installed | Ready — use nomadterm claude or nomadterm start |
[✗] claude | Tool not found | Install the AI tool first |
After adding hooks or installing nomadterm you must restart the current AI tool for nomadterm to activate.
Tool Support
| Tool | Message Delivery |
|---|---|
| Claude Code (incl. subagents) | automatic |
| Gemini CLI | automatic |
| Codex | automatic |
| OpenCode | automatic |
| Any AI tool | manual - via nomadterm start |
Troubleshooting
"nomadterm not working"
nomadterm status # Check installation
nomadterm hooks status # Check hooks specifically
nomadterm daemon status
nomadterm relay status
Hooks missing? nomadterm hooks add then restart tool.
Still broken?
nomadterm reset all && nomadterm hooks add
# Close all claude/codex/gemini/opencode/nomadterm windows
nomadterm claude # Fresh start
"messages not arriving"
- Check recipient:
nomadterm list— are theylisteningoractive? - Check message sent:
nomadterm events --sql "type='message'" --last 5 - Recipient shows
[claude*]? Restart the AI tool
Sandbox / Permission Issues
export NOMADTERM_DIR="$PWD/.nomadterm" # Project-local mode
nomadterm hooks add # Installs to project dir
Files
| What | Location |
|---|---|
| Database | ~/.nomadterm/nomadterm.db |
| Config | ~/.nomadterm/config.toml |
| Logs | ~/.nomadterm/.tmp/logs/nomadterm.log |
With NOMADTERM_DIR set, uses that path instead of ~/.nomadterm.
More Info
nomadterm --help # All commands
nomadterm <command> --help # Command details
nomadterm run docs # Full CLI + config + API reference