moltbot
Physical presence display for AI agents. Shows a customizable monogram (A-Z), status state, and current activity on a dedicated terminal/screen. Provides faster feedback than chat - glance at the display to see what the agent is doing. Use when setting up always-on agent visibility.
bunx add-skill moltbot/skills -s clawd-presenceLoading…
Terminal-based presence display for AI agents.
Chat has latency. A presence display inverts this - the agent broadcasts state continuously, you glance at it like a clock.
# Configure (auto-detect from clawdbot or manual)
python3 scripts/configure.py --auto
# or
python3 scripts/configure.py --letter A --name "AGENT"
# Run display in dedicated terminal
python3 scripts/display.py
Call from your agent whenever starting a task:
python3 scripts/status.py work "Building feature"
python3 scripts/status.py think "Analyzing data"
python3 scripts/status.py idle "Ready"
python3 scripts/status.py alert "Need attention"
python3 scripts/status.py sleep
| State | Color | Use |
|---|---|---|
idle | Cyan | Waiting |
work |
| Green |
| Executing |
think | Yellow | Processing |
alert | Red | Needs human |
sleep | Blue | Low power |
Returns to idle after 5 minutes of no updates. Prevents stale states.
python3 scripts/configure.py --timeout 300 # seconds, 0 to disable
scripts/display.py - Main displayscripts/status.py - Update statusscripts/configure.py - Settingsassets/monograms/ - Letter designs A-ZUse when you need to run Flow type checking, or when seeing Flow type errors in React code.
Use when you want to validate changes before committing, or when you need to check all React contribution requirements.
Use when feature flag tests fail, flags need updating, understanding @gate pragmas, debugging channel-specific test failures, or adding new flags to React.
Use when you need to check feature flag states, compare channels, or debug why a feature behaves differently across release channels.