optional-skills/autonomous-ai-agents/blackbox/SKILL.md
Delegate coding tasks to Blackbox AI CLI agent. Multi-model agent with built-in judge that runs tasks through multiple LLMs and picks the best result. Requires the blackbox CLI and a Blackbox AI API key.
npx skillsauth add garrettroi/open-manus blackboxInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Delegate coding tasks to Blackbox AI via the Hermes terminal. Blackbox is a multi-model coding agent CLI that dispatches tasks to multiple LLMs (Claude, Codex, Gemini, Blackbox Pro) and uses a judge to select the best implementation.
The CLI is open-source (GPL-3.0, TypeScript, forked from Gemini CLI) and supports interactive sessions, non-interactive one-shots, checkpointing, MCP, and vision model switching.
npm install -g @blackboxai/cligit clone https://github.com/blackboxaicode/cli.git
cd cli && npm install && npm install -g .
blackbox configure and enter your API keypty=true in terminal calls — Blackbox CLI is an interactive terminal appterminal(command="blackbox --prompt 'Add JWT authentication with refresh tokens to the Express API'", workdir="/path/to/project", pty=true)
For quick scratch work:
terminal(command="cd $(mktemp -d) && git init && blackbox --prompt 'Build a REST API for todos with SQLite'", pty=true)
For tasks that take minutes, use background mode so you can monitor progress:
# Start in background with PTY
terminal(command="blackbox --prompt 'Refactor the auth module to use OAuth 2.0'", workdir="~/project", background=true, pty=true)
# Returns session_id
# Monitor progress
process(action="poll", session_id="<id>")
process(action="log", session_id="<id>")
# Send input if Blackbox asks a question
process(action="submit", session_id="<id>", data="yes")
# Kill if needed
process(action="kill", session_id="<id>")
Blackbox CLI has built-in checkpoint support for pausing and resuming tasks:
# After a task completes, Blackbox shows a checkpoint tag
# Resume with a follow-up task:
terminal(command="blackbox --resume-checkpoint 'task-abc123-2026-03-06' --prompt 'Now add rate limiting to the endpoints'", workdir="~/project", pty=true)
During an interactive session, use these commands:
| Command | Effect |
|---------|--------|
| /compress | Shrink conversation history to save tokens |
| /clear | Wipe history and start fresh |
| /stats | View current token usage |
| Ctrl+C | Cancel current operation |
Clone to a temp directory to avoid modifying the working tree:
terminal(command="REVIEW=$(mktemp -d) && git clone https://github.com/user/repo.git $REVIEW && cd $REVIEW && gh pr checkout 42 && blackbox --prompt 'Review this PR against main. Check for bugs, security issues, and code quality.'", pty=true)
Spawn multiple Blackbox instances for independent tasks:
terminal(command="blackbox --prompt 'Fix the login bug'", workdir="/tmp/issue-1", background=true, pty=true)
terminal(command="blackbox --prompt 'Add unit tests for auth'", workdir="/tmp/issue-2", background=true, pty=true)
# Monitor all
process(action="list")
Blackbox's unique feature is running the same task through multiple models and judging the results. Configure which models to use via blackbox configure — select multiple providers to enable the Chairman/judge workflow where the CLI evaluates outputs from different models and picks the best one.
| Flag | Effect |
|------|--------|
| --prompt "task" | Non-interactive one-shot execution |
| --resume-checkpoint "tag" | Resume from a saved checkpoint |
| --yolo | Auto-approve all actions and model switches |
| blackbox session | Start interactive chat session |
| blackbox configure | Change settings, providers, models |
| blackbox info | Display system information |
Blackbox automatically detects images in input and can switch to multimodal analysis. VLM modes:
"once" — Switch model for current query only"session" — Switch for entire session"persist" — Stay on current model (no switch)Control token usage via .blackboxcli/settings.json:
{
"sessionTokenLimit": 32000
}
pty=true — Blackbox CLI is an interactive terminal app and will hang without a PTYworkdir — keep the agent focused on the right directorybackground=true and monitor with process toolpoll/log, don't kill sessions because they're slowblackbox CLI is installed before attempting delegationdevelopment
# Voice Sanitizer This skill cleans up text before it is sent to the Text-to-Speech (TTS) engine. It removes technical jargon, code blocks, and long URLs to ensure the agent sounds natural and conversational in voice chat. ## Usage To sanitize text for speech, run the following command in the terminal: ```bash python3 /app/skills/voice_sanitizer/sanitizer.py "Your long, technical text with `code` and https://links.com/long-url" ``` ### Example Output ```text Your long, technical text with a
tools
Professional AI video production workflow. Use when creating videos, short films, commercials, or any video content using AI generation tools.
tools
Secure API key access from the centralized vault. Fetch keys on-demand without storing them in environment variables.
testing
# Task Board — Persistent Task Tracking for Open Manus This skill provides a shared task board backed by Redis. Harmony uses it to track delegated work across all agents, and agents use it to report progress and completion. ## When to Use - **Harmony**: Use this whenever you delegate a task to an agent. Add the task to the board, then check the board periodically to follow up. - **Worker Agents**: Use this to update your task status or mark tasks as complete. ## Commands ### Add a new task