New to Claude Skills? Learn how to install them →

nousresearch on GitHub

Blackbox CLI

Free

Delegate coding tasks to multiple AI models seamlessly.

Get this skill

Free · Opens the source repo

What Blackbox CLI does

Blackbox CLI is a powerful tool designed for developers looking to streamline their coding tasks by leveraging the capabilities of multiple AI models. This command-line interface allows users to delegate coding tasks to Blackbox AI, which intelligently dispatches these tasks to various language models, including Claude, Codex, and Gemini. By employing a judging mechanism, Blackbox selects the most effective implementation for the task at hand, ensuring optimal results. This multi-model approach enhances the quality of code generation and reduces the time spent on repetitive tasks.

The Blackbox CLI operates in an interactive terminal environment, making it suitable for both one-off commands and longer, background tasks. Users can initiate quick coding sessions or set up more complex operations that require monitoring over time. The CLI supports checkpointing, allowing developers to pause and resume tasks as needed, which is particularly useful for lengthy operations. Additionally, users can spawn multiple instances of Blackbox for parallel work, enabling them to tackle several tasks simultaneously without interruption.

For those who require visual input handling, Blackbox also includes vision model support, allowing it to analyze images in the input and switch to multimodal analysis as necessary. This feature is particularly beneficial for projects that involve image processing or require visual context. Overall, Blackbox CLI is targeted at developers and teams looking to improve their coding efficiency by harnessing the power of AI in a structured way, making it an essential tool in modern software development workflows.

When to use it

Use Blackbox CLI when you need to delegate coding tasks efficiently across multiple AI models, especially for complex or lengthy tasks.

When not to use it

This tool may not be suitable for simple coding tasks that do not require AI assistance or when working in environments without terminal support.

What you can build with it

Quick Code Snippet Generation

Use Blackbox CLI to quickly generate code snippets for tasks like adding authentication to an API.

Long Task Monitoring

Start a long refactoring task in background mode and monitor its progress without interrupting your workflow.

Parallel Task Execution

Spawn multiple Blackbox instances to tackle different coding issues simultaneously, enhancing productivity.

How to install Blackbox CLI

View source

1. Install with the skills CLI

npx skills add nousresearch/hermes-agent/blackbox --agent claude-code

2. Or install it manually

Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.

Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs

Inside SKILL.md

Written by nousresearch

Blackbox CLI

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 (npm @blackbox_ai/blackbox-cli, binary blackbox) is a TypeScript coding agent (forked from Gemini CLI) and supports interactive sessions, non-interactive one-shots, checkpointing, MCP, and vision model switching.

Prerequisites

  • Node.js 20+ installed
  • Blackbox CLI installed: npm install -g @blackbox_ai/blackbox-cli (binary: blackbox)
  • API key from app.blackbox.ai/dashboard
  • Configured: run blackbox configure and enter your API key
  • Use pty=true in terminal calls — Blackbox CLI is an interactive terminal app

One-Shot Tasks

terminal(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)

Background Mode (Long Tasks)

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>")

Checkpoints & Resume

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)

Session Commands

During an interactive session, use these commands:

CommandEffect
/compressShrink conversation history to save tokens
/clearWipe history and start fresh
/statsView current token usage
Ctrl+CCancel current operation

PR Reviews

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)

Parallel Work

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")

Multi-Model Mode

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.

Key Flags

FlagEffect
--prompt "task" (-p)Non-interactive one-shot execution
--resume-checkpoint "tag"Resume from a saved checkpoint
--yolo (-y)Auto-approve all actions and model switches
--vlm-switch-mode <mode>Image-handling: once, session, or persist
-c, --checkpointingEnable checkpointing of file edits
blackbox configureChange settings, providers, models
blackbox updateUpdate the CLI to the latest version
blackbox mcpManage MCP servers
blackbox extensionsManage CLI extensions
blackbox voice <action> / blackbox shortcutConfigure voice input / the b shortcut

Vision Support

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)

Token Limits

Control token usage via .blackboxcli/settings.json:

{
  "sessionTokenLimit": 32000
}

Rules

  1. Always use pty=true — Blackbox CLI is an interactive terminal app and will hang without a PTY
  2. Use workdir — keep the agent focused on the right directory
  3. Background for long tasks — use background=true and monitor with process tool
  4. Don't interfere — monitor with poll/log, don't kill sessions because they're slow
  5. Report results — after completion, check what changed and summarize for the user
  6. Credits cost money — Blackbox uses a credit-based system; multi-model mode consumes credits faster
  7. Check prerequisites — verify blackbox CLI is installed before attempting delegation

Frequently asked questions about Blackbox CLI

Similar skills