From blaxel
Manage Blaxel resources from the command line using the bl CLI. Deploy agents, sandboxes, jobs, and MCP servers. Also installs the Blaxel CLI if not present.
How this skill is triggered — by the user, by Claude, or both
Slash command
/blaxel:blaxel-cliThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
A CLI to manage Blaxel cloud resources from the command line: agents, sandboxes,
SKILL.template.mdassets/blaxel-logo.svgdeno.jsondeno.lockmetadata.jsonreferences/apply.mdreferences/chat.mdreferences/commands.mdreferences/connect.mdreferences/delete.mdreferences/deploy.mdreferences/drive.mdreferences/get.mdreferences/login.mdreferences/logout.mdreferences/logs.mdreferences/new.mdreferences/push.mdreferences/run.mdreferences/serve.mdA CLI to manage Blaxel cloud resources from the command line: agents, sandboxes, jobs, MCP servers, drives, and more.
The bl command must be available on PATH. To check:
bl version
If not installed, install via the official install script:
curl -fsSL https://raw.githubusercontent.com/blaxel-ai/toolkit/main/install.sh | sh
Or via Homebrew:
brew tap blaxel-ai/blaxel && brew install blaxel
After installation, log in to your workspace:
bl login my-workspace
All commands support these flags:
| Flag | Description |
|---|---|
-o, --output <format> | Output format: pretty, yaml, json, table |
-w, --workspace <name> | Override workspace for this command |
-v, --verbose | Enable verbose output |
-u, --utc | Enable UTC timezone |
--skip-version-warning | Skip version warning |
For commands that prompt for input (confirmations, selections), add -y or
--yes to auto-confirm. This is required when running in non-interactive /
no-TTY environments (scripts, CI, agents).
bl apply # Apply configuration changes to resources declaratively using YAML files.
bl chat # Start an interactive chat session with a deployed agent.
bl connect # Open an interactive terminal session to a sandbox
bl delete # Delete Blaxel resources from your workspace.
bl deploy # Deploy your Blaxel project to the cloud.
bl drive # Manage drives and drive mounts on sandboxes.
bl get # Retrieve information about Blaxel resources in your workspace.
bl login # Authenticate with Blaxel to access your workspace.
bl logout # Remove stored credentials for a workspace.
bl logs # View logs for Blaxel resources.
bl new # Create a new Blaxel resource from templates.
bl push # Build and push a container image to the Blaxel registry without creating a deployment.
bl run # Execute a Blaxel resource with custom input data.
bl serve # Start a local development server for your Blaxel project.
bl share # Share Blaxel resources with other workspaces in your account.
bl token # Retrieve the authentication token for the specified workspace.
bl unshare # Remove shared Blaxel resources from other workspaces.
bl upgrade # Upgrade the Blaxel CLI to the latest version.
bl version # Print the version number
bl workspaces # List and manage Blaxel workspaces.
To see available subcommands and flags, run --help on any command:
bl --help
bl deploy --help
bl get --help
bl get agents --help
# 1. Create a sandbox with bl apply
bl apply -f - <<EOF
apiVersion: blaxel.ai/v1alpha1
kind: Sandbox
metadata:
name: my-sandbox
spec:
runtime:
image: blaxel/base-image:latest
memory: 2048
lifecycle:
expirationPolicies:
- type: ttl-idle
value: 1h # Delete after 1 hour of inactivity. Units: h, d, w
action: delete
EOF
# 2. Retrieve sandbox configuration
bl get sandbox my-sandbox
# 3. Execute a command in the sandbox and get stdout of the command
bl run sandbox my-sandbox --path /process --data '{"command": "echo hello world", "name": "my-cmd", "waitForCompletion": true}'
# 4. Retrieve the logs for that command in case stdout was not sufficient
bl logs sandbox my-sandbox my-cmd
bl run sandbox ... --path /process --data '<json>' requires the JSON payload
to survive shell quoting. As soon as the command embeds nested quotes,
backslashes, multiple lines, or interpreters like sh -lc / python3 -c,
inline --data becomes brittle and the API rejects the request with
400 Bad Request: invalid character ... in string escape code.
Decision rule for an agent:
--data '{"command": "...", "waitForCompletion": true}' directly.--file.# Step 1 — agent writes /tmp/process.json with content like:
# {
# "command": "sh -lc 'python3 -c \"print(\\\"hello\\\")\"'",
# "name": "cve-check",
# "waitForCompletion": true
# }
#
# Step 2 — execute it
bl run sandbox my-sandbox --path /process --file /tmp/process.json
bl new agent my-agent
cd my-agent
bl serve --hotreload # Test locally
bl deploy # Deploy to cloud
bl chat my-agent # Chat with it
bl get sandboxes # List all
bl get sandbox my-sandbox --watch # Watch status
bl connect sandbox my-sandbox # Interactive terminal
bl logs sandbox my-sandbox --follow # Stream logs
bl delete sandbox my-sandbox # Clean up
bl workspaces dev # Switch to dev
bl deploy # Deploy to dev
bl workspaces prod # Switch to prod
bl deploy # Deploy to prod
Provides CDSS development patterns for drug interaction checking, dose validation, clinical scoring (NEWS2, qSOFA), and alert classification integrated into EMR workflows.
npx claudepluginhub blaxel-ai/agent-skills --plugin blaxel