run other cli agents

Data Community

Skill notes

When to use this skill

Use when the user request matches this skill's domain and capabilities. Use when this workflow or toolchain is explicitly requested.

When not to use this skill

Do not use when another skill is a better direct match for the task. Do not use when the request is outside this skill's scope. Execute external CLI agents safely with comprehensive error handling, async execution, output format detection, and security controls.

Core Capabilities

Safe Execution: Built-in error handling, retries, and timeout management Async Mode: Run agents in background for long-running tasks Format Detection: Auto-detect and validate JSON, XML, or text output Sandboxing: Execute untrusted agents with filesystem and network isolation Agent Chaining: Pipe output from one agent to another

Using the Helper Script

The scripts/run_agent.sh script provides robust agent execution with multiple options:

Common Options

--async - Run agent in background, return immediately with run ID --timeout N - Set timeout in seconds (default: 300) --retry N - Retry N times on failure (default: 0) --format FMT - Expected output format: json|text|auto (default: auto) --sandbox - Run in restricted sandbox (requires firejail)

Fluxly profile Runtime and permissions are inferred by Fluxly static checks, not author declarations or runtime test results.
Domain
Data
Author-declared agents
No explicit declaration found; this is not inferred or tested compatibility
Static check
88 / 100 · heuristic scan, not runtime safety proof
Runtime evidence
Not run; no isolated runtime test evidence is currently recorded
Author / version / license
@0-CYBERDYNE-SYSTEMS-0 · no license declared
Token usage
Lean
Setup complexity
Manual integration
External API key
Not required
Operating systems
macOS · Docker
Runtime requirements
Docker
Detected file/system behavior
  • Read-only
  • Shell exec
  • Env read
Network behavior
Local-only
Install commands
None (reference only)

Heads up: Tool permissions are not declared; actual access depends on the runtime.

Output preview run-other-cli-agents.preview
# Quick Security Example

# Run untrusted agent with multiple protections
./scripts/run_agent.sh \
    --sandbox \
    --timeout 30 \
    --format json \
    --quiet \
    untrusted-agent "task"

Discussion

Powered by GitHub Discussions. Sign in with GitHub to comment, react, or subscribe.