Conductor

Conductor

CLI tool for defining and running multi-agent workflows with the GitHub Copilot SDK, Anthropic Claude, Claude Agent SDK, or Hermes (NousResearch, experimental).

DO NOT create new workflow files unless the user explicitly asks you to create one. Default to running, validating, or debugging existing workflows. If the user's request is ambiguous, assume they want to run or modify an existing workflow rather than create a new one.

Error Handling

CRITICAL — do NOT improvise workarounds. If conductor fails for any reason (installation failure, provider error, missing dependency, platform bug), you MUST:

1. Report the exact error to the user — include the full error message.
2. Stop and wait for user direction. Do NOT attempt to simulate, replicate, or approximate the multi-agent workflow yourself. The value of this skill is the structured multi-agent orchestration — a single-agent attempt is not an equivalent substitute.

Setup

Conductor is installed automatically when needed. If a conductor command fails with "command not found", install it. For installation instructions, see references/setup.md.

Quick Reference

conductor run workflow.yaml --input question="Hello"     # Execute (full output by default)
conductor -q run workflow.yaml --input question="Hello"  # Quiet: lifecycle + routing only
conductor -s run workflow.yaml --input question="Hello"  # Silent: JSON result only
conductor run workflow.yaml --log-file auto               # Log full debug output to file
conductor run workflow.yaml --web --input q="Hello"       # Real-time web dashboard
conductor run workflow.yaml --web-bg --input q="Hello"    # Background mode (prints URL, exits)
conductor run workflow.yaml -m tracker=ado -m work_item=42 # Attach metadata (merged on top of YAML)
conductor run workflow.yaml --workspace-instructions     # Auto-discover AGENTS.md / CLAUDE.md / etc.
conductor validate workflow.yaml                         # Validate (schema + semantic checks)
conductor show workflow.yaml                             # Show inputs, agents, and outputs
conductor replay events.jsonl                            # Replay a recorded run in the dashboard
conductor registry add official myorg/workflows --default # Add a registry (--type github|path)
conductor registry list official                          # List registry workflows
conductor run qa-bot@official@1.0.0 --input q="Hello"    # Run from registry
conductor stop                                           # Stop background workflow
conductor update                                         # Check + print install command
conductor update --apply                                 # Check + launch installer (then exit)
conductor resume workflow.yaml                           # Resume from last checkpoint
conductor resume workflow.yaml --web                     # Resume with dashboard (run-flag parity)
conductor checkpoint list                                # List available checkpoints

Full output is shown by default. Use -q (quiet) for minimal output or -s (silent) for JSON-only — both are root-level options and must come before the subcommand (conductor -q run ..., not conductor run ... -q).

When to Use Each Guide

Creating or modifying workflows? → See references/authoring.md

• Agent definitions, prompts, and output schemas
• Routing patterns (linear, conditional, loop-back)
• Parallel and for-each groups
• Human gates
• Context modes and MCP servers
• Cost tracking configuration

Running or debugging workflows? → See references/execution.md

• CLI options and flags (run, resume, checkpoint list, stop, update)
• Debugging techniques
• Error troubleshooting
• Checkpoint/resume after failures
• Environment setup and providers

Need complete YAML schema? → See references/yaml-schema.md

• All configuration fields with types and defaults
• Validation rules
• Type definitions

Minimal Workflow Example

workflow:
  name: my-workflow
  entry_point: answerer
  input:
    question: { type: string }

agents:
  - name: answerer
    prompt: "Answer: {{ workflow.input.question }}"
    output:
      answer: { type: string }
    routes:
      - to: $end

output:
  answer: "{{ answerer.output.answer }}"

For runtime config, context modes, limits, and cost tracking, see references/authoring.md.

Key Concepts

For pattern examples (linear, loop, conditional, parallel, for-each, human gate) and template syntax, see references/authoring.md.