Orchestrate multi-agent workflows into phased execution plans with agent-bus communication.
npx skills add https://github.com/artosetrov/iron-fist-arena-backend --skill cdo
Please help me install this Agent Skill. Skill: cdo Source: https://github.com/artosetrov/iron-fist-arena-backend/tree/main/.claude/skills/cdo Command: npx skills add https://github.com/artosetrov/iron-fist-arena-backend --skill cdo
CDO provides a safe, structured way to orchestrate multiple AI agents to complete complex tasks that require delegation, parallel execution, and cross-system coordination. It prevents uncoordinated agent runs and ensures results are produced only when explicitly requested by the user and allowed by the environment.
Enable CDO only when the user explicitly requests orchestration or parallel agent work and the environment allows subagents.
High-intent search queries and answers about installing and using this skill.
Multi-agent workflows are coordinated safely by classifying tasks into a structured pipeline of agents that run in defined phases with built-in safety prompts, gate checks, and escalation blocks to prevent uncoordinated execution.
Parallel agent waves are supported in HYBRID and PARALLEL modes, allowing agents to read and write results from a shared agent bus and escalate issues via @mentions to trigger additional execution waves.
Orchestrating AI agents for delegation is best handled by classifying tasks into a sequential or hybrid pipeline, deploying specialized agents like guardians and oracles, and synthesizing final results from their combined outputs.
Yes, an environment that explicitly permits subagents is required to enable multi-agent orchestration, and orchestration should only be activated when a user explicitly requests delegation or parallel agent work.
An agent bus handles communication by allowing agents to write results to a shared directory and read outputs from others, escalating blockers via @mentions to trigger additional waves if issues arise during execution.
Multi-agent orchestration pipelines should not be used without explicit user prompts for delegation, and built-in safeguards will block execution if tasks fall outside an agent's competence or safe operating constraints.
pur3v4d3rConfigure Claude Code settings.json, permissions, sandbox, environment variables, and hooks.
StudentCristianExecute remaining NW waves sequentially with artifact verification and failure guidance.
jmolzCoordinate multiple specialized agents executing parallel tasks with defined roles.
espennilsenOrchestrate task delegation to isolated subprocesses for parallel or sequential execution.
