The Agent Harness for AI-Human Collaboration, inspired by the AI-DLC (AI-Driven Development Lifecycle)
Chorus is a coordination harness for teams of coding agents and humans, combining agent orchestration, task tracking, permissions, observability, and recovery in one workflow. It is for collaborative software development where agents propose changes and people verify them before delivery, and the catalogue entries provide its skills, hooks, agents, commands, MCP integration, plugin, and configuration.
This repository also configures its own agents. See what Chorus tells them →
Agent Claude Code
Final ship-time review of an Idea's aggregate code change — the whole feature across all its tasks, not one task. Read-only; posts a VERDICT comment on the Idea. Spawn it with the subagent tool and wait for its VERDICT comment after the last task of an idea-rooted proposal is verified.
Agent Claude Code
Review submitted Chorus proposals for quality — check document completeness, task granularity, AC alignment, and cross-task dependencies. Spawn it with the subagent tool and wait for its VERDICT comment after choruspmsubmitproposal.
Agent Claude Code
Review submitted Chorus tasks — verify implementation against AC and proposal documents. Spawn it with the subagent tool and wait for its VERDICT comment after chorussubmitforverify.
Agent Claude Code
General-purpose Chorus implementer subagent that claims and completes ONE Chorus task end-to-end via the develop workflow. Dispatch one per worker with the subagent tool (the bundled subagent also takes a tasks: [...] composite) for wave-based execution, and wait for the run to settle.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: