consensus-loop

Automate GitHub issue and pull request resolution through multi-perspective consensus.

24|6|Updated May 25, 2026
One-click install
npx skills add https://github.com/ChronoAIProject/consensus-rnd --skill consensus-loop
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: consensus-loop
Source: https://github.com/ChronoAIProject/consensus-rnd/tree/main/skills/consensus-loop
Command: npx skills add https://github.com/ChronoAIProject/consensus-rnd --skill consensus-loop

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Coordinating multiple AI agents to resolve GitHub issues and pull requests requires managing independent solvers, converging their conflicting proposals, and safely executing the resulting plan—all while maintaining strict boundaries between design, implementation, and review. Without a disciplined consensus engine, teams risk inconsistent decisions, scope creep, and broken automation that bypasses essential review gates.

Core Features & Use Cases

  • Biased multi-solver consensus: Deploys independent minimal-change, structural, and delete solvers followed by a meta-judge to converge on a single concrete plan, ensuring no single perspective dominates.
  • Full lifecycle automation: Manages the complete workflow from GitHub issue intake and design consensus through isolated worktree implementation, multi-role review, and conditional merge or release publication.
  • Audit-driven fallback: When no managed work is available, the skill performs repository audits to surface philosophy violations and architecture drift, feeding findings back into the main resolution path.

Quick Start

Use the consensus-loop skill to resolve the attached GitHub issue by running the full unattended consensus engine that designs, implements, reviews, and merges the solution.

Frequently Asked Questions about consensus-loop

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate GitHub issue resolution using multiple AI agents?

Automating GitHub issue resolution with multiple AI agents requires a biased multi-perspective consensus engine that deploys independent solvers and a meta-judge to converge conflicting proposals into a single actionable plan.

What is multi-solver consensus for AI code review and pull request automation?

Multi-solver consensus for AI code review deploys minimal-change, structural, and delete solvers independently, then uses a meta-judge to converge their conflicting proposals into one concrete implementation plan for pull requests.

How to manage isolated worktree implementation for autonomous AI pull requests?

Managing isolated worktree implementation for autonomous AI pull requests involves orchestrating deterministic workflows that separate design consensus, implementation in isolated worktrees, and multi-role review gates before conditional merges.

Does consensus-loop work with Codex workers for unattended GitHub automation?

Yes, it orchestrates Codex workers for unattended GitHub automation by synchronizing GitHub state, applying host-agnostic runtime configuration via injected environment facts, and enforcing strict boundaries between design, implementation, and review.

What happens when there are no open GitHub issues for the AI consensus engine to process?

When no managed GitHub issues are available, the AI consensus engine performs repository audits to surface philosophy violations and architecture drift, feeding those findings back into the main resolution path.

Why use a biased consensus engine instead of a single AI agent for GitHub pull requests?

A biased consensus engine prevents any single AI perspective from dominating GitHub pull request resolution, avoiding inconsistent decisions, scope creep, and broken automation that bypasses essential multi-role review gates.