omnireview-github

OmniForge

Multi-agent adversarial PR review — 3 parallel agents, 3 worktrees, 1 consolidated report.

Dispatch 3 parallel specialized agents in isolated git worktrees to perform adversarial, independent analysis of a GitHub PR. Consolidate findings via confidence scoring, present actionable report, then offer structured actions (comment, create issues, approve).

Core principle: Independent adversarial review + confidence filtering + worktree isolation = high-signal feedback with minimal noise.

Announce at start: "I'm using OmniForge to review PR #{id}."

Prerequisites

• gh CLI authenticated (gh auth status to verify)
• Git repository with remote pointing to GitHub
• Current working directory is in the git repo

Input Parsing

Accept any of: PR number (136), prefixed (#136), or full GitHub URL. Extract PR ID. If URL provided, extract owner/repo and PR number.

The Process

digraph omnireview_flow {
    rankdir=TB;
    node [shape=box];

    gather [label="Phase 1: Gather PR Data\ngh pr view + diff + comments"];
    worktrees [label="Phase 2: Create 3 Worktrees\n(on PR source branch)"];
    dispatch [label="Phase 3: Dispatch 3 OmniForge Agents\nIN PARALLEL"];
    analyst [label="PR Analyst (OmniForge)\n(worktree 1)"];
    codebase [label="Codebase Reviewer (OmniForge)\n(worktree 2)"];
    security [label="Security Reviewer (OmniForge)\n(worktree 3)"];
    consolidate [label="Phase 4: Consolidation\nconfidence scoring + cross-correlation"];
    report [label="Phase 5: Present Report\n(NEVER auto-post)"];
    action [label="Phase 6: Action Menu\n(user chooses)"];
    cleanup [label="Phase 7: Cleanup\n(ALWAYS runs)"];

    gather -> worktrees -> dispatch;
    dispatch -> analyst;
    dispatch -> codebase;
    dispatch -> security;
    analyst -> consolidate;
    codebase -> consolidate;
    security -> consolidate;
    consolidate -> report -> action -> cleanup;
}

---

Phase 1: Gather PR Data

Fetch ALL data before dispatching agents. Agents get data injected — they never re-fetch.