egm-review-loop

原文涵盖的主题

• Goldfish Review: Loop (Orchestration Driver)
• Overview
• Delegation
• Inputs
• Path & Standard Resolution Logic
• Execution Workflow
• Step 1: Intake & Configuration UX
• Step 2: The Sharpening Loop (Iterative Cycle)

When running in Codex or ChatGPT Work, first read Codex integration. In Claude Code or Cowork, read ${CLAUDEPLUGINROOT}/docs/claude.md first. This skill acts as the central orchestration engine driving the multi-agent review loop. It coordinates two distinct agent memory models: The Goldfish (Adversarial Auditors): Subagents spawned in isolated, fresh context windows to catch unstated assumptions without historical bias. The Elephant (Persistent Resolver): The primary agent context holding institutional knowledge to evaluate findings and apply approved repairs. The driver manages argument intake, resolves paths for reviewers and standards, unconditionally re-parses target line ranges before every iteration, spawns concurrent specialized Goldfish auditors based on configuration, and coordinates with the Elephant context to resolve findings. A Goldfish runs in a fresh context with no conversation history. Spawn each subagent with your harness's subagent tool (Antigravity: invokesubagent; Claude Code: Agent; Codex: spawnagent). Each subagent is defined in agents/ .md, and its frontmatter name (for example egm-zoom-out) is the subagent type to request where your harness registers named

这里只展示节选，请以完整原文和当前要求为准。