# Egm Review Loop

Executes the Antagonistic-Review process from the Elephant-Goldfish Model (EGM) via an...

- Repository: https://github.com/google/elephant-goldfish-model (8873 stars)
- Category: Design
- License: Apache-2.0
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add google/elephant-goldfish-model --skill egm-review-loop -g -a claude-code -y`
Codex: `npx skills add google/elephant-goldfish-model --skill egm-review-loop -g -a codex -y`
Cursor: `npx skills add google/elephant-goldfish-model --skill egm-review-loop -g -a cursor -y`
Gemini CLI: `npx skills add google/elephant-goldfish-model --skill egm-review-loop -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add google/elephant-goldfish-model`

## Description

Executes the Antagonistic-Review process from the Elephant-Goldfish Model (EGM) via an automated multi-agent review loop to audit documents against qualitative standards and structural templates, and automatically apply approved fixes. Use when reviewing design docs, READMEs, feature specifications, implementation plans, or verifying document completeness and tone.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Goldfish Review: Loop (Orchestration Driver)

When running in Codex or ChatGPT Work, first read [Codex integration](../../docs/codex.md).
In Claude Code or Cowork, read `${CLAUDE_PLUGIN_ROOT}/docs/claude.md` first.

## Overview

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.

## Delegation

A Goldfish runs in a fresh context with no conversation history. Spawn each
subagent with your harness's subagent tool (Antigravity: `invoke_subagent`; Claude Code: `Agent`; Codex: `spawn_agent`). Each subagent is defined in `agents/<file>.md`, and its
frontmatter `name` (for example `egm-zoom-out`) is the subagent type to request
where your harness registers named subagents. Otherwise spawn a general-purpose
subagent and tell it to read that persona file first. Pass the prompt verbatim
and wait for the report. If your harness cannot nest subagents,
use direct dispatch instead of the synthesizer. See `docs/harnesses.md`.
If your harness has no subagent tool, stop and tell the user: a review in the same
context is not a Goldfish review.

## Inputs

The caller or user provides exactly these parameters:

The rest: https://github.com/google/elephant-goldfish-model/blob/HEAD/distributions/claude/skills/egm-review-loop/SKILL.md