Individual skill

egm-review-loop

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.

skills/egm-review-loop/SKILL.md

Read pinned source

Source commit 113a3afc44e8f4f54722d7150d5701f65cc8ef7f

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: Yes
Repository scan complete: No
Skill scan complete: No
Observed behavior: Local scripts
Last checked: Nov 9, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 15,604
Repository last updated: Nov 9, 2026
License: Apache-2.0

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

agent-skills Repository topic
spec-driven-development Repository topic
antigravity Repository topic
gemini Repository topic
ai-agents Repository topic
claude-code Repository topic
claude-code-plugin Repository topic
claude-skills Repository topic
codex Repository topic
codex-plugin Repository topic
design Derived category
operations Derived category
security Derived category
docs Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

SKILL.mdcore · 10,325 bytes
SKILL.mdcore · 10,325 bytes
TEST.mddoc · 1,180 bytes
agents/openai.yamlasset · 204 bytes
assets/icon.svgasset · 544 bytes
test_scenarios.yamlasset · 5,179 bytes

Read excerpt


# 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.