#126126th of 324 in Skills, plugins and prompts
elephant-goldfish-model
Plugin that drafts design specs and reviews them with fresh-context subagents
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 8.5k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Python
1,815 on 18 Sept 20268,497 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
EGM is a plugin for Antigravity, Claude Code and Codex that adds skills for brainstorming, drafting and reviewing design documents before implementation. The main agent drafts a spec with full project context, then reviewers spawned as fresh subagents check it without the earlier conversation to surface unstated assumptions. The user resolves trade-offs and approves the design.
Who it is for: Engineers using coding agents who want reviewed design specs before coding
Strengths
- Reviewers run in fresh subagent contexts, so they judge the document without conversation bias
- Seven skills (brainstorm, draft, review, resolve, bootstrap, review-loop, drift-report) usable independently
- Installs through the plugin systems of Antigravity, Claude Code and Codex
- Drift report compares checked-in design docs against current source code
Weaknesses
- Review stops if the agent cannot create fresh subagents
- README states a review does not replace tests or human judgment
- Meant for features needing design decisions, not small bug fixes
- Not an officially supported Google product; no tagged release
What it needs
- no GPU
- Needs Antigravity, Claude Code or Codex
Quick answers
Is elephant-goldfish-model open source?
Yes. Its code is on GitHub under the Apache-2.0 license.
Also in Skills, plugins and prompts
See all 324| Rank | Project | Score |
|---|---|---|
| 1 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 96 out of 100 |
| 2 | skillsAgent skills for planning, TDD, debugging and code review | 95 out of 100 |
| 3 | eccAgents, skills, hooks and rules bundle for Claude Code, Codex and other harnesses | 95 out of 100 |
| #4 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 95 out of 100 |
| #5 | cavemanCuts token use in coding agents with terse replies and compressed inputs | 95 out of 100 |