Google's open-source plugin for designing before you build: your main agent drafts the spec with full project context, then fresh subagents with no memory of the chat attack it to find gaps before a line of code is written.
In short: Google's open-source plugin for designing before you build: your main agent drafts the spec with full project context, then fresh subagents with no memory of the chat attack it to find gaps before a line of code is written. It is a free skill for people who use Claude Code or Codex and want help with coding agent skills.
Checked on · Added
| Agent / tool | Access / cost | Link |
|---|---|---|
| Claude Code | Paid Claude plan or API | claude.com/claude-code |
| Codex | ChatGPT plan or API | openai.com/codex |
| GitHub repo | Open source · ★ 10.3k | google/elephant-goldfish-model |
Image: from the GitHub README, shown with credit.
claude plugin marketplace add google/elephant-goldfish-model claude plugin install egm@egm codex plugin marketplace add google/elephant-goldfish-model
Install command copied from the project README. Check the README for the latest version.
Google's open-source plugin for designing before you build: your main agent drafts the spec with full project context, then fresh subagents with no memory of the chat attack it to find gaps before a line of code is written.
The Elephant-Goldfish Model is a spec-first way of working that the README says thousands of Google engineers use. The 'elephant' is your main agent: it holds the project context, talks through requirements with you and…
Short excerpt from the README of google/elephant-goldfish-model. Read the full README on GitHub.
From the original post, credited below.
It is meant for features that need design decisions; for a small clear bug fix it is overkill. Reviews need an agent that can start fresh subagents and stop otherwise. A review does not replace tests or your own judgement.
Google's open-source plugin for designing before you build: your main agent drafts the spec with full project context, then fresh subagents with no memory of the chat attack it to find gaps before a line of code is written.
It works with Claude Code and Codex. The code is on GitHub at google/elephant-goldfish-model.
Free & open source (Apache-2.0). No extra account or API key. Runs on the agent plan you already pay for, but every review starts several subagents, so it uses more of your plan than a normal chat.
Run the install command from the README: “claude plugin marketplace add google/elephant-goldfish-model”. Check the README on GitHub for the latest version, then follow the steps on this page.
We read 124 instruction and code files in the repo and found no red flags. That is not a guarantee, so review anything that runs commands on your machine. How to check a skill before you install it →
All credit to the original authors. We rewrite in our own words and link back. Something wrong? Report it.
SKILLYour coding agent connects to an Android or Google TV over Wi-Fi, switches off the ad and tracking apps, and puts in a clean, Apple TV-style home screen. Nothing is uninstalled.
Claude Code +2★ 14.8k
SKILLA pack of 14 skills from a design engineer that make your agent review and polish interfaces with exact rules: ranked UI reviews, typography, colour, accessibility, layout and product writing, plus tools that stress-test components and draw technical illustrations.
Claude Code +2★ 10.3k
SKILLA Claude Code skill that records an animation from a live site, a screen recording, a gif or a Lottie file, rebuilds it in your own code, then films the copy the same way and compares the two, round after round, until timing and motion match.
Claude Code★ 809
SKILLA Claude skill that reviews a vibecoded screen like a designer: it lists the tell-tale AI touches, proposes a direction from your own product, then fixes spacing, colour, icons, copy, type and layout pass by pass. Works on dashboards, apps, landing pages, or a live site from a link.
Claude Code★ 540
SKILLOne install gives your agent a plan, test, build, review and remember routine, with 71 helper agents, about 300 skills, memory between sessions and a built-in scanner for risky agent settings.
Claude Code +3★ 285.3k
SKILLA skills framework that makes agents brainstorm, plan, test and debug systematically.
Claude Code +1★ 299.2kFree newsletter
New AI tools you can use right away, in plain words. Every Friday.