Radar / AI coding tools / Elephant-Goldfish Model
Elephant-Goldfish Model: Google's spec-first plugin for coding agents
Google open-sourced the Elephant-Goldfish Model plugin: a long-context 'Elephant' session writes the design spec while stateless 'Goldfish' subagents attack it through three staged review gates before any code is written.
Why it matters
Google's internal fix for AI 'slop' — design in one session, review in fresh ones — now an Apache 2.0 plugin used daily by thousands of Googlers.
What you could build with it
A team shipping with coding agents could adopt the Elephant-Goldfish workflow for its riskiest changes, letting a fresh-context reviewer challenge the design doc before implementation starts, catching wrong assumptions while they are still cheap to fix.
Does it hold up?
Usable today on Antigravity, Claude Code, Codex and ChatGPT, though it is explicitly not an officially supported Google product, and one open issue reports AGENTS.md leaking into Codex reviewers, so isolation is not yet guaranteed on every host.
Built with Elephant-Goldfish Model
- Google AI Releases Elephant-Goldfish Model Plugin for Spec-First Codingmarktechpost · Runs on any harness that can spawn fresh subagents; live harness test runs passed, but no accuracy benchmark published.
- Google's Elephant-Goldfish Method for AI Design Reviewsdigitalapplied · Method explainer: seven skills, reviewer personas and document standards under Apache 2.0, not an officially supported Google product.
- Google Open-Sources Elephant-Goldfish Model Plugin for Spec-First AI Codingthemetaverseguy · November 8 coverage noting the harness guide now covers Antigravity, Claude Code, Codex, ChatGPT, omp and Muse.
Learn more
First spotted on github: source.
More AI coding tools
Chrome DevTools MCP: give your coding agent a real browserOfficial MCP server from the Chrome team that lets coding agents drive a live Chrome — console, network, traces…coding · JEV 0.82Orca: the agent development environment for running coding-agent fleetsStably AI's open-source desktop app for running many CLI coding agents side by side — Claude Code, Codex, Cursor and…coding · JEV 0.78Open Code Review: Alibaba's hybrid AI code reviewer, now past 50,000 starsAlibaba's open-source code review CLI (Apache 2.0) pairs deterministic rules with an LLM agent to review git diffs…coding · JEV 0.77Astryx: Meta's agent-ready design system, open sourceMeta open-sourced the React 19 + StyleX design system behind 13,000 internal apps: 150+ accessible components, themes…coding · JEV 0.76GitHub Spec Kit — spec-driven development for coding agentsGitHub's open-source toolkit that gives any coding agent a structured spec, plan, tasks, implement workflow, so specs…coding · JEV 0.75shadcn/improve: audit with your best model, execute with your cheapestAn MIT-licensed Agent Skill that audits any codebase across nine categories with parallel subagents, vets its own…coding · JEV 0.75
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.