Maintainer of this skill?
Automated security scan — not a certification.
by google
An open-source method and skill set created at Google for spec-driven development with LLMs
# Add to your Claude Code skills
git clone https://github.com/google/elephant-goldfish-modelGuides for using ai agents skills like elephant-goldfish-model.
Last scanned: 10/27/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-10-27T09:37:37.902Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}See how elephant-goldfish-model compares with popular alternatives.
elephant-goldfish-model is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by google. An open-source method and skill set created at Google for spec-driven development with LLMs. It has 1,984 GitHub stars.
Yes. elephant-goldfish-model passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/google/elephant-goldfish-model" and add it to your Claude Code skills directory (see the Installation section above).
elephant-goldfish-model is primarily written in Python. It is open-source under google on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh elephant-goldfish-model against similar tools.
No comments yet. Be the first to share your thoughts!
30 days in the Featured rail · terms & refunds
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
Automated security scan — not a certification.
See comparison
Thousands of Google engineers use EGM, an open-source plugin, to draft specs with deep-context agents and stress-test them with zero-context subagents before writing code.
Elephant holds your project context and drafts the specification. Goldfish reviewers examine the draft and referenced source material without the earlier conversation, helping expose unstated assumptions and blind spots. You make the architectural trade-offs and approve the specification before implementing.
Use it when a feature needs design decisions before implementation. For a small, clear bug fix, use your normal coding workflow.
Choose your coding agent. Install the complete plugin so its skills can read the reviewer prompts and document standards.
agy plugin install https://github.com/google/elephant-goldfish-model
claude plugin marketplace add google/elephant-goldfish-model
claude plugin install egm@egm
codex plugin marketplace add google/elephant-goldfish-model
codex plugin add egm@egm
Start a new session after installation. For Claude Cowork and ChatGPT Work, see the setup guide.
Open your project in your coding agent and choose a feature that needs design decisions. This example adds webhook delivery: what should happen when a delivery fails, or the same event arrives twice?
Use the commands below in Antigravity. In Claude Code, use the /egm: prefix, for example /egm:egm-brainstorm. In Codex, select the corresponding EGM skill from the skill picker. Brainstorming and review require a session that can create fresh subagents.
Explore the idea
/egm-brainstorm Add webhook delivery to this project.
Discuss requirements and trade-offs with the agent. Fresh reviewers challenge the proposal, and the agent saves the agreed direction in concepts_brief.md.
Draft the specification
/egm-draft
The agent turns the brief into design_draft.md, pausing after each section for your feedback in chat.
Review the draft
/egm-review design_draft.md
Use the draft path returned by the agent.
Fresh reviewers check the design, its clarity, its fit with the code, and its implementation plan. Choose which findings to address. When you approve the design, ask your coding agent to implement it.
See the workflow guide for the full process, including saving approved specifications under docs/designs/.
Goldfish reviews require fresh subagent contexts. If your agent cannot create them, EGM stops the review. A review does not replace tests or human judgment. See supported environments and verification limits.
You can use each skill when you need it. You do not have to follow the full sequence.
Read contributing for PRs, issues for bugs, and discussions for questions.
Apache 2.0. This is not an officially supported Google product.