elephant-goldfish-model
An open-source method and skill set created at Google for spec-driven development with LLMs
Runs with mockssource: GitHubPythonApache-2.0commit d651fe86c12d
Python, Apache-2.0 licensed. The project labels itself: agent skills, ai agents, antigravity, claude code, claude code plugin, claude skills, codex and codex plugin.
elephant-goldfish-model runs, with stand-ins for the services it depends on. An Argusic agent installed it in 1 minute and hit 1 error on a clean machine with no GPU, and the whole session was recorded.
Python venv installed with pytest 9.1.1 and PyYAML 6.0.3, all 49 unit tests pass, 7 skills and 9 agent personas validated with correct YAML frontmatter, all 24 docs/designs cross-references resolve, all skills under 24KB body limit
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 72 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page. Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- Astro site build requires Node.js >=22.12.0, container has v18.19.1. No root to upgrade.0.2 minutes
- Install time
- 1 minutes
- Cold machine to finish
- 3 minutes
- Errors hit and fixed
- 1 hit, 0 fixed with no human help
- How the result was proved
- pytest tests/unit exited 0, 49 passed across 6 test modules (test_frontmatter, test_link_integrity, test_harnesses, test_claude_traces, test_scenario_coverage, test_skill_load_limits)
- Model tokens used
- 81,149
- Exact commit tested
- d651fe86c12d
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
egm_review_loop/TEST.md: ok All TEST.md files valid Here's my final assessment: The repository installs and the unit test suite runs successfully. The only limitation is the Astro… ``` ``` tokens used 81,149 Here's my final assessment: The repository installs and the unit test suite runs successfully. The only limitation is the Astro… ``` ```
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Installed in 1 minute, faster than the median of the 81 comparable projects Argusic has measured.
- Licensed Apache-2.0, as reported by its host.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
- Hit 1 error during setup, 1 of which were not solved.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 82 agent-skills projects Argusic has installed and timed, elephant-goldfish-model was the 17th fastest to reach a running state, and 58 of 82 reached one at all.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 72.00 | 0.01 |
Topics (from GitHub)
agent-skillsai-agentsantigravityclaude-codeclaude-code-pluginclaude-skillscodexcodex-plugincoding-agentscontext-engineeringdeveloper-toolsgeminillmmulti-agentprompt-engineeringspec-driven-development
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/elephant-goldfish-model)Questions
- Does elephant-goldfish-model run?
- elephant-goldfish-model runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 1 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test elephant-goldfish-model?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit d651fe86c12d. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test elephant-goldfish-model?
- The run that produced this verdict cost $0.01: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does elephant-goldfish-model take to install?
- 1 minute in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does elephant-goldfish-model need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing elephant-goldfish-model?
- 1 thing broke in the recorded run. Each one, and the time it cost, is listed on this page.
- How does elephant-goldfish-model compare with the alternatives?
- Of the 82 agent-skills projects Argusic has installed and timed, elephant-goldfish-model was the 17th fastest to reach a running state, and 58 of 82 reached one at all.
- Where is the evidence for elephant-goldfish-model?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.