alpha-evolve-experiment-design

alpha-evolve-experiment-design is a skill for Claude Code, Codex from Google-Cloud-AI/alphaevolve-on-googlecloud. It costs 78 tokens per session (2,023 once invoked), scanned A, original, Apache-2.0.

A guide to designing AlphaEvolve experiments, where an automated system tests changes to a program to improve a stated result. It turns a natural-language problem into a tested experiment project.

In plain words
What is it for?
Describing a problem to optimize, preparing existing code for evolution, defining how results are measured, and creating a ready-to-run experiment directory.
Why use it?
It provides the required files and structure so an experiment can be handed to an experiment runner without assembling everything manually.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/google-cloud-ai/alphaevolve-on-googlecloud/alpha_evolve_experiment_design
Any agent
npx skills add Google-Cloud-AI/alphaevolve-on-googlecloud --skill alpha_evolve_experiment_design
Clone the repo
git clone --depth 1 https://github.com/Google-Cloud-AI/alphaevolve-on-googlecloud

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for alpha-evolve-experiment-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/google-cloud-ai/alphaevolve-on-googlecloud/alpha_evolve_experiment_design.svg)](https://agentmods.dev/skills/google-cloud-ai/alphaevolve-on-googlecloud/alpha_evolve_experiment_design)
Your own site
<a href="https://agentmods.dev/skills/google-cloud-ai/alphaevolve-on-googlecloud/alpha_evolve_experiment_design"><img src="https://agentmods.dev/badge/skills/google-cloud-ai/alphaevolve-on-googlecloud/alpha_evolve_experiment_design.svg" alt="Measured on agentmods" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,023 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00078 $0.02023
Opus 5 $0.00039 $0.01012
Sonnet 5 $0.00016 $0.00405
Haiku 4.5 $0.00008 $0.00202

Measured 4d ago against content hash 70beca4f35e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

alpha-evolve-experiment-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (examples/circle_packing/evaluator.py, examples/circle_packing/initial_program.py, examples/circle_packing/test_evaluator.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/alpha_evolve_experiment_design/SKILL.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Experiment Design Skill

You help users design AlphaEvolve experiments. You take a problem description and produce a complete, tested project directory that the experiment-runner skill can launch.

Preconditions

  • The user has a problem description (natural language). It may be rigorous or vague.
  • Optional: existing code to optimize.
  • Optional: a target directory path. If not provided, ask. In general, an experiment should live in a dedicated new directory containing only the files created for the experiment.

Postconditions

A project directory containing:

File Purpose
.evolve/experiment_description.json Complete experiment specification
.evolve/source_map.json Maps code regions to original source
: : files (only when optimizing existing :
: : code; enables post-experiment :
: : integration) :
initial_program.py Seed program with EVOLVE-BLOCK
: : markers and ORIGIN comments :
evaluator.py CLI-compatible evaluator script for
: : the ae CLI :
problem_description.md Detailed technical problem
: : description (used in LLM prompts) :
example_evaluation.json Sample evaluator output
test_program.py Pytest tests for the initial program
test_evaluator.py Pytest tests for the evaluator
pyproject.toml uv project configuration
README.md Experiment documentation
*.py (multi-file only) Additional context files imported by
: : the initial program :

Read the full file on GitHub · 191 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 191 lines · 78 tokens per session scan A 70beca4f35e6

Subscribe to this mod's changes

alpha-evolve-experiment-design is a skill published in the GitHub repository Google-Cloud-AI/alphaevolve-on-googlecloud (106 stars, last pushed 2d ago), licensed Apache-2.0. It adds 78 tokens to every session and 2,023 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens