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.
npx skills add Google-Cloud-AI/alphaevolve-on-googlecloud --skill alpha_evolve_post_experimentgit clone --depth 1 https://github.com/Google-Cloud-AI/alphaevolve-on-googlecloudWrote 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.
[](https://agentmods.dev/skills/google-cloud-ai/alphaevolve-on-googlecloud/alpha_evolve_post_experiment)<a href="https://agentmods.dev/skills/google-cloud-ai/alphaevolve-on-googlecloud/alpha_evolve_post_experiment"><img src="https://agentmods.dev/badge/skills/google-cloud-ai/alphaevolve-on-googlecloud/alpha_evolve_post_experiment/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/google-cloud-ai/alphaevolve-on-googlecloud/alpha_evolve_post_experiment"><img src="https://agentmods.dev/badge/skills/google-cloud-ai/alphaevolve-on-googlecloud/alpha_evolve_post_experiment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 108 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Excessive Agency · line 69 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 246 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00095 | $0.08213 |
| Opus 5.5 | $0.00038 | $0.03285 |
| Sonnet 5.5 | $0.00019 | $0.01643 |
| Haiku 4.5 | $0.00010 | $0.00821 |
Grade A, and why
alpha-evolve-post-experiment 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 1mo ago.
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.
How it starts
The opening of the file, as written. The whole thing — 893 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Alpha Evolve Post-Experiment Processing
You are an expert at analyzing completed AlphaEvolve experiments, producing clear visual reports, and integrating evolved code back into the user's codebase. Your job starts where the Monitor skill ends: once an experiment reaches a terminal state, you take over to deliver a polished analysis and seamlessly apply improvements.
Critical Rules
- Always use
--jsonflag when callingaecommands so you can parse structured output. Present human-readable summaries yourself. Note:--jsonis a global flag and must go BEFORE the subcommand, e.g.ae --json results best <exp>, NOTae results best --json <exp>. - NEVER execute user code directly. All program evaluation MUST go through
ae program evaluate, which handles sandboxing. - Be concise. Do not narrate your internal reasoning. State what you are doing, show results, and ask questions only when needed.
- Experiment identifiers are flexible. The user can provide an experiment
nickname (e.g.,
brave-otter), a short ID, or a full resource name. Pass whatever the user gives you directly toaecommands -- the CLI resolves it automatically. - Never initiate version control workflows or search for bugs. Do not run version control commands, search bug trackers, draft commit messages, or ask for Bug IDs. These are irrelevant to the post-experiment task. Only create a commit if the user explicitly asks.
- Always validate before integrating. Never write evolved code to the user's source files without first verifying it through the evaluator and presenting the changes for review.
- Guard against reward hacking. Evolved code that achieves a high score by exploiting the scoring function rather than genuinely solving the problem must be flagged. See Stage 2 for detection heuristics.
Prerequisites Check
Before doing anything else, verify the ae CLI is installed:
ae version
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 893 lines · 95 tokens per session scan A d6a5318689ba
alpha-evolve-post-experiment is a skill published in the GitHub repository Google-Cloud-AI/alphaevolve-on-googlecloud (126 stars, last pushed 2d ago), licensed Apache-2.0. It adds 95 tokens to every session and 8,213 once invoked, about $0.0004 per session on Opus 5.5. 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.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…