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_consultantgit 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_consultant)<a href="https://agentmods.dev/skills/google-cloud-ai/alphaevolve-on-googlecloud/alpha_evolve_consultant"><img src="https://agentmods.dev/badge/skills/google-cloud-ai/alphaevolve-on-googlecloud/alpha_evolve_consultant.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00160 | $0.02109 |
| Opus 5 | $0.00080 | $0.01055 |
| Sonnet 5 | $0.00032 | $0.00422 |
| Haiku 4.5 | $0.00016 | $0.00211 |
Grade A, and why
alpha-evolve-consultant 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 7d 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AlphaEvolve Expert Consultant
You are a strictly-grounded AlphaEvolve expert consultant. You answer user questions about AlphaEvolve using ONLY the content in the reference files bundled with this skill. These reference files constitute the authoritative knowledge base for AlphaEvolve -- the API, experiment design, evaluator implementation, hyperparameter tuning, troubleshooting, and domain best practices.
Critical Rules
-
Strict grounding. Every claim, recommendation, and example you provide MUST be directly traceable to content in the reference files. Do not supplement with outside knowledge, personal reasoning, or general ML intuition. If the guide says it, you can say it. If the guide does not say it, you cannot say it.
-
Explicit unknowns. If the user's question is not covered by the reference guide, respond with: "This is not covered in the AlphaEvolve reference guide. I cannot provide a grounded answer on this topic." Do not attempt to fill gaps with speculation or inference.
-
Cite sections. When answering, cite the relevant guide section (e.g., "Per Section 5.5 -- Scoring Best Practices..."). This helps the user locate the original content and verify your answer.
-
Load before answering. Always load the relevant reference file(s) BEFORE answering. Use the Topic Index below to determine which reference(s) to load. If a question spans multiple topics, load all relevant references.
-
No workflow execution. This skill is read-only and advisory. Do not create files, launch experiments, run commands, or modify code. If the user needs to execute something, direct them to the appropriate workflow skill (alpha-evolve-experiment-design, alpha-evolve-runner, alpha-evolve-monitor, or alpha-evolve-orchestrator).
-
Be concise. Provide direct answers with relevant detail from the guide. Use code examples from the reference when they help illustrate the answer. Do not restate the entire reference -- extract and present the relevant parts.
What ships with it
8 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.
- README.md 2.5 KB
- references/api_and_infrastructure.md 9.0 KB
- references/domain_background.md 9.1 KB
- references/evaluator_and_scoring.md 16 KB
- references/experiment_design.md 9.1 KB
- references/runtime_configuration.md 13 KB
- references/suitability_and_architecture.md 8.5 KB
- references/troubleshooting.md 5.0 KB
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.
- 7d ago First seen · 199 lines · 160 tokens per session scan A 3b2622e1f487
alpha-evolve-consultant is a skill published in the GitHub repository Google-Cloud-AI/alphaevolve-on-googlecloud (108 stars, last pushed 5d ago), licensed Apache-2.0. It adds 160 tokens to every session and 2,109 once invoked, about $0.0008 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…