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 agentmods add skills/google-cloud-ai/alphaevolve-on-googlecloud/alpha_evolve_monitornpx skills add Google-Cloud-AI/alphaevolve-on-googlecloud --skill alpha_evolve_monitorgit clone --depth 1 https://github.com/Google-Cloud-AI/alphaevolve-on-googlecloudWhat 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 | $0.00068 | $0.04061 |
| Opus 5 | $0.00034 | $0.02031 |
| Sonnet 5 | $0.00014 | $0.00812 |
| Haiku 4.5 | $0.00007 | $0.00406 |
Grade A, and why
alpha-evolve-monitor 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 3d 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 — 466 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Alpha Evolve Experiment Monitor
You are an expert at monitoring AlphaEvolve experiments using the ae CLI. Your
job is to run the evaluation control loop, track experiment progress, and
present clear status reports to the user.
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 experiment describe <exp>, NOTae experiment describe --json <exp>. - NEVER execute user code directly. All program evaluation MUST go through
ae experiment run, which handles sandboxing via the evaluator. - 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. - If the experiment name is not provided, ask the user for it. You can
also run
ae --json experiment listto show available experiments and let the user pick one.
Prerequisites Check
Before doing anything else, verify the ae CLI is installed:
ae version
If this command fails, tell the user:
The
aeCLI is not installed. This is required before proceeding. Please follow theaeCLI documentation to install it, then try again.
Stop here if ae version fails. Do not proceed.
Stage 1: Identify the Experiment
Objective: Determine which experiment to monitor and confirm it exists.
Step 1.1: Get the experiment identifier
If the user provided an experiment name/nickname/ID, use it directly.
If not, ask the user:
Which experiment would you like to monitor? You can provide a nickname (e.g.,
brave-otter), an ID, or a full resource name.
What ships with it
4 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.
- 3d ago First seen · 466 lines · 68 tokens per session scan A 3fbef4652318
alpha-evolve-monitor is a skill published in the GitHub repository Google-Cloud-AI/alphaevolve-on-googlecloud (104 stars, last pushed 20d ago), licensed Apache-2.0. It adds 68 tokens to every session and 4,061 once invoked, about $0.0003 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
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
bigquery-ai-ml
Leverages BigQuery's built-in machine learning and GenAI capabilities for advanced data analytics. Use when you need to write SQL queries that perform time-series forecasting, predict values, detect outliers or anomalies, find key drivers, perform semantic search or vector search, classify text, calculate similarity…
ondb
A logical analysis and reasoning tool for AI. Use when decomposing documents into structured knowledge, querying entities and relations, validating consistency, or indexing files. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", "analyze this document", entity CRUD, or cross-skill…
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
mixed-precision
Use FP16/BF16 mixed precision to accelerate training and reduce memory. Use when optimizing GPU performance.
sparse-autoencoder-training
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.