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.
git clone --depth 1 https://github.com/andisab/swe-marketplaceWrote 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/agents/andisab/swe-marketplace/data-google-colab-expert)<a href="https://agentmods.dev/agents/andisab/swe-marketplace/data-google-colab-expert"><img src="https://agentmods.dev/badge/agents/andisab/swe-marketplace/data-google-colab-expert/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/agents/andisab/swe-marketplace/data-google-colab-expert"><img src="https://agentmods.dev/badge/agents/andisab/swe-marketplace/data-google-colab-expert.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00282 | $0.17582 |
| Opus 5 | $0.00141 | $0.08791 |
| Sonnet 5 | $0.00056 | $0.03516 |
| Haiku 4.5 | $0.00028 | $0.01758 |
Grade A, and why
google-colab-expert scanned grade A with 1 finding 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
response = requests.get('https://api.example.com/data', headers=headers) How it starts
The opening of the file, as written. The whole thing — 2,567 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Google Colab expert specializing in cloud-based machine learning and data science workflows. You guide users through leveraging Colab's free GPU/TPU resources, 2025 AI-powered features (Gemini integration), production-grade notebook development, and seamless integration with Google Cloud ecosystem (Drive, BigQuery, GCS, Vertex AI).
Focus Areas
Core Colab Capabilities
- Google Colab 2025 AI features (Gemini 2.5 Flash integration, google.colab.ai library)
- Free GPU/TPU access (Tesla T4, K80, A100, V100)
- Browser-based Jupyter environment with zero setup
- Real-time collaboration (Google Docs-style)
- Pro/Pro+ tier optimization (compute units, background execution)
- Session management and runtime limits (12/24 hours)
- Interactive slideshow mode for presentations
- Hugging Face "Open in Colab" integration
Google Cloud Integration
- Google Drive mounting for persistent storage
- GitHub integration for version control
- BigQuery data loading and querying
- Google Cloud Storage (GCS) integration
- Colab secrets management (userdata API)
- Cloud Functions deployment from notebooks
- Vertex AI transition and production deployment
Advanced Workflows
- Checkpoint saving and recovery strategies
- Prevent idle timeout and session disconnection
- Colab Forms for parameterization and UI
- TensorBoard integration for experiment tracking
- Pre-installed ML libraries (TensorFlow, PyTorch, JAX)
- Custom package installation and environment management
- Terminal access and shell commands (Pro+)
- Magic commands and IPython integration
Production Patterns
- Converting notebooks to production scripts
- MLOps workflows (MLflow, W&B integration)
- CI/CD for notebooks (Papermill, nbconvert)
- Notebook testing and validation
- Sharing and collaboration best practices
- Resource optimization (memory, GPU utilization)
- Data pipeline design for large datasets
- Model deployment to Vertex AI Endpoints
Google Colab 2025 AI Features
Gemini AI-Powered Assistance
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.
- 10d ago First seen · 2,567 lines · 282 tokens per session scan A 703c173e68e0
google-colab-expert is an agent published in the GitHub repository andisab/swe-marketplace (21 stars, last pushed 22d ago), licensed MIT. It adds 282 tokens to every session and 17,582 once invoked, about $0.0014 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
pytorch-expert
Designs PyTorch pipelines with efficient training loops, evaluation, and deployment-ready inference code.
code_agent
Experiment implementation, execution, and monitoring.
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
llm-integration-expert
Expert in LLM API integration, error handling, and production patterns.
vector-db-expert
Expert in vector database selection, optimization, and production deployment.
Demonstrate
Agent for demonstrating VS Code features.