docker
Execute research code inside isolated Docker containers for safe replication, experiments, and benchmarks. Use when the user selects Docker as the execution environment or asks to run code safely, in isolation, or in a sandbox.
How do I install this agent skill?
npx skills add https://github.com/companion-inc/feynman --skill dockerIs this agent skill safe to install?
- Gen Agent Trust Hubpass
The skill facilitates the execution of research code within isolated Docker containers to ensure safe replication and experimentation. It uses standard Docker commands and well-known base images from official repositories to create sandboxed environments for untrusted code.
- Socketpass
No alerts
- Snykpass
Risk: LOW · No issues
What does this agent skill do?
Docker Sandbox
Run research code inside Docker containers while Feynman stays on the host. The container gets the project files, runs the commands, and results sync back.
When to use
- User selects "Docker Sandbox" as the execution environment in
/replicateor/autoresearch - Running untrusted code from a paper's repository
- Experiments that install packages or modify system state
- Any time the user asks to run research code safely or isolated for a Feynman workflow
How it works
- Build or pull an appropriate base image for the research code
- Mount the project directory into the container
- Run experiment commands inside the container
- Results write back to the mounted directory
Running commands in a container
For Python research code (most common):
docker run --rm -v "$(pwd)":/workspace -w /workspace python:3.11 bash -c "
pip install -r requirements.txt &&
python train.py
"
For projects with a Dockerfile:
docker build -t feynman-experiment .
docker run --rm -v "$(pwd)/results":/workspace/results feynman-experiment
For GPU workloads:
docker run --rm --gpus all -v "$(pwd)":/workspace -w /workspace pytorch/pytorch:latest bash -c "
pip install -r requirements.txt &&
python train.py
"
Choosing the base image
| Research type | Base image |
|---|---|
| Python ML/DL | pytorch/pytorch:latest or tensorflow/tensorflow:latest-gpu |
| Python general | python:3.11 |
| Node.js | node:20 |
| R / statistics | rocker/r-ver:4 |
| Julia | julia:1.10 |
| Multi-language | ubuntu:24.04 with manual installs |
Persistent containers
For iterative experiments (like /autoresearch), create a named container instead of --rm. Choose a descriptive name based on the experiment:
docker create --name <name> -v "$(pwd)":/workspace -w /workspace python:3.11 tail -f /dev/null
docker start <name>
docker exec <name> bash -c "pip install -r requirements.txt"
docker exec <name> bash -c "python train.py"
This preserves installed packages across iterations. Clean up with:
docker stop <name> && docker rm <name>
Notes
- The mounted workspace syncs results back to the host automatically
- Containers are network-enabled by default — add
--network nonefor full isolation - For GPU access, Docker must be configured with the NVIDIA Container Toolkit
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/companion-inc/feynman/docker">View docker on skillZs</a>