hardened-shell

Name: hardened-shell
Availability: InStock
Author: spinlockdevelopment

Run agents inside an isolated Docker sandbox with read-only host mounts.

1|Updated Apr 14, 2026

Search Tags:#devops #security #claude #agent #docker #sandbox #hshell

Ready to run

npx skills add https://github.com/spinlockdevelopment/dev-setup --skill hardened-shell

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: hardened-shell
Source: https://github.com/spinlockdevelopment/dev-setup/tree/main/plugins/spindev-devenv/skills/hardened-shell
Command: npx skills add https://github.com/spinlockdevelopment/dev-setup --skill hardened-shell

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires docker, and includes scripts (resource) components.

What problem does it solve?

Provides a reproducible, locked-down environment to run Claude or other agents without risking host writes or exposing host credentials, enabling banshee-mode agent productivity while containing blast radius.

Core Features & Use Cases

Read-only host mount at /host with a project-only writable workspace at /work to prevent unintended host modifications.
Blocklist masking of sensitive host paths and files so agents cannot read common credential stores.
Per-project persistent Claude state seeded from a home template, plus launcher, image build, install, verify, and self-heal scripts to maintain a pinned, auditable runtime.
Use cases: run one-shot agents, debug agent workflows, or provision ephemeral development sandboxes safely.

Quick Start

Build the image, install the launcher, and verify health by running the build-image, install, and verify scripts in the skill directory in sequence.

Frequently Asked Questions about hardened-shell

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I run AI agents safely in a Docker sandbox to prevent host file modifications?▼

Run AI agents safely in a Docker sandbox using a read-only host mount at /host with a project-only writable workspace at /work, preventing unintended host modifications and credential exposure during local development.

How does Docker sandbox masking protect host credentials from AI agents?▼

Docker sandbox masking protects host credentials by applying file-path blocklists that prevent agents from reading common credential stores, ensuring sensitive host paths and files remain inaccessible during execution.

Do I need Docker to set up an isolated development environment for one-shot agent runs?▼

Yes, Docker is required to build and run the pinned Debian-based image, which uses mise-managed Node and Python to provide a reproducible, isolated environment for one-shot agent runs and debugging.

What is the best way to maintain a pinned, auditable runtime for ephemeral development sandboxes?▼

Maintain a pinned runtime for ephemeral development sandboxes by using the provided build, install, verify, and self-heal scripts to manage the Debian-based image, hshell launcher, and per-project persistent state.

Can I use a read-only Docker mount to debug agent workflows without risking my host environment?▼

Yes, you can debug agent workflows safely by mounting the host directory as read-only at /host, which provides per-project persistent Claude state while blocking host writes and protecting your local environment.