ContAIned — Security skill for Claude Code
A governed coding agent CLI built on Claude Code.
How to install ContAIned
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open aiquilibria/contAIned and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What ContAIned does
A governed coding agent CLI built on Claude Code. Runs inside an isolated Docker container with operator-controlled policy baked into the image, per-tool-call audit logging, and QA gates enforced before every session is accepted.
Alternatives in Security
- MCP Security Checklist (SlowMist) — Comprehensive checklist: input validation, rate limiting, RBAC, credential management, container hardening 819 ★
- ThinkWatch — Self-hosted AI API and MCP gateway for organizations: SSO and RBAC, per-user identity for MCP tool calls, PII 817 ★
- Review Artifact — Creates one polished, self-contained HTML artifact from review findings, audit notes, PR feedback, code review 652 ★
README
cont[AI]ned
[✦] take back control of your coding agent!
A coding agent CLI built on [Claude Code](https://docs.anthropic.com/en/docs/claude-code/overview).
The agent operates within a defined workspace inside an isolated Docker container. All tool calls are audited. Policy is baked into the container image at build time and enforced by hook scripts before every tool call — the agent cannot change the rules it operates under. High-risk actions (such as git mutations) can be configured to escalate to the operator for explicit approval rather than being allowed or blocked outright.
Contents
- Why contAIned?
- Install
- Quickstart
- Commands
- Task lifecycle
- How it works
- Customizing policy
- Image support
- Known gaps
- Security model
Why contAIned?
Three existing primitives handle adjacent problems but leave a critical gap:
Claude Code's `/sandbox`
Claude Code ships a built-i
Related Skills
Docker Claude Code
new Run Claude Code in an isolated Docker container with multi-profile support, security hardening, best-pract
Agent Observability Logging
Log everything that happens inside your agent system, from deterministic code: hook-written audit events, inva
Docker Review
Review a Dockerfile/image for multi-stage correctness, size, and security.
Sanctuary Framework
Open-source security for AI agents: kernel-enforced egress control on macOS and Linux, keys only the operator
MCP Intercepter
Transparent proxy + enterprise gateway for MCP: audit logging, tool allow/deny policy, secrets/PII redaction,
Crewforth
Enterprise engineering workflow for Claude Code — not just prompts. AI agents that plan, build, audit, and shi
Related Agents
Production Docker Auditor
Audits Dockerfiles and container configuration for production hardening — multi-stage builds, non-root users,
Docker Container Master
Designs, reviews, and hardens Dockerfiles, OCI images, and Docker Compose environments with BuildKit/buildx. D
Docker Engineer
Use for anything Docker — installing Docker for a beginner, writing or reviewing a Dockerfile, docker-compose.
