From superpowers-devops
Use when reviewing code or a codebase for DevOps readiness, security issues, and missing best practices
How this skill is triggered — by the user, by Claude, or both
Slash command
/superpowers-devops:code-auditThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
- **Repo mode** — scan actual files in the working directory
Run through each category. Report findings as: CRITICAL, WARNING, or INFO.
.env files committed to git (check .gitignore)FROM ubuntu:latest without pinned version).dockerignore present (prevents leaking local files into image)latest)HEALTHCHECK in Dockerfile or K8s livenessProbe)requests and limits set for CPU and memorylivenessProbe and readinessProbe definedreplicas > 1 for production workloadsdefault)imagePullPolicy: Always for mutable tags.github/workflows/, .gitlab-ci.yml, Jenkinsfile)/health, /ready)/metrics)For each finding:
[SEVERITY] Category — Description
File: path/to/file (or "pasted code")
Why it matters: ...
Fix: ...
End with a summary count: X critical, Y warnings, Z info items.
Provides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
npx claudepluginhub tspry/superpowers-devops --plugin superpowers-devops