llms: Skill for Claude Code

.claude/skills/docker-audit/SKILL.md

docker-audit is a skill for Claude Code from matteocervelli/llms. It costs 61 tokens per session (2,220 once invoked), scanned B, original, MIT.

A checklist-based audit tool for Dockerfiles and Docker Compose files. Docker packages an application and its dependencies into containers, while Compose describes how several containers run together.

In plain words
What is it for?
Use it to review container image tags, image size, build practices, runtime safety, and Compose configuration.
Why use it?
It helps find insecure images, inefficient builds, and unsafe runtime settings before they cause deployment or maintenance problems.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: positional $N argument.

This is matteocervelli/llms's own configuration. It tells Claude Code how to work on llms itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything llms configures →

Reuse

Borrowing it

Nothing to install: this file belongs to matteocervelli/llms. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/matteocervelli/llms/main/.claude/skills/docker-audit/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/matteocervelli/llms

Made for: Claude Code.

Wrote 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.

agentmods badge for docker-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/matteocervelli/llms/docker-audit.svg)](https://agentmods.dev/skills/matteocervelli/llms/docker-audit)
Your own site
<a href="https://agentmods.dev/skills/matteocervelli/llms/docker-audit"><img src="https://agentmods.dev/badge/skills/matteocervelli/llms/docker-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,220 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00061 $0.02220
Opus 5 $0.00030 $0.01110
Sonnet 5 $0.00012 $0.00444
Haiku 4.5 $0.00006 $0.00222

Measured 3d ago against content hash db76a5ba14aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

docker-audit scanned grade B 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 3d 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.

Recursive force deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

grep -n "rm -rf.*apt\|rm -rf.*cache\|rm -rf.*tmp\|rm -rf.*lists" Dockerfile*

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

.claude/skills/docker-audit/SKILL.md · 301 lines

How it starts

The opening of the file, as written. The whole thing — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Docker Audit Skill

Purpose

Systematic audit of Docker configurations against the 10 most common Docker mistakes. Covers image security, build efficiency, runtime safety, and Compose best practices. Works with grep-based detection (no external tools required) plus optional deep scanning with hadolint, trivy, and dockle.

Quick Start

/docker-audit [path]

Discovery

Find all Docker files in scope:

find . -name "Dockerfile*" -o -name "compose*.yaml" -o -name "compose*.yml" -o -name "docker-compose*.yml" -o -name "docker-compose*.yaml" -o -name ".dockerignore" | head -50

Audit Categories

1. Image Tags (Critical)

# Detect :latest or untagged images
grep -n "^FROM.*:latest" Dockerfile*
grep -n "^FROM [^ :]*$" Dockerfile*
grep -rn "image:.*:latest" compose*.yaml docker-compose*.yml 2>/dev/null
grep -rn "image: [^ :]*$" compose*.yaml docker-compose*.yml 2>/dev/null

Pass: All FROM/image directives use pinned version tags (e.g., node:22.12-alpine) Fail: Any :latest or missing tag

2. Image Size (High)

# Check for bloated base images
grep -n "^FROM.*ubuntu\|^FROM.*debian\|^FROM.*centos\|^FROM.*fedora" Dockerfile*

Pass: Uses alpine, slim, or distroless variants Fail: Full OS base images without justification

3. Build Cache Ordering (Medium)

# Check COPY order — dependency files should come before source
grep -n "^COPY\|^ADD" Dockerfile*
# Correct: COPY package*.json -> RUN npm install -> COPY . .
# Wrong: COPY . . -> RUN npm install

Pass: Dependency manifests (package.json, requirements.txt, go.mod, Gemfile) copied and installed before source code Fail: COPY . . appears before dependency installation

4. Non-Root User (Critical)

# Check for USER directive
grep -n "^USER" Dockerfile*
# Check for user creation
grep -n "adduser\|useradd\|addgroup\|groupadd" Dockerfile*

Pass: USER directive present with non-root user Fail: No USER directive (defaults to root)

Read the full file on GitHub · 301 lines

Changes

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.

  1. 3d ago First seen · 301 lines · 61 tokens per session scan B db76a5ba14aa

Subscribe to this mod's changes

docker-audit is a skill published in the GitHub repository matteocervelli/llms (25 stars, last pushed 3mo ago), licensed MIT. It adds 61 tokens to every session and 2,220 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

deploy-docker-compose

Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…

omnigent-ai/omnigent · 84 tokens

compute-env-setup

Set up a reproducible Feynman compute environment for research jobs. Use when a task needs Python/R packages, GPU libraries, containers, Modal, SSH, caches, or managed model runtime setup.

companion-inc/feynman · 45 tokens

securing-kubernetes-on-cloud

This skill covers hardening managed Kubernetes clusters on EKS, AKS, and GKE by implementing Pod Security Standards, network policies, workload identity, RBAC scoping, image admission controls, and runtime security monitoring. It addresses cloud-specific security features including IRSA for EKS, Workload Identity for…

xalgorix/xalgorix · 80 tokens

detecting-privilege-escalation-in-kubernetes-pods

Detect and prevent privilege escalation in Kubernetes pods by monitoring security contexts, capabilities, and syscall patterns with Falco and OPA policies.

xalgorix/xalgorix · 40 tokens

implementing-rbac-hardening-for-kubernetes

Harden Kubernetes Role-Based Access Control by implementing least-privilege policies, auditing role bindings, eliminating cluster-admin sprawl, and integrating external identity providers.

xalgorix/xalgorix · 41 tokens

docker-socket-mount

Docker / containerd socket mounted into a container → host RCE. Common in CI runners, GitOps controllers (ArgoCD, Flux), and 'Docker-in-Docker' setups. Single-command escape via docker run --rm --privileged -v /:/host alpine chroot /host.

PurpleAILAB/Decepticon · 67 tokens