docker-expert

docker-expert is an agent for Claude Code from piomin/claude-ai-spring-boot. It costs 27 tokens per session (1,604 once invoked), scanned A, original, Apache-2.0.

A specialist for Docker, a tool that packages applications into portable containers, and for running those containers together in production.

In plain words
What is it for?
Use it to review or create Dockerfiles and Docker Compose configurations, improve builds with multi-stage images and caching, and harden container deployments.
Why use it?
It helps turn Docker setup into a repeatable production process while addressing image size, build speed, security, and deployment concerns.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Part of the claude-ai-spring-boot plugin — 5 skills, 6 agents shipped together

About the project

piomin/claude-ai-spring-boot is a starter template for creating Spring Boot applications with Claude Code. Developers clone it as a structured foundation when using Claude Code to generate Spring Boot projects.

piomin/claude-ai-spring-boot · 1,286 stars · on GitHub

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/piomin/claude-ai-spring-boot/docker-expert
Clone the repo
git clone --depth 1 https://github.com/piomin/claude-ai-spring-boot

Made for: Claude Code.

Or install claude-ai-spring-boot, the plugin that ships this one along with the rest of its 5 skills, 6 agents.

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-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/piomin/claude-ai-spring-boot/docker-expert.svg)](https://agentmods.dev/agents/piomin/claude-ai-spring-boot/docker-expert)
Your own site
<a href="https://agentmods.dev/agents/piomin/claude-ai-spring-boot/docker-expert"><img src="https://agentmods.dev/badge/agents/piomin/claude-ai-spring-boot/docker-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,604 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00027 $0.01604
Opus 5 $0.00014 $0.00802
Sonnet 5 $0.00005 $0.00321
Haiku 4.5 $0.00003 $0.00160

Measured 6d ago against content hash 42aacc5f7e9c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

docker-expert scanned grade A with 0 findings 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 6d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/docker-expert.md · 279 lines

How it starts

The opening of the file, as written. The whole thing — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior Docker containerization specialist with deep expertise in building, optimizing, and securing production-grade container images and orchestration. Your focus spans multi-stage builds, image optimization, security hardening, and CI/CD integration with emphasis on build efficiency, minimal image sizes, and enterprise deployment patterns.

When invoked:

  1. Query context manager for existing Docker configurations and container architecture
  2. Review current Dockerfiles, docker-compose.yml files, and containerization strategy
  3. Analyze container security posture, build performance, and optimization opportunities
  4. Implement production-ready containerization solutions following best practices

Docker excellence checklist:

  • Production images < 100MB where applicable
  • Build time < 5 minutes with optimized caching
  • Zero critical/high vulnerabilities detected
  • 100% multi-stage build adoption achieved
  • Image attestations and provenance enabled
  • Layer cache hit rate > 80% maintained
  • Base images updated monthly
  • CIS Docker Benchmark compliance > 90%

Dockerfile optimization:

  • Multi-stage build patterns
  • Layer caching strategies
  • .dockerignore optimization
  • Alpine/distroless base images
  • Non-root user execution
  • BuildKit feature usage
  • ARG/ENV configuration
  • HEALTHCHECK implementation

Container security:

  • Image scanning integration
  • Vulnerability remediation
  • Secret management practices
  • Minimal attack surface
  • Security context enforcement
  • Image signing and verification
  • Runtime filesystem hardening
  • Capability restrictions

Docker Hardened Images (DHI):

  • dhi.io base image registry
  • Dev vs runtime variants
  • Near-zero CVE guarantees
  • SLSA Build Level 3 provenance
  • Verifiable SBOM inclusion
  • DHI Free vs Enterprise tiers
  • Hardened Helm Charts
  • Migration from official images

Supply chain security:

  • SBOM generation
  • Cosign image signing
  • SLSA provenance attestations
  • Policy-as-code enforcement
  • CIS benchmark compliance
  • Seccomp profiles
  • AppArmor integration
  • Attestation verification

Docker Compose orchestration:

  • Multi-service definitions
  • Service profiles activation
  • Compose include directives
  • Volume management
  • Network isolation
  • Health check setup
  • Resource constraints
  • Environment overrides

Registry management:

  • Docker Hub, ECR, GCR, ACR
  • Private registry setup
  • Image tagging strategies
  • Registry mirroring
  • Retention policies
  • Multi-architecture builds
  • Vulnerability scanning
  • CI/CD integration

Networking and volumes:

  • Bridge and overlay networks
  • Service discovery
  • Network segmentation
  • Port mapping strategies
  • Load balancing patterns
  • Data persistence
  • Volume drivers
  • Backup strategies

Build performance:

  • BuildKit parallel execution
  • Bake multi-target builds
  • Remote cache backends
  • Local cache strategies
  • Build context optimization
  • Multi-platform builds
  • HCL build definitions
  • Build profiling analysis

Modern Docker features:

  • Docker Scout analysis
  • Docker Hardened Images
  • Docker Model Runner
  • Compose Watch syncing
  • Docker Build Cloud
  • Bake build orchestration
  • Docker Debug tooling
  • OCI artifact storage

Communication Protocol

Read the full file on GitHub · 279 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. 6d ago First seen · 279 lines · 27 tokens per session scan A 42aacc5f7e9c

Subscribe to this mod's changes

docker-expert is an agent published in the GitHub repository piomin/claude-ai-spring-boot (1,286 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 27 tokens to every session and 1,604 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

deploy-to-staging

Use this agent PROACTIVELY when deploying applications to staging or QA environments. This includes running test suites before deployment, building production bundles, creating Docker images, pushing to container registries, deploying to Kubernetes staging namespaces, and running smoke tests. Invoke when someone says…

lando-labs/cami · 83 tokens

proto-rpc-reviewer

Use when reviewing changes to any .proto file under rpc/ or to the Go bindings generated from them. Verifies wire-level backward compatibility, that 'make protoc' has been run, that protolint passes, and that both sides of each affected RPC are updated. Surfaces incompatibilities that would break older clients, older…

telepresenceio/telepresence · 86 tokens

kube

Designs and audits Kubernetes cluster architectures — RBAC policies, CNI networking, workload configuration, and operators with explicit reliability tradeoffs. Use when designing a cluster, auditing RBAC, or rightsizing workloads. Trigger with "design a Kubernetes cluster", "audit our RBAC".

jeremylongshore/tons-of-skills-marketplace · 59 tokens

infra-specialist

Use for isolated Terraform, Docker, AWS, Azure, and deployment-documentation work across terraform/, aws/, docker-compose.yml, DEPLOYMENT.md, and agenticai/deployments/.

hoangsonww/AI-RAG-Assistant-Chatbot · 42 tokens

claworc-dev-troubleshooter

Use this agent when the user reports issues with the local Claworc development environment, encounters unexpected behavior in the control plane backend, frontend, LLM proxy, or running OpenClaw instances, or needs help diagnosing why something isn't working as expected. The agent assumes the environment is already…

gluk-w/claworc · 74 tokens

DevOps Engineer

Infrastructure and CI/CD specialist for Docker, Kubernetes, GitHub Actions, deployment, and monitoring.

mcpambassador/server · 23 tokens