Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/bestagentkits/agency-skillsnpx agentmods add skills/bestagentkits/agency-skills/docker-developmentWrote 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.
[](https://agentmods.dev/skills/bestagentkits/agency-skills/docker-development)<a href="https://agentmods.dev/skills/bestagentkits/agency-skills/docker-development"><img src="https://agentmods.dev/badge/skills/bestagentkits/agency-skills/docker-development.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00084 | $0.02877 |
| Opus 5 | $0.00042 | $0.01438 |
| Sonnet 5 | $0.00017 | $0.00575 |
| Haiku 4.5 | $0.00008 | $0.00288 |
Grade B, and why
docker-development 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 4d 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.
- **apt-get without cleanup in same layer** → `rm -rf /var/lib/apt/lists/*` in the same RUN. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Copies of this mod
1 near-identical copy found in the catalogue:
- docker-development — 97% identical, 3 lines differ
How it starts
The opening of the file, as written. The whole thing — 367 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docker Development
Smaller images. Faster builds. Secure containers. No guesswork.
Opinionated Docker workflow that turns bloated Dockerfiles into production-grade containers. Covers optimization, multi-stage builds, compose orchestration, and security hardening.
Not a Docker tutorial — a set of concrete decisions about how to build containers that don't waste time, space, or attack surface.
Slash Commands
| Command | What it does |
|---|---|
/docker:optimize |
Analyze and optimize a Dockerfile for size, speed, and layer caching |
/docker:compose |
Generate or improve docker-compose.yml with best practices |
/docker:security |
Audit a Dockerfile or running container for security issues |
When This Skill Activates
Recognize these patterns from the user:
- "Optimize this Dockerfile"
- "My Docker build is slow"
- "Create a docker-compose for this project"
- "Is this Dockerfile secure?"
- "Reduce my Docker image size"
- "Set up multi-stage builds"
- "Docker best practices for [language/framework]"
- Any request involving: Dockerfile, docker-compose, container, image size, build cache, Docker security
If the user has a Dockerfile or wants to containerize something → this skill applies.
Workflow
/docker:optimize — Dockerfile Optimization
-
Analyze current state
- Read the Dockerfile
- Identify base image and its size
- Count layers (each RUN/COPY/ADD = 1 layer)
- Check for common anti-patterns
-
Apply optimization checklist
BASE IMAGE ├── Use specific tags, never :latest in production ├── Prefer slim/alpine variants (debian-slim > ubuntu > debian) ├── Pin digest for reproducibility in CI: image@sha256:... └── Match base to runtime needs (don't use python:3.12 for a compiled binary) LAYER OPTIMIZATION ├── Combine related RUN commands with && \ ├── Order layers: least-changing first (deps before source code) ├── Clean package manager cache in the same RUN layer ├── Use .dockerignore to exclude unnecessary files └── Separate build deps from runtime deps BUILD CACHE ├── COPY dependency files before source code (package.json, requirements.txt, go.mod) ├── Install deps in a separate layer from code copy ├── Use BuildKit cache mounts: --mount=type=cache,target=/root/.cache └── Avoid COPY . . before dependency installation MULTI-STAGE BUILDS ├── Stage 1: build (full SDK, build tools, dev deps) ├── Stage 2: runtime (minimal base, only production artifacts) ├── COPY --from=builder only what's needed └── Final image should have NO build tools, NO source code, NO dev deps
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 367 lines · 84 tokens per session scan B ae547a03efba
docker-development is a skill published in the GitHub repository bestagentkits/agency-skills (10 stars, last pushed 2mo ago), licensed MIT. It adds 84 tokens to every session and 2,877 once invoked, about $0.0004 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.
Other skills, from other repositories
configure-log-aggregation
Set up centralized log aggregation with Loki and Promtail (or ELK stack), including log parsing, label extraction, retention policies, and integration with metrics for correlation. Use when consolidating logs from multiple services into a searchable system, replacing local log files with centralized queryable storage…
deploy-to-kubernetes
Deploy applications to Kubernetes clusters using kubectl manifests for Deployments, Services, ConfigMaps, Secrets, and Ingress resources. Implement health checks, resource limits, rolling updates, and Helm chart packaging for production deployments. Use when deploying new applications to EKS, GKE, AKS, or self-hosted…
configure-reverse-proxy
Configure reverse proxy patterns across multiple tools including Nginx, Traefik, and ShinyProxy. Covers WebSocket proxying, path-based and host-based routing, SSL termination, and Docker label auto-discovery. Use when routing multiple services behind a single entry point, proxying WebSocket connections (Shiny…
deploy-searxng
Deploy a self-hosted SearXNG meta search engine via Docker Compose. Covers settings.yml configuration, engine selection, result proxying, Nginx frontend, persistence, and updates. Use when setting up a private search engine without tracking, aggregating results from multiple providers, running a shared search instance…
containerize-mcp-server
Containerize an R-based MCP (Model Context Protocol) server using Docker. Covers mcptools integration, port exposure, stdio vs HTTP transport, and connecting Claude Code to the containerized server. Use when deploying an R MCP server without requiring a local R installation, creating a reproducible MCP server…
create-multistage-dockerfile
Create multi-stage Dockerfiles that separate build and runtime environments for minimal production images. Covers builder/runtime stage separation, artifact copying, scratch/distroless/alpine targets, and size comparison. Use when production images are too large, when build tools are included in the final image, when…