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.
npx skills add Ozzeron/prompt-pack --skill dockergit clone --depth 1 https://github.com/Ozzeron/prompt-packWrote 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/ozzeron/prompt-pack/docker)<a href="https://agentmods.dev/skills/ozzeron/prompt-pack/docker"><img src="https://agentmods.dev/badge/skills/ozzeron/prompt-pack/docker/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ozzeron/prompt-pack/docker"><img src="https://agentmods.dev/badge/skills/ozzeron/prompt-pack/docker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 159 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium MCP Rug Pull · line 162 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
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 | $0.00096 | $0.03114 |
| Opus 5.5 | $0.00038 | $0.01246 |
| Sonnet 5.5 | $0.00019 | $0.00623 |
| Haiku 4.5 | $0.00010 | $0.00311 |
Grade A, and why
docker 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docker Discipline
You write and modify Dockerfiles and docker-compose files. You match the project's existing container conventions before introducing your own, build images that are small, cached correctly, run as a non-root user, and never bake secrets into layers. You are stack-agnostic — the rules below apply identically to Node, Python, Go, Java, Ruby, and anything else that gets containerised.
Read annotated examples when you need a reference Dockerfile, .dockerignore, secret-mount,
and docker-compose.yml examples that pair with the rules in this file.
Preflight (do this before writing or editing any container file)
The rules in this skill close concrete AI failure modes (unpinned latest, secrets in
ARG, COPY . . before install, missing .dockerignore, root in final stage). Empirical
behaviour: agents that read the existing Dockerfile first skip almost all of these
mistakes. Agents that start writing first hit every one.
- Routing check. Is this an edit to an existing
Dockerfile/docker-compose.yml, or a new image from scratch? If the file exists, you are editing — open it first, do not draft a parallel one. Creating a secondDockerfile.newis a Preflight failure. - Convention discovery, before any change. Read in this order, stop when you have
enough to match style: existing
DockerfileandDockerfile.*variants →docker-compose.yml/compose.yml→.dockerignore→ anyMakefile/package.json/pyproject.tomlscripts that invokedocker build. Note: base image and tag, build tool (multi-stage pattern,buildx,bake), package manager, non-root user setup, entrypoint shape. Match it. Do not introduce a second runtime (e.g. switchingpython:3.12-slimtoalpine"because it's smaller") without an explicit reason and the user's nod. - Out-of-scope check. If the request is for Kubernetes manifests, Helm charts,
ECS task definitions, or Docker Swarm stacks, stop — this skill does not cover those.
CI/CD: do not edit workflow YAML unless the user explicitly asked. You may read
CI to learn how the image is built (args, targets, platforms, contexts, tags) — same
boundary as
## Scopebelow. - Secrets path. Before writing any
ARGorENV, decide where secrets will come from at build time (BuildKit--secret, neverARG) and at runtime (orchestrator env / mounted file, neverENVin the image). If you cannot answer both, ask before writing.
What ships with it
2 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.
- 1mo ago Changed · -56 lines · +70 tokens per session 91d15dddd99c
- 1mo ago First seen · 283 lines · 26 tokens per session scan A ed949adf14e7
docker is a skill published in the GitHub repository Ozzeron/prompt-pack (8 stars, last pushed 1mo ago), licensed MIT. It adds 96 tokens to every session and 3,114 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
create-dockerfile
Create general-purpose Dockerfiles for Node.js, Python, Go, Rust, and Java projects. Covers base image selection, dependency installation, user permissions, COPY patterns, ENTRYPOINT vs CMD, and .dockerignore. Use when containerizing an application for the first time, creating a consistent build/runtime environment…
kubernetes-patterns
Kubernetes workload patterns, resource management, RBAC, probes, autoscaling, ConfigMap/Secret handling, and kubectl debugging for production-grade deployments.
deployment-patterns
Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications. Use when setting up deployment infrastructure or planning releases.
docker-patterns
Docker and Docker Compose patterns for local development, container security, networking, volume strategies, and multi-service orchestration. Use when setting up containerized development environments or reviewing Docker configurations.
kubernetes-architect
Expert Kubernetes architect specializing in cloud-native infrastructure, advanced GitOps workflows (ArgoCD/Flux), and enterprise container orchestration.
docker-patterns
Docker and Docker Compose patterns for local development, container security, networking, volume strategies, and multi-service orchestration.