docker-customize

docker-customize is a skill for Claude Code from gtapps/claude-code-hermit. It costs 116 tokens per session (1,095 once invoked), scanned C, original, MIT.

A set of instructions for changing the tools, packages, environment variables, and background services available inside a Docker development container. Docker is software that runs an application in an isolated, repeatable environment.

In plain words
What is it for?
It helps add system packages, configure startup commands, adjust persistent directories, and validate Docker or Compose changes.
Why use it?
It helps ensure container changes are placed in the right configuration file and survive container rebuilds. It also accounts for the container's restricted permissions and separates changes the operator must run on the host.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the claude-code-hermit plugin — 32 skills, 4 agents shipped together

Good fit It helps add system packages, configure startup commands, adjust persistent directories, and validate Docker or Compose changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gtapps/claude-code-hermit/docker-customize
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.

Any agent
npx skills add gtapps/claude-code-hermit --skill docker-customize
Clone the repo
git clone --depth 1 https://github.com/gtapps/claude-code-hermit

Made for: Claude Code.

Or install claude-code-hermit, the plugin that ships this one along with the rest of its 32 skills, 4 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-customize

README.md
[![agentmods](https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/docker-customize/github.svg)](https://agentmods.dev/skills/gtapps/claude-code-hermit/docker-customize)
Your own site
<a href="https://agentmods.dev/skills/gtapps/claude-code-hermit/docker-customize"><img src="https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/docker-customize/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.

agentmods 80×15 button for docker-customize

Your own site · 80×15
<a href="https://agentmods.dev/skills/gtapps/claude-code-hermit/docker-customize"><img src="https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/docker-customize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 116 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,095 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. 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 $0.00116 $0.01095
Opus 5 $0.00058 $0.00548
Sonnet 5 $0.00023 $0.00219
Haiku 4.5 $0.00012 $0.00110

Measured 8d ago against content hash dd780c9d7b48, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade C, and why

docker-customize scanned grade C with 2 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 8d 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 deletehighDestructive command

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

rm -rf /var/lib/apt/lists/*

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL <url> -o "${PROJECT_DIR}/.claude.local/<name>/<bin>"
plugins/claude-code-hermit/skills/docker-customize/SKILL.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Docker Customize

Land a container change in the first channel that can carry it, in the order below. Files sit on the project bind mount, so this skill runs from inside the container or on the host. Rebuild, restart, and compose validation are host-only (the image has no Docker CLI): name the command for the operator, do not run it from inside the container.

1. Apt package

The container runs as USER claude with cap_drop: ALL and no-new-privileges, so nothing installs a package at runtime. It has to be in the image.

Add it inside the operator block of Dockerfile.hermit (between # --- operator: and # --- end operator ---):

RUN apt-get update && apt-get install -y --no-install-recommends \
      <pkg> <pkg> && \
    rm -rf /var/lib/apt/lists/*

A Dockerfile rendered before the operator block existed has no such markers. Add the block yourself, between the gh install layer and the # Match host UID comment, then put the RUN inside it:

# --- operator: root-context installs go here; upgrades merge around this block ---
#
# --- end operator ---

Then rebuild on the host: .claude-code-hermit/bin/hermit-docker restart --build (it needs the container running; from stopped, .claude-code-hermit/bin/hermit-docker up --build).

Tell the operator: docker.packages in config.json is read only when the templates are rendered, so setting it installs nothing on its own. Re-check the file after an upgrade.

2. Boot-time shell

If a shell can do it at boot, put it in <project-root>/docker-entrypoint.hermit-local.sh. Persist files under .claude.local/ (bind-mounted, gitignored). Upgrades never touch the sidecar.

The managed entrypoint sources the sidecar twice, with HERMIT_ENTRY_PHASE naming which:

  • pre-boot: channel dirs exist, env resolved, before plugins install. Env, directories, downloads, pip / npm -g, pre-session checks.
  • pre-launch: immediately before hermit-start. Side services, last-second overrides.

Read the full file on GitHub · 64 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. 8d ago Changed · +7 lines · -2 tokens per session dd780c9d7b48
  2. 8d ago First seen · 57 lines · 118 tokens per session scan C b77c04730649

Subscribe to this mod's changes

docker-customize is a skill published in the GitHub repository gtapps/claude-code-hermit (74 stars, last pushed yesterday), licensed MIT. It adds 116 tokens to every session and 1,095 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). 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

symfony:runner-selection

Select and configure the appropriate command runner based on Docker Compose standard, Symfony Docker (FrankenPHP), or host environment.

dev-toolings/superpowers-symfony · 29 tokens

docker-expert

Use when working with Dockerfile, docker-compose.yml, .dockerignore, or multi-stage builds. Build, debug, secure, and optimize Docker 27+ images and Docker Compose services.

Aarvion-AI/stackwise-skills · 42 tokens

infra-standards

Infrastructure, container, and CI/CD discipline — IaC, Dockerfiles and compose files, CI pipelines, platform deploy config, env/secrets handling. INVOKE PROACTIVELY when creating or editing any such file (.tf, .bicep, Dockerfile, docker-compose, .github/workflows/, vercel.json) — even when nobody says "infra". Not for…

PrabhdeepSingh/claude-plugins · 106 tokens

ccc-devops

For scheduled deployments and automated infra tasks, see: https://code.claude.com/docs/en/scheduled-tasks — ccc-devops skills (especially cicd-pipeline-generator and zero-downtime-deploy) can be wrapped as scheduled routines for nightly deployments, weekly security scans, or periodic drift detection.

KevinZai/commander · 38 tokens

helm-k8s-patterns

No artifact. This skill emits prescriptive guidance inline. The implementing agent writes the chart and values files in the assigned IaC worktree.

lukasrepublic/agentic-foundry · 0 tokens

legacy-app-containerize

Skill "legacy-app-containerize" from lukasrepublic/agentic-foundry, covering when to trigger and anti-patterns.

lukasrepublic/agentic-foundry · 0 tokens