Borrowing it
Nothing to install: this file belongs to TheDecipherist/claude-code-mastery-project-starter-kit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/TheDecipherist/claude-code-mastery-project-starter-kit/main/.claude/commands/optimize-docker.mdgit clone --depth 1 https://github.com/TheDecipherist/claude-code-mastery-project-starter-kitWrote 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/commands/thedecipherist/claude-code-mastery-project-starter-kit/optimize-docker)<a href="https://agentmods.dev/commands/thedecipherist/claude-code-mastery-project-starter-kit/optimize-docker"><img src="https://agentmods.dev/badge/commands/thedecipherist/claude-code-mastery-project-starter-kit/optimize-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/commands/thedecipherist/claude-code-mastery-project-starter-kit/optimize-docker"><img src="https://agentmods.dev/badge/commands/thedecipherist/claude-code-mastery-project-starter-kit/optimize-docker.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00007 | $0.02554 |
| Opus 5.5 | $0.00003 | $0.01022 |
| Sonnet 5.5 | $0.00001 | $0.00511 |
| Haiku 4.5 | $0.00001 | $0.00255 |
Grade A, and why
optimize-docker scanned grade A 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 2mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
CMD wget --no-verbose --tries=1 --spider http://localhost:3001/health || exit 1 How it starts
The opening of the file, as written. The whole thing — 353 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Optimize Docker Build
Analyze and optimize the Docker setup for: $ARGUMENTS
If no Dockerfile path provided, search for Dockerfiles in the project root.
Step 0 — Auto-Branch (if on main)
Before modifying any files, check the current branch:
git branch --show-current
Default behavior (auto_branch = true in claude-mastery-project.conf):
- If on
mainormaster: automatically create a feature branch and switch to it:
Report: "Created branchgit checkout -b chore/docker-optimizechore/docker-optimize— main stays untouched." - If already on a feature branch: proceed
- If not a git repo: skip this check
To disable: Set auto_branch = false in claude-mastery-project.conf. When disabled, warn and ask the user before proceeding on main.
Step 1 — Find and Read All Docker Files
Read these files (if they exist):
Dockerfile(or the path provided in $ARGUMENTS)docker-compose.yml/docker-compose.yaml.dockerignorepackage.json(for build scripts and dependencies)
Step 2 — Audit Against Best Practices
Check every rule below. For each violation, report:
- What's wrong
- Why it matters (performance impact or security risk)
- The fix
RULE 1: Multi-Stage Builds (MANDATORY)
Every production Dockerfile MUST use multi-stage builds. No exceptions.
# CORRECT — multi-stage: build artifacts don't ship to production
FROM node:20-alpine AS builder
WORKDIR /app
COPY package.json pnpm-lock.yaml ./
RUN corepack enable && pnpm install --frozen-lockfile
COPY . .
RUN pnpm build
FROM node:20-alpine AS runner
WORKDIR /app
COPY --from=builder /app/dist ./dist
COPY --from=builder /app/node_modules ./node_modules
COPY --from=builder /app/package.json ./
CMD ["node", "dist/index.js"]
# WRONG — single stage ships devDependencies, source code, build tools
FROM node:20
WORKDIR /app
COPY . .
RUN npm install
RUN npm run build
CMD ["node", "dist/index.js"]
Why: Single-stage images are 3-10x larger. They ship TypeScript source, devDependencies, build tools — none of which are needed at runtime.
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.
- 2mo ago First seen · 353 lines · 7 tokens per session scan A 751f6b51b3c4
optimize-docker is a command published in the GitHub repository TheDecipherist/claude-code-mastery-project-starter-kit (342 stars, last pushed 4mo ago), licensed MIT. It adds 7 tokens to every session and 2,554 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
optimize-docker compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| optimize-dockerTheDecipherist/claude-code-mastery-project-starter-kit | Command | 342 | 4mo ago | MIT | A | 7 | Claude Code |
| create-docker-mcp-tunnelanthropics/claude-plugins-official | Command | 46k | yesterday | Apache-2.0 | B | 26 | Claude Code |
| cisco-isovalent-platform-setupchambear2809/splunk-cisco-skills | Command | 40 | 6d ago | Apache-2.0 | A | 0 | Claude Code |
| build-agentTheLobbi/claude | Command | 21 | 7d ago | MIT | A | 0 | Claude Code |
| application-crudtranfu-labs/tranfu-skills | Command | 2 | 1mo ago | MIT | A | 0 | Claude Code |
| review-helminfraspecdev/tesseract | Command | 6 | 4mo ago | MIT | A | 25 | Claude Code |
| create-operatorSagart-cactus/claude-k8s-plugin | Command | 34 | 8mo ago | MIT | A | 12 | Claude Code |