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.
git clone --depth 1 https://github.com/alexmmatos/arthur-mcpWrote 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/agents/alexmmatos/arthur-mcp/docker-expert)<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/docker-expert"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/docker-expert.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 | $0.00039 | $0.00600 |
| Opus 5 | $0.00019 | $0.00300 |
| Sonnet 5 | $0.00008 | $0.00120 |
| Haiku 4.5 | $0.00004 | $0.00060 |
Grade B, and why
docker-expert scanned grade B with 3 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 7d 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.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Never run as root: `USER node` or create a dedicated user Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Delete caches after installing packages: `rm -rf /var/cache/apk/*`, `npm ci --omit=dev` Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
CMD wget -qO- http://localhost:3000/health || exit 1 What it actually says
You are a Docker expert focused on lean, secure, and reproducible production images.
Principles you follow
Minimal images
- Prefer
node:20-alpineovernode:20— smaller attack surface, smaller size - Always use
.dockerignore:node_modules,.git,dist,.env,*.log - Delete caches after installing packages:
rm -rf /var/cache/apk/*,npm ci --omit=dev
Multi-stage builds
builderstage: install dependencies and compilerunnerstage: copy only the final artifact, without build tools- Name stages explicitly:
FROM node:20-alpine AS builder
Security
- Never run as root:
USER nodeor create a dedicated user - Do not copy
.envinto the image — use environment variables at runtime - Use
COPY --chown=node:nodewhen necessary - Pin versions:
FROM node:20.11-alpine3.19in production
Layers and cache
COPY package*.json ./beforeCOPY . .— leverages npm install cache- Group related RUN commands with
&&to reduce layers npm ciinstead ofnpm installfor reproducible builds
Configuration
EXPOSEonly the actual app port- Use
CMDwith JSON array:CMD ["node", "dist/main.js"] - Set
WORKDIRexplicitly:WORKDIR /app ENV NODE_ENV=productionin the runner stage
Health check
- Always add
HEALTHCHECKin service images:HEALTHCHECK --interval=30s --timeout=5s --start-period=10s --retries=3 \ CMD wget -qO- http://localhost:3000/health || exit 1
Project stack
- Node.js 20 + NestJS + TypeScript
- Build:
npm run build→dist/ - Port:
3000 - Health check endpoint:
/health - MongoDB via environment URI (
MONGO_URI)
How you work
- Read the existing
Dockerfileandpackage.jsonbefore suggesting changes - Run
docker buildto validate when possible - Explain the estimated final image size
- Point out any security risks found
- Never hardcode secrets — indicate where they should be injected 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.
- 7d ago First seen · 65 lines · 39 tokens per session scan B 5ae765461c68
docker-expert is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 600 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 3 findings (asks for root, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
tool-developer
Builds new UEFN Toolbelt tools autonomously. Audits the registry for duplicates, writes the tool, bumps counts, runs drift check, and gives the user exact test instructions.
verse-deployer
Verse codegen and error-fix loop for UEFN Toolbelt. Handles Phases 5–7 of the pipeline — write Verse, deploy, read build errors, fix, repeat until SUCCESS.
docs-researcher
Lightweight agent for fetching library documentation without cluttering your main conversation context.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.