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 agentmods add skills/fdueblab/micro-agent/docker_packagingnpx skills add fdueblab/Micro-Agent --skill docker_packaginggit clone --depth 1 https://github.com/fdueblab/Micro-AgentWhat 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 | $0.00000 | $0.00320 |
| Opus 5 | $0.00000 | $0.00160 |
| Sonnet 5 | $0.00000 | $0.00064 |
| Haiku 4.5 | $0.00000 | $0.00032 |
Grade A, and why
docker_packaging 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 2d 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.
What it actually says
你是容器化部署专家。为 Python MCP 服务生成 Docker 配置时，遵循以下规范：
Dockerfile 模板
FROM python:3.10-slim
WORKDIR /app
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple
COPY . .
EXPOSE 8000
CMD ["python", "server.py"]
requirements.txt 必要依赖
MCP 服务必须包含以下依赖：
mcp>=1.4.0
starlette
uvicorn
httpx
根据原始代码的依赖补充其他包。如果原项目有 requirements.txt，合并后去重。
docker-compose.yml 模板
version: '3.8'
services:
mcp-service:
build: .
ports:
- "8000:8000"
restart: unless-stopped
environment:
- PYTHONUNBUFFERED=1
关键规则
- 基础镜像固定
python:3.10-slim，保持轻量 - pip 安装源使用清华镜像加速
- EXPOSE 端口与 server.py 中 uvicorn 端口一致
- 不要在镜像中包含 .git、pycache、.env 等文件
- 如原代码依赖系统库（如 gcc），在 pip install 前用 apt-get 安装
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.
- 2d ago First seen · 53 lines · 0 tokens per session scan A fcf3dfda4774
docker_packaging is a skill published in the GitHub repository fdueblab/Micro-Agent (99 stars, last pushed 20d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 320 tokens. 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 2026-08-30.
Other skills, from other repositories
emil-design-eng
This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.
playwright-testing
Use when writing Playwright tests, fixing flaky tests, debugging failures, implementing Page Object Model, configuring CI/CD, optimizing performance, mocking APIs, handling authentication or OAuth, testing accessibility (axe-core), file uploads/downloads, date/time mocking, WebSockets, geolocation, permissions…
content-quality-auditor
Publish-readiness gate: 80-item CORE-EEAT audit with weighted scoring, veto checks, and fix plan. 内容质量/EEAT评分.
content-refresher
Refresh outdated posts with current stats, new sections, freshness signals to restore rankings. 内容更新/排名恢复.
domain-authority-auditor
40-item CITE domain audit: citation, impact, trust, entity scoring with veto checks. 域名权威/网站可信度.
entity-optimizer
Build entity presence in Knowledge Graph, Wikidata, AI systems for brand recognition and citations. 实体优化/知识图谱.