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/sumonmselim/agentguard/dockernpx skills add SumonMSelim/agentguard --skill dockergit clone --depth 1 https://github.com/SumonMSelim/agentguardWhat 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 | $0.00038 | $0.00819 |
| Opus 5 | $0.00019 | $0.00409 |
| Sonnet 5 | $0.00008 | $0.00164 |
| Haiku 4.5 | $0.00004 | $0.00082 |
Grade A, and why
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 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.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Never run as root. Prefer images with built-in non-root user: distroless `nonroot`, `node` user in Node images, `nobody` in Alpine. Otherwise add non-root user and switch: `USER appuser` Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docker
Image security
- Never run as root. Prefer images with built-in non-root user: distroless
nonroot,nodeuser in Node images,nobodyin Alpine. Otherwise add non-root user and switch:USER appuser - Minimal base:
distroless,alpine, or official slim variants - Pin by digest or immutable tag. Never
FROM node:latestorimage: myapp:latestin Compose - Multi-stage builds: build in full image, copy only artifact to minimal runtime image
- No build tools in final image
- Scan with Trivy or Grype in CI. Fail on critical/high CVEs
- Multi-arch: build with
--platform linux/amd64,linux/arm64for cross-platform targets
Dockerfile
- One process per container
- Enable BuildKit:
DOCKER_BUILDKIT=1. Use--mount=type=cachefor dependency caches,--mount=type=secretfor build-time secrets COPYspecific files. AvoidCOPY . .when targeted copy suffices- Layer order: least → most frequently changed.
COPY package.jsonbeforeCOPY src/ .dockerignore: exclude.git,node_modules, test files, secrets,.env- Explicit
WORKDIR. No implicit root working dir ENTRYPOINTfor executable,CMDfor default args- No secrets in
ENV,ARG, orRUN— persist in layer history. Use--mount=type=secret HEALTHCHECKon all long-running services
Runtime
- Read-only root filesystem where possible:
--read-only - Drop all capabilities, re-add only what's needed:
--cap-drop ALL --cap-add NET_BIND_SERVICE - No
--privilegedin production - Set resource limits:
--memory,--cpus - Named volumes for persistent data. No bind mounts in production
- No secrets via env vars. Use Docker secrets or mounted secret files
- Log rotation: set
--log-opt max-size=10m --log-opt max-file=3. Unbounded logs fill disks
Compose
compose.ymlfor local dev only. Production: Kubernetes, ECS, or equivalent- Explicit dependencies:
depends_on+condition: service_healthy - Named volumes for persistent data. Never rely on container filesystem
env_filefor local config. Never commit.envwith real secretsrestart: unless-stoppedfor crash-resilient services- Custom networks per service group. Avoid default bridge
profiles:for optional services (e.g. debug tools, mock servers). Keep default startup lean
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 · 59 lines · 0 tokens per session scan A 462f04203e97
docker is a skill published in the GitHub repository SumonMSelim/agentguard (56 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 819 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
deck-ljg-present
把 outline 1:1 铸成色块大字宣言 deck, 原文不动只做美化。三档主题 black / red / yellow.
data-report
把 CSV/Excel/JSON 数据转成漂亮的可视化报告页.
deck-presenter-mode
【模板: Presenter Mode Deck】 【意图】怕忘词的演讲者专用 deck, 含逐字稿 notes 与 popup teleprompter。 【布局】.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
invoice
标准发票: 寄件/收件 + 明细 + 税 + 总额 + 付款指引.
tcapi
Skill to call Cloud API for Tencent Cloud (腾讯云). Used for cloud automation or resource management. 当用户需要查询、创建、管理腾讯云资源,或执行云 API 自动化操作时触发。优先使用 Octop 自带 venv 中的 tccli,凭证支持全自动 OAuth 登录。.