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 skills add michaelChe956/Cadence-skills --skill devbox-stackgit clone --depth 1 https://github.com/michaelChe956/Cadence-skillsWrote 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/skills/michaelche956/cadence-skills/devbox-stack)<a href="https://agentmods.dev/skills/michaelche956/cadence-skills/devbox-stack"><img src="https://agentmods.dev/badge/skills/michaelche956/cadence-skills/devbox-stack/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/skills/michaelche956/cadence-skills/devbox-stack"><img src="https://agentmods.dev/badge/skills/michaelche956/cadence-skills/devbox-stack.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 | $0.00089 | $0.01087 |
| Opus 5.5 | $0.00036 | $0.00435 |
| Sonnet 5.5 | $0.00018 | $0.00217 |
| Haiku 4.5 | $0.00009 | $0.00109 |
Grade A, and why
devbox-stack 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 1mo 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.
- 应用侧连通性排障用镜像内已装客户端：`mysql`（mysql-client）、`redis-cli`（redis-tools）；rabbitmq/minio 用端口探活（`nc`/`curl`）； How it starts
The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
devbox 中间件与应用栈运维（唯一入口）
适用性检测（先于一切操作）
test -d /cadence/stack && command -v stack >/dev/null 2>&1 \
|| { echo "devbox-stack 不适用：当前环境非 devbox 容器（无 /cadence/stack 或无 stack 命令）"; exit 0; }
非 devbox 环境（裸机 Linux/macOS 用户）不得伪造 stack 行为或直接操作不存在的工作目录，声明不适用即可静默退出。
硬性规则
- 中间件的启停/重启/日志/配置变更/版本更换/追加/删除，必须通过
stack命令完成（/usr/local/bin/stack，镜像内置），禁止裸写docker compose/docker命令操作/cadence/stack下的服务； stack add与stack rm是/cadence/stack/CHANGES.md留痕的唯一写入口——未留痕的改动不会被启动时模板同步与维护者评估识别，也不要手工编辑 CHANGES.md；- 目录外自加服务必须走「追加协议」三步（设计 4.7）：先
stack ls查官方目录 → 目录内没有才stack add <name> --tpl <最接近的官方模板>→ 完成后告知用户「这是临时配置，建议反馈维护者固化入官方目录」； - 连接串一律使用 compose 服务名（
mysql/redis/rabbitmq/minio），禁止在应用配置里写宿主 localhost——用stack conn <name>获取标准连接串与 application.yaml 片段后原样粘贴； stack rm --purge会删除数据且不可恢复：必须先向用户复述后果（服务名+数据位置）并获得明确确认后才执行；- enable/disable 修改的是
/cadence/stack/.env的COMPOSE_PROFILES——容器内与宿主侧是同一 compose 项目（name: cadence），任一侧生效即全局生效。
命令速查（引用镜像内已装命令，本 skill 不复制任何脚本）
| 场景 | 命令 | 说明 |
|---|---|---|
| 服务运行状态 | stack status |
compose ps |
| 目录与启用清单 | stack ls |
官方目录 + 当前 COMPOSE_PROFILES + CHANGES.md 摘要 |
| 启用 | stack enable rabbitmq（或 stack enable mq） |
写 COMPOSE_PROFILES 并尝试拉起 |
| 停用 | stack disable mq |
移出 COMPOSE_PROFILES；默认服务（mysql/redis）仅 stop 保留数据 |
| 重启 | stack restart mysql |
配置改动后生效手段（改 /cadence/stack/catalog/<svc>/conf 后重启） |
| 日志 | stack logs mysql |
--tail 100 跟随 |
| 连接串 | stack conn mysql |
标准连接串 + Spring 片段 |
| 目录外自加 | stack add kafka --tpl rabbitmq |
参数化生成 service 骨架+自动留痕 |
| 删除 | stack rm kafka（--purge 连数据） |
二次确认 |
| 本地应用 | stack app run demo mvn spring-boot:run（同组：app stop/logs/port <name>） |
run=后台起（pid/log 落 stack/../run/app/）、port=端口探活带超时；spring-boot/vite 起停不经 docker |
排障与边界
- 应用侧连通性排障用镜像内已装客户端：
mysql（mysql-client）、redis-cli（redis-tools）；rabbitmq/minio 用端口探活（nc/curl）； - docker.sock ≈ 宿主 root 等价（设计 4.7 安全口径）：仅用于本项目中间件运维，不得操作用户其他容器；
- 建库建表走项目自身 Flyway/JPA；无此能力的项目在容器内执行 SQL 前先
stack conn mysql核对连接信息。
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.
- 1mo ago First seen · 46 lines · 89 tokens per session scan A 7956ad21c1f4
devbox-stack is a skill published in the GitHub repository michaelChe956/Cadence-skills (10 stars, last pushed 1mo ago), licensed MIT. It adds 89 tokens to every session and 1,087 once invoked, about $0.0004 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 2026-09-12.
Other skills, from other repositories
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
bdd-container-update
Update the BDD test container image when its dependencies or runtime change. Determines version bump (major vs minor vs patch), rebuilds the Docker image, pushes to GitLab registry, and updates the image tag in starttest.sh. Test source (tests/, features/, scripts/, data/, conftest.py) is bind-mounted from the host…
securing-kubernetes-on-cloud
This skill covers hardening managed Kubernetes clusters on EKS, AKS, and GKE by implementing Pod Security Standards, network policies, workload identity, RBAC scoping, image admission controls, and runtime security monitoring. It addresses cloud-specific security features including IRSA for EKS, Workload Identity for…
detecting-privilege-escalation-in-kubernetes-pods
Detect and prevent privilege escalation in Kubernetes pods by monitoring security contexts, capabilities, and syscall patterns with Falco and OPA policies.
docker-socket-mount
Docker / containerd socket mounted into a container → host RCE. Common in CI runners, GitOps controllers (ArgoCD, Flux), and 'Docker-in-Docker' setups. Single-command escape via docker run --rm --privileged -v /:/host alpine chroot /host.
k8s-networking
Kubernetes networking management for services, ingresses, endpoints, and network policies. Use when configuring connectivity, load balancing, or network isolation.