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 sanjay3290/ai-skills --skill apple-containergit clone --depth 1 https://github.com/sanjay3290/ai-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/sanjay3290/ai-skills/apple-container)<a href="https://agentmods.dev/skills/sanjay3290/ai-skills/apple-container"><img src="https://agentmods.dev/badge/skills/sanjay3290/ai-skills/apple-container/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/sanjay3290/ai-skills/apple-container"><img src="https://agentmods.dev/badge/skills/sanjay3290/ai-skills/apple-container.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 89 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00146 | $0.02057 |
| Opus 5 | $0.00073 | $0.01028 |
| Sonnet 5 | $0.00029 | $0.00411 |
| Haiku 4.5 | $0.00015 | $0.00206 |
Grade A, and why
apple-container 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apple container
Apple's container is an open-source CLI for building, running, and managing OCI/Linux
containers on Apple-silicon Macs. Each container runs inside its own lightweight virtual
machine (backed by the Containerization framework and the Virtualization API), so there is no
shared daemon like Docker — services run per-user via launchd. Images are standard OCI
artifacts, so they interoperate with Docker registries and other OCI tooling. The CLI is
deliberately Docker-like (container run, container build, and image ops under
container image push/pull), but it is a distinct tool: do not assume Docker command paths,
flags, defaults, or daemon behavior carry over (e.g. there is no container images/push/pull
top-level command — image verbs live under container image).
Requirements
- Apple silicon only (M1 or later). Intel Macs are not supported.
- macOS 26 (Tahoe) is the officially supported target. The maintainers do not support
older macOS and typically will not fix issues that can't be reproduced on 26. The binary
still runs on macOS 15 (Sequoia) but with reduced networking: only the single default
subnet is available, and the
container networkgroup and--networkflag error out. macOS-26-gated features are called out throughout the reference files. - Version: this skill documents the 1.0.0 release (the fullest feature set). The
machinegroup,container cp,container export,container prune,container image prune,container registry list, andcontainer system versionwere added in 1.0.0 (not in 0.7.1) — features that postdate 0.7.1 are flagged (1.0.0+) in the reference files. Runcontainer --versionandcontainer <group> --helpto see what your installed build supports. - Install by downloading the signed
.pkginstaller from the project's GitHub releases (apple/container) and running it. Seereferences/concepts.mdfor the full requirements/compatibility matrix and how the VM-per-container model works.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 141 lines · 146 tokens per session scan A e0a9f14532d9
apple-container is a skill published in the GitHub repository sanjay3290/ai-skills (420 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 146 tokens to every session and 2,057 once invoked, about $0.0007 per session on Opus 5. 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
container-orchestration
Docker, Kubernetes, and AWS ECS/Fargate patterns. Triggers on: Dockerfile, docker-compose, kubernetes, k8s, helm, pod, deployment, service, ingress, container, image, ecs, fargate, task definition, ecs service, awsvpc, FARGATESPOT, ALB, ecs vs kubernetes.
docker
Apply when writing or reviewing Dockerfiles, docker compose files, or container build pipelines. Covers layer caching, multi-stage builds, security hardening, and compose conventions.
docker-orchestrator
Docker containerization including multi-stage builds, Docker Compose, security best practices, image optimization, and orchestration patterns. Trigger when users create Dockerfiles, docker-compose.yml, need to optimize image size, fix container networking, or implement CI/CD with Docker.
kubernetes-ops
Kubernetes operations including deployments, services, HPA, RBAC, debugging, Helm charts, and cluster management. Trigger when users deploy to Kubernetes, debug pod issues, configure scaling, set up RBAC, or write Helm charts.
proxmox-lxc
Deploy and configure Proxmox LXC containers for self-hosted services. Always trigger immediately when Mick asks to deploy, set up, or configure a new service on Proxmox, mentions spinning up a container, or needs a systemd service, Cloudflare Tunnel entry, or UniFi static IP assignment. Generate the full stack…
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…