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 vinnie357/claude-skills --skill k8s-agent-sandboxgit clone --depth 1 https://github.com/vinnie357/claude-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/vinnie357/claude-skills/k8s-agent-sandbox)<a href="https://agentmods.dev/skills/vinnie357/claude-skills/k8s-agent-sandbox"><img src="https://agentmods.dev/badge/skills/vinnie357/claude-skills/k8s-agent-sandbox/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/vinnie357/claude-skills/k8s-agent-sandbox"><img src="https://agentmods.dev/badge/skills/vinnie357/claude-skills/k8s-agent-sandbox.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Data Exfiltration · line 188 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.02294 |
| Opus 5 | $0.00044 | $0.01147 |
| Sonnet 5 | $0.00018 | $0.00459 |
| Haiku 4.5 | $0.00009 | $0.00229 |
Grade A, and why
k8s-agent-sandbox 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 8d 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.
- Don't claim a sandbox has Anthropic egress without exec'ing into the pod and curl'ing `https://api.anthropic.com/v1/models` (or equivalent). How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
k8s-agent-sandbox
The upstream open-source project kubernetes-sigs/agent-sandbox ships four CRDs that model "give me a per-session, isolated pod for an AI agent and reap it when the session ends." This skill covers the controller, the CRD model, and the lifecycle. Pair with kata-on-kind / kata-on-gke / kina-microvm for the RuntimeClass install and with claude-code-on-sandbox for the workload-side packaging.
What it is
kubernetes-sigs/agent-sandbox is Apache-2.0 (verified at https://github.com/kubernetes-sigs/agent-sandbox). Latest release v0.4.6 (2026-05-14). API group agents.x-k8s.io (core Sandbox) and extensions.agents.x-k8s.io (templates, claims, warm pools). The upstream README example uses v1alpha1; docs/api.md documents v1beta1. Verify the installed CRD version before authoring manifests:
kubectl api-resources | grep -E 'agents\.x-k8s\.io'
GKE ships a managed variant ("Agent Sandbox") that became GA on 2026-05-20. The managed variant is gVisor-only; the upstream open-source project accepts any runtimeClassName including Kata. This skill targets the upstream because Kata (microVM isolation) is the primary use case here.
Install
Upstream (any conformant cluster: kind, k3s, kops, kubeadm, GKE Standard)
VERSION=v0.4.6
kubectl apply -f https://github.com/kubernetes-sigs/agent-sandbox/releases/download/${VERSION}/manifest.yaml
kubectl apply -f https://github.com/kubernetes-sigs/agent-sandbox/releases/download/${VERSION}/extensions.yaml
Two manifests because the project splits the core Sandbox CRD from the higher-level SandboxTemplate / SandboxClaim / SandboxWarmPool extensions. Apply both.
Verify the controller comes up:
kubectl get pods -n agent-sandbox-system
kubectl get crd | grep agents.x-k8s.io
GKE managed (Autopilot)
gcloud beta container clusters create-auto ${CLUSTER_NAME} \
--location=${LOCATION} \
--cluster-version=${CLUSTER_VERSION} \
--enable-agent-sandbox
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.
- 8d ago First seen · 189 lines · 89 tokens per session scan A 77d224999297
k8s-agent-sandbox is a skill published in the GitHub repository vinnie357/claude-skills (25 stars, last pushed 2d ago), licensed MIT. It adds 89 tokens to every session and 2,294 once invoked, about $0.0004 per session on Opus 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 2026-09-03.
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…
compute-env-setup
Set up a reproducible Feynman compute environment for research jobs. Use when a task needs Python/R packages, GPU libraries, containers, Modal, SSH, caches, or managed model runtime setup.
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.
implementing-rbac-hardening-for-kubernetes
Harden Kubernetes Role-Based Access Control by implementing least-privilege policies, auditing role bindings, eliminating cluster-admin sprawl, and integrating external identity providers.
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.