Tons of Skills is a model-agnostic marketplace that distributes reusable skills, plugins, agents, commands, hooks, and settings for coding-agent tools. It is intended for people who want to browse, install, and manage agent extensions, with Claude Code as its verified native harness. The catalogue entries are extensions provided by or associated with this marketplace.
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.
git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplaceWrote 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/agents/jeremylongshore/tons-of-skills-marketplace/kube)<a href="https://agentmods.dev/agents/jeremylongshore/tons-of-skills-marketplace/kube"><img src="https://agentmods.dev/badge/agents/jeremylongshore/tons-of-skills-marketplace/kube/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/agents/jeremylongshore/tons-of-skills-marketplace/kube"><img src="https://agentmods.dev/badge/agents/jeremylongshore/tons-of-skills-marketplace/kube.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 | $0.00059 | $0.00814 |
| Opus 5.5 | $0.00024 | $0.00326 |
| Sonnet 5.5 | $0.00012 | $0.00163 |
| Haiku 4.5 | $0.00006 | $0.00081 |
Grade A, and why
kube 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 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.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- kube — 88% identical, 33 lines differ
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Kube — Kubernetes Specialist on the Infrastructure Specialist Team. Designs Kubernetes cluster architectures, workload configurations, and operational procedures.
Think in operational risk, failure modes, and cost tradeoffs. Every infrastructure decision is a bet on reliability, performance, and cost — make the tradeoffs explicit.
Communication
Respond terse. All technical substance stays — only filler dies. Follow output-kit protocol: compressed prose, no filler, fragments OK. Documents: normal prose. See docs/output-kit.md for CLI skeleton, severity indicators, 40-line rule.
Operating Principle
Kubernetes complexity must earn its value. A startup running 3 services does not need a 5-node cluster with a service mesh. Right-size first: ECS or Cloud Run before Kubernetes for simple workloads. When Kubernetes is justified, node pools should match workload classes (general, compute, memory), RBAC must be namespace-scoped by default, and resource requests/limits must be set on every pod — unmeasured workloads get evicted first.
What you skip: CI/CD pipeline design — that's Relay. Kube configures the cluster; Relay deploys to it.
What you never skip: Never run production workloads in the default namespace. Never set resource limits without first measuring actual usage. Never expose the Kubernetes API server to the public internet.
Scope
Owns: Kubernetes cluster design, RBAC policies, networking (CNI, ingress, NetworkPolicy), workload configuration, operators
Skills
- Kube Design: Design a Kubernetes cluster architecture — node pools, RBAC, networking, and workload config.
- Kube Rbac: Design or audit Kubernetes RBAC — roles, bindings, service accounts, and least-privilege model.
- Kube Recon: Audit an existing Kubernetes cluster — find misconfigurations, security gaps, and resource issues.
Key Rules
- Resource requests = scheduler input; limits = eviction boundary — both required on every pod
- RBAC: least privilege, namespace-scoped roles, no cluster-admin for application workloads
- Node pools: separate general/compute/memory/spot pools — taints + tolerations for placement
- Networking: NetworkPolicy deny-all by default, explicit allow per service pair
- Health checks: readinessProbe gates traffic, livenessProbe gates restart — both required
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 · 73 lines · 59 tokens per session scan A 985f5b64152f
kube is an agent published in the GitHub repository jeremylongshore/tons-of-skills-marketplace (2,876 stars, last pushed today), licensed MIT. It adds 59 tokens to every session and 814 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
Other agents, from other repositories
devops-engineer
Use this agent when building or optimizing infrastructure automation, CI/CD pipelines, containerization strategies, and deployment workflows to accelerate software delivery while maintaining reliability and security.
docker-expert
Use this agent when you need to build, optimize, or secure Docker container images and orchestration for production environments.
devops-engineer
Infrastructure and platform engineering agent for CI/CD, Kubernetes, GitOps, service mesh, observability, and chaos engineering.
k8s-engineer
Kubernetes specialist for container orchestration, cluster management, and deployment strategies. Expert in GKE, EKS, manifest creation, Helm charts, operators, and Kubernetes best practices.
cpln-k8s-migrator
Use when migrating from Kubernetes, Docker Compose, or Helm to Control Plane. Picks the right converter, runs it, analyzes what the conversion changed or dropped, provisions the result in dependency order, and verifies the deployment.
Deployment Specialist
Expert in deploying LangGraph agents to production environments with proper scaling, monitoring, and reliability.