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 CATWILLgh/MAINFRAME --skill mainframe-k3sgit clone --depth 1 https://github.com/CATWILLgh/MAINFRAMEWrote 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/catwillgh/mainframe/mainframe-k3s)<a href="https://agentmods.dev/skills/catwillgh/mainframe/mainframe-k3s"><img src="https://agentmods.dev/badge/skills/catwillgh/mainframe/mainframe-k3s/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/catwillgh/mainframe/mainframe-k3s"><img src="https://agentmods.dev/badge/skills/catwillgh/mainframe/mainframe-k3s.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 | $0.00043 | $0.00617 |
| Opus 5.5 | $0.00017 | $0.00247 |
| Sonnet 5.5 | $0.00009 | $0.00123 |
| Haiku 4.5 | $0.00004 | $0.00062 |
Grade A, and why
mainframe-k3s 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 9d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operate K3s with evidence
Establish the requested result, exact cluster and environment, current K3s versions, datastore, node roles, and relevant workload before choosing an operation. Reuse verified project context and caller authority. A local kubeconfig, loopback address, SSH tunnel, or local CLI does not establish a local or disposable cluster. Verify the API endpoint and node/host identities without printing credentials. If a missing fact changes the safe decision, resolve it rather than assuming a default installation.
Use mainframe-infrastructure for broader infrastructure coordination and its
project map; keep K3s-specific decisions here. Use mainframe-secrets when
credentials are required. This skill does not grant cluster write authority.
Load the relevant method
| Decision | Read |
|---|---|
| Choose topology, provision nodes, join servers or preserve configuration | Topology and installation |
| CNI, DNS, ingress, ServiceLB, registry or connectivity failure | Network and components |
| Access control, hardening, certificates or encryption | Security |
| Persistent data, backup, disaster recovery or rollback | Data and recovery |
| Upgrade, drain, capacity or incident investigation | Operations |
| A flag, version gate, compatibility decision or missing detail | Official source map, then the applicable live documentation |
Load only references needed by the current decision. Check version-sensitive syntax against the installed binary's help and official documentation for that release. Do not treat a documentation example, latest channel, or remembered component version as the target's actual configuration.
Make the result reviewable
For a design, explain the selected topology, failure tolerance, data durability, resource/network assumptions, and alternatives that materially change cost or risk. For a change, identify its configuration owner, exact targets, expected impact, recovery path and bounded verification. Preserve unrelated settings and existing GitOps or configuration-management ownership.
What ships with it
6 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.
- 9d ago First seen · 55 lines · 43 tokens per session scan A 1d0aacd066e5
mainframe-k3s is a skill published in the GitHub repository CATWILLgh/MAINFRAME (2 stars, last pushed 3d ago), licensed MIT. It adds 43 tokens to every session and 617 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 2026-10-07.
Other skills, from other repositories
kubernetes
Deploy, manage, and debug Kubernetes in production — Deployments, Services, Gateway API, Service Mesh (Istio/Linkerd/Cilium), eBPF observability (Cilium Hubble), security hardening (Pod Security Standards, OPA/Kyverno, seccomp, runtime security with Falco/Tetragon), Helm, HPA, PDB, topology spread, and debugging. Use…
deploy-checklist
Pre-deployment verification checklist for Docker Swarm deployments to Azure. Use before deploying to production. Trigger words include deploy, release, production, go live.
openshell-cli
Guide agents through using the OpenShell CLI (openshell) for sandbox management, gateway registration, provider configuration and refresh, profile management, policy iteration, settings, service exposure, BYOC workflows, and attached-provider inference. Covers basic through advanced multi-step workflows. Trigger…
azd-deployment
Deploy containerized frontend + backend applications to Azure Container Apps with remote builds, managed identity, and idempotent infrastructure.
langbot-deploy
Deploy and configure a LangBot instance — Docker / Docker Compose, Kubernetes, the config.yaml model, the Box sandbox runtime, the plugin runtime, and the global API key. Use when installing, deploying, upgrading, or configuring LangBot in production or self-hosted environments. Triggers on "deploy langbot", "langbot…
compute-env-setup
Set up a compute environment on a remote provider so Claude Science jobs can run there. Covers direct SSH/conda hosts, Slurm clusters, container-via-bridge runners, and managed-API providers (Modal, GCP, RunPod). Use when standing up a new provider, porting an env to a different backend, adding a tool that needs its…