agentmods.dev

deploy

deploy is a command for Claude Code from kubestellar/kubestellar-mcp. It costs 0 tokens per session (300 once invoked), scanned A, original, Apache-2.0.

A deployment command for sending an application to one or more Kubernetes clusters, which are groups of machines that run containerized applications.

In plain words
What is it for?
Use it to deploy Kubernetes YAML to chosen or matching clusters, select clusters by resources such as GPUs or memory, and preview changes with a dry run.
Why use it?
It finds suitable clusters, applies the deployment manifest, and reports the result for each target instead of requiring each cluster to be handled separately.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

not rated 2 today A scan 0 tokens original Apache-2.0
View the source file kubestellar/kubestellar-mcp
Install

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.

agentmods
npx agentmods add commands/kubestellar/kubestellar-mcp/deploy
Clone the repo
git clone --depth 1 https://github.com/kubestellar/kubestellar-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for deploy

README.md
[![agentmods](https://agentmods.dev/badge/commands/kubestellar/kubestellar-mcp/deploy.svg)](https://agentmods.dev/commands/kubestellar/kubestellar-mcp/deploy)
Your own site
<a href="https://agentmods.dev/commands/kubestellar/kubestellar-mcp/deploy"><img src="https://agentmods.dev/badge/commands/kubestellar/kubestellar-mcp/deploy.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 300 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00300
Opus 5 $0.00000 $0.00150
Sonnet 5 $0.00000 $0.00060
Haiku 4.5 $0.00000 $0.00030

Measured 5d ago against content hash 3e90fda2eb17, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

deploy 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 5d 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.

commands/deploy.md · 44 lines

What it actually says

Deploy

Deploy an app to multiple clusters with smart placement.

Usage

Deploy a workload to clusters. You can specify target clusters explicitly or let kubestellar-deploy find matching clusters based on requirements.

Examples

  • "Deploy this nginx deployment to all clusters"
  • "Deploy my ML model to clusters with GPUs"
  • "Deploy this app to clusters with at least 16Gi memory"
  • "Do a dry run of deploying this manifest"

What it does

  1. Finds clusters matching your requirements (or uses all clusters)
  2. Applies the manifest to each target cluster
  3. Reports success/failure per cluster

MCP Tools Used

  • deploy_app - Deploy an app to clusters
  • find_clusters_for_workload - Find clusters matching requirements
  • list_cluster_capabilities - See what each cluster can run

Implementation

Use the deploy_app tool with:

  • manifest: The Kubernetes YAML manifest
  • clusters: Optional list of target clusters
  • gpu_type: Optional GPU type requirement (e.g., "nvidia.com/gpu")
  • min_gpu: Optional minimum GPU count
  • dry_run: Set to true to preview without applying

Smart Placement

If you don't specify clusters, kubestellar-deploy can:

  • Deploy to all clusters
  • Filter to clusters with specific GPU types
  • Filter to clusters with minimum CPU/memory
  • Filter to clusters with specific node labels
Changes

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.

  1. 5d ago First seen · 44 lines · 0 tokens per session scan A 3e90fda2eb17

Subscribe to this mod's changes

deploy is a command published in the GitHub repository kubestellar/kubestellar-mcp (2 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 300 tokens. 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 2026-08-31.

CloudContainersDevOps and cloud
Related

Other commands, from other repositories

create-docker-mcp-tunnel

Stand up an Anthropic MCP tunnel locally with Docker Compose so Claude can call a private MCP server (manual-credentials quickstart).

anthropics/claude-plugins-official · 26 tokens

health

Check remote dev environment health dashboard.

bybren-llc/safe-agentic-workflow · 0 tokens

deploy

Build, test, deploy with staged rollout.

dinhnguyenngoc/spec-driven-claude-code · 10 tokens

k8s-manifest

Generate production-ready Kubernetes manifests for the current application.

rohitg00/awesome-claude-code-toolkit · 0 tokens

cisco-isovalent-platform-setup

Install the Isovalent platform on Kubernetes (Cilium CNI, Hubble observability, Tetragon eBPF runtime security) in either OSS or Enterprise edition. Renders Helm values and install/upgrade scripts; this is the platform install prerequisite for the Splunk Observability + Splunk Platform integration done by…

chambear2809/splunk-cisco-skills · 0 tokens

extract-infrastructure

Extract Azure infrastructure and generate Docker Compose stack for local development.

JosiahSiegel/claude-plugin-marketplace · 11 tokens