container-manager-multi-context

container-manager-multi-context is a skill for Claude Code, Codex from Knuckles-Team/container-manager-mcp. It costs 118 tokens per session (2,050 once invoked), scanned A, original, MIT.

A control interface for managing several container environments at once, including Kubernetes clusters, Docker hosts, Podman hosts, and Docker Swarm.

In plain words
What is it for?
Use it to check available environments, run container operations in a named context, compare staging and production, or perform selected Kubernetes actions across multiple clusters.
Why use it?
It removes the need to reconnect separately to each environment when comparing systems, migrating workloads, or repeating an operation across them.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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 skills/knuckles-team/container-manager-mcp/container-manager-multi-context
Any agent
npx skills add Knuckles-Team/container-manager-mcp --skill container-manager-multi-context
Clone the repo
git clone --depth 1 https://github.com/Knuckles-Team/container-manager-mcp

Made for: Claude Code, Codex.

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 container-manager-multi-context

README.md
[![agentmods](https://agentmods.dev/badge/skills/knuckles-team/container-manager-mcp/container-manager-multi-context.svg)](https://agentmods.dev/skills/knuckles-team/container-manager-mcp/container-manager-multi-context)
Your own site
<a href="https://agentmods.dev/skills/knuckles-team/container-manager-mcp/container-manager-multi-context"><img src="https://agentmods.dev/badge/skills/knuckles-team/container-manager-mcp/container-manager-multi-context.svg" alt="Measured on agentmods" height="20"></a>
Per session 118 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,050 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 $0.00118 $0.02050
Opus 5 $0.00059 $0.01025
Sonnet 5 $0.00024 $0.00410
Haiku 4.5 $0.00012 $0.00205

Measured 6d ago against content hash ab9a27b7e6dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

container-manager-multi-context 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 6d 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.

container_manager_mcp/skills/container-manager-multi-context/SKILL.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multi-Context Container Management

Domain-typed control across a pool of backends and contexts — Kubernetes clusters, Docker hosts, Podman, and Swarm managers — through the single cm_multi_context tool on the container-manager-mcp server. Each call selects a backend (and optional context) so one MCP server can drive many environments without reconnecting. Best suited to cross-cluster comparisons, staged migrations, and fan-out operations.

When to use

  • Enumerate every configured backend/context and its health in one call (list_contexts).
  • Run the same container/image/volume/network/service verb against a specific named context without re-authenticating per call.
  • Compare state across contexts (e.g. staging vs prod Kubernetes clusters, or two Docker hosts) before/during a migration.
  • Kubernetes-specific fan-out: list pods/deployments or scale a deployment in a named context + namespace.

When NOT to use

  • A single, already-known backend → use the themed skill directly: container-manager-lifecycle (Docker/Podman), container-manager-swarm, container-manager-kubernetes-operations (full k8s surface — cm_multi_context's Kubernetes actions are a narrow subset: containers/images/volumes/networks/ services/pods/deployments only, not the full cm_k8s_* themed surface). container-manager-podman-operations (pods/checkpoint/kube-yaml — not exposed here).
  • First-time setup of K8S_CONTEXTS/DOCKER_CONTEXTS/SWARM_CONTEXTS → see the Walkthrough below, then container-manager-config-walkthrough.

Prerequisites & environment

Connect via the mcp-client skill against the container-manager-mcp MCP server. Multi-context mode is enabled by configuring one or more context-pool env vars (or MULTI_CONTEXT_MODE=true); each pool var is a ;-separated list of name=value pairs.

Variable Required Notes
MULTI_CONTEXT_MODE optional Forces multi-context mode even with a single context configured
K8S_CONTEXTS optional "prod=prod-ctx;staging=staging-ctx" — kubeconfig context names
DEFAULT_K8S_CONTEXT optional Which K8S_CONTEXTS entry is used when context is omitted; else the first one
DOCKER_CONTEXTS optional "local=;remote1=<tunnel-manager-host-alias>" — Docker host aliases
DEFAULT_DOCKER_CONTEXT optional Default Docker context name
SWARM_CONTEXTS optional "cluster1=<manager-host-alias>" — Swarm manager host aliases
DEFAULT_SWARM_CONTEXT optional Default Swarm context name
PODMAN_ENABLED optional Default true; local Podman only (no multi-context Podman pool)
MULTI_CONTEXT_MAX_WORKERS optional Thread pool size for fan-out, default 8
MULTICONTEXTTOOL optional Tool toggle, default true; set false to hide cm_multi_context

Read the full file on GitHub · 154 lines

Files

What ships with it

1 file 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.

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. 6d ago First seen · 154 lines · 118 tokens per session scan A ab9a27b7e6dc

Subscribe to this mod's changes

container-manager-multi-context is a skill published in the GitHub repository Knuckles-Team/container-manager-mcp (5 stars, last pushed 8d ago), licensed MIT. It adds 118 tokens to every session and 2,050 once invoked, about $0.0006 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 2026-08-31.