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 agentmods add skills/knuckles-team/container-manager-mcp/container-manager-multi-contextnpx skills add Knuckles-Team/container-manager-mcp --skill container-manager-multi-contextgit clone --depth 1 https://github.com/Knuckles-Team/container-manager-mcpWrote 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/knuckles-team/container-manager-mcp/container-manager-multi-context)<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>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 | $0.00118 | $0.02050 |
| Opus 5 | $0.00059 | $0.01025 |
| Sonnet 5 | $0.00024 | $0.00410 |
| Haiku 4.5 | $0.00012 | $0.00205 |
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.
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 fullcm_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, thencontainer-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 |
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.
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.
- 6d ago First seen · 154 lines · 118 tokens per session scan A ab9a27b7e6dc
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.
Other skills, from other repositories
docker
Use when authoring or auditing a Dockerfile, shrinking a bloated image, hardening a container that runs as root, picking a base image, or wiring a Compose dev loop with hot reload. NOT CI builds or deploy-to-host (that is deployment), NOT k8s autoscaling (that is scaling), NOT app-level injection or secrets-in-code…
docker-compose-generator
Generate Docker Compose configurations for development environments - auto-detect project stack, configure services with dependencies, volumes, networking, and health checks.
DevOps & Deployment
CI/CD pipelines, containerization, Kubernetes, and infrastructure as code patterns.
buildah
Buildah OCI container image builder reference. Build container images without Docker daemon. Covers Containerfile builds, scripted builds with shell commands, direct filesystem mount, rootless operation, multi-arch manifests, and CI/CD integration.
agent-sandbox
Agent skill for sandbox - invoke with $agent-sandbox.
implementing-container-image-minimal-base-with-distroless
Reduce container attack surface by building application images on Google distroless base images that contain only the application runtime with no shell, package manager, or unnecessary OS utilities.