container-manager-swarm

container-manager-swarm is a skill for Claude Code, Codex from Knuckles-Team/container-manager-mcp. It costs 91 tokens per session (1,148 once invoked), scanned A, original, MIT.

A set of controls for managing Docker Swarm clusters through an MCP server. A Swarm cluster runs container services across multiple machines from a manager node.

In plain words
What is it for?
Use it to inspect Swarm nodes and services, initialize or leave a cluster, and create or remove replicated services.
Why use it?
It prevents using the wrong container tools for Kubernetes, Compose, or single-host operations.

Skill for Claude CodeCodex

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

Good fit Use it to inspect Swarm nodes and services, initialize or leave a cluster, and create or remove replicated services.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/knuckles-team/container-manager-mcp/container-manager-swarm
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.

Any agent
npx skills add Knuckles-Team/container-manager-mcp --skill container-manager-swarm
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-swarm

README.md
[![agentmods](https://agentmods.dev/badge/skills/knuckles-team/container-manager-mcp/container-manager-swarm/github.svg)](https://agentmods.dev/skills/knuckles-team/container-manager-mcp/container-manager-swarm)
Your own site
<a href="https://agentmods.dev/skills/knuckles-team/container-manager-mcp/container-manager-swarm"><img src="https://agentmods.dev/badge/skills/knuckles-team/container-manager-mcp/container-manager-swarm/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.

agentmods 80×15 button for container-manager-swarm

Your own site · 80×15
<a href="https://agentmods.dev/skills/knuckles-team/container-manager-mcp/container-manager-swarm"><img src="https://agentmods.dev/badge/skills/knuckles-team/container-manager-mcp/container-manager-swarm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,148 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00091 $0.01148
Opus 5 $0.00046 $0.00574
Sonnet 5 $0.00018 $0.00230
Haiku 4.5 $0.00009 $0.00115

Measured 9d ago against content hash c553b21fa605, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

container-manager-swarm 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.

container_manager_mcp/skills/container-manager-swarm/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Docker Swarm Orchestration

Domain-typed control of a Docker Swarm cluster through the container-manager-mcp server. These operate the cluster control plane (services + nodes) and must be aimed at a swarm manager node.

When to use

  • Inventory swarm nodes (role/availability/status) and services (image/replicas/ports).
  • Create a replicated service, or remove one.
  • Initialize a swarm or make a node leave it.

When NOT to use

  • Single-host container/image lifecycle or exec/logs → container-manager-lifecycle.
  • Plain docker-compose stacks (non-swarm) → cm_compose_operations in the lifecycle skill.
  • Kubernetes → container-manager-kubernetes-operations, not these tools. If the target is a Kubernetes cluster, cm_swarm_operations action=list_nodes / list_services are the wrong tools entirely — they only understand Docker Swarm's control plane, not the Kubernetes API.

Prerequisites & environment

Connect via the mcp-client skill against the container-manager-mcp MCP server. Cluster reads/writes MUST target a swarm manager — pass its host alias.

Variable Required Notes
CONTAINER_MANAGER_TYPE optional docker (Swarm is a Docker feature)
CONTAINER_MANAGER_HOST optional Default manager alias (else pass host explicitly)

Call cm_list_hosts to see aliases; a swarm-manager alias is required for list_nodes / list_services / create_service / remove_service.

Tools & actions

Condensed tool Actions
cm_swarm_operations init_swarm, leave_swarm, list_nodes, list_services, create_service, remove_service

Key parameters

  • host — the swarm manager alias (required for cluster reads/writes).
  • name + image — required to create_service.
  • replicas — desired replica count for create_service.
  • service_id — required to remove_service.
  • advertise_addr — for init_swarm.
  • force — for leave_swarm on a manager.

Read the full file on GitHub · 101 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. 9d ago First seen · 101 lines · 91 tokens per session scan A c553b21fa605

Subscribe to this mod's changes

container-manager-swarm is a skill published in the GitHub repository Knuckles-Team/container-manager-mcp (5 stars, last pushed 12d ago), licensed MIT. It adds 91 tokens to every session and 1,148 once invoked, about $0.0005 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.