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 Knuckles-Team/container-manager-mcp --skill container-manager-kg-ingestiongit 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-kg-ingestion)<a href="https://agentmods.dev/skills/knuckles-team/container-manager-mcp/container-manager-kg-ingestion"><img src="https://agentmods.dev/badge/skills/knuckles-team/container-manager-mcp/container-manager-kg-ingestion/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/knuckles-team/container-manager-mcp/container-manager-kg-ingestion"><img src="https://agentmods.dev/badge/skills/knuckles-team/container-manager-mcp/container-manager-kg-ingestion.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 | $0.00116 | $0.01694 |
| Opus 5 | $0.00058 | $0.00847 |
| Sonnet 5 | $0.00023 | $0.00339 |
| Haiku 4.5 | $0.00012 | $0.00169 |
Grade A, and why
container-manager-kg-ingestion 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 11d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Container Inventory → Knowledge Graph
Push a host's live container inventory into the ONE epistemic-graph knowledge graph as
typed OWL nodes, natively from the container-manager-mcp server. Best-effort and
engine-guarded: with no reachable KG engine the tool still lists the inventory and reports
ingested: null per modality.
When to use
- Record the current containers/images/volumes/networks (and swarm services/nodes) of a host into the KG for later querying, drift detection, or cross-source joins.
- Record a Kubernetes cluster's live pods/deployments/namespaces/native services into
the KG (when
CONTAINER_MANAGER_TYPE=kubernetes). - Refresh the KG snapshot after a deploy or before an audit.
When NOT to use
- Operating containers (start/stop/logs/exec) →
container-manager-lifecycle. - Managing swarm services/nodes →
container-manager-swarm. - Generic KG queries → the graph-os
graph_query/graph_searchsurface.
Prerequisites & environment
Connect via the mcp-client skill against the container-manager-mcp MCP server.
A reachable Docker/Podman engine is required; a reachable epistemic-graph engine is
optional (ingestion no-ops cleanly without one).
| Variable | Required | Notes |
|---|---|---|
CONTAINER_MANAGER_TYPE |
optional | docker / podman; auto-detected |
CONTAINER_MANAGER_HOST |
optional | Default host alias (else LOCAL socket) |
The typed nodes match container_manager_mcp.ontology (container.ttl), federated into
the hub under http://knuckles.team/kg/container (reusing the shared :Container,
:ContainerImage, :ContainerStack, :Host classes).
Tools & actions
| Tool | Modalities |
|---|---|
cm_ingest_inventory |
all, containers, images, volumes, networks, services, nodes, pods, deployments, namespaces, k8s_services |
Kubernetes modalities (
pods,deployments,namespaces,k8s_services): live.cm_ingest_inventorysnapshots a Kubernetes cluster into:Pod/:Deployment/:Namespace/:K8sServicetyped nodes (mirroring the containers/images pattern) alongside the Docker/Podman/Swarm modalities.allsweeps them automatically when the active manager is a Kubernetes manager (manager_type=kubernetes); on a Docker/Swarm managerallstays Docker/Swarm-scoped. Call a single k8s modality directly, e.g.cm_ingest_inventory action=... modality=pods manager_type=kubernetes.
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.
- 11d ago First seen · 127 lines · 116 tokens per session scan A 28f066d386db
container-manager-kg-ingestion is a skill published in the GitHub repository Knuckles-Team/container-manager-mcp (5 stars, last pushed 13d ago), licensed MIT. It adds 116 tokens to every session and 1,694 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.
coolify
Use when self-hosting apps and databases with Coolify on a VPS you own — install, first-admin lockdown, Git-to-deploy (Nixpacks/Dockerfile/compose), managed Postgres/Redis, scheduled S3 backups, domains + auto-SSL. NOT a PaaS someone else runs (that is railway), NOT sizing/hardening the box (that is hetzner), NOT…
deployment
Use when taking an app from source to live: choosing the deploy target from requirements (Hetzner+Coolify vs Vercel vs a third), then wiring container → CI → registry → host with build secrets, healthchecks and rollback. NOT one platform's mechanics (that is coolify, vercel, railway, render), NOT the Dockerfile alone…
performing-container-image-hardening
This skill covers hardening container images by minimizing attack surface, removing unnecessary packages, implementing multi-stage builds, configuring non-root users, and applying CIS Docker Benchmark recommendations to produce secure production-ready images.
dev-environment-setup
Use this skill as a router/index when the user faces a development environment question that spans multiple domains: containers (Docker/Podman), WSL2 on Windows, office-skill dependencies (DOCX/PDF/XLSX/ PPTX), or system tools (LibreOffice/Poppler/Pandoc/Tesseract). For pure Python issues use python-runtime skill; for…