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-mcp-developmentgit 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-mcp-development)<a href="https://agentmods.dev/skills/knuckles-team/container-manager-mcp/container-manager-mcp-development"><img src="https://agentmods.dev/badge/skills/knuckles-team/container-manager-mcp/container-manager-mcp-development/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-mcp-development"><img src="https://agentmods.dev/badge/skills/knuckles-team/container-manager-mcp/container-manager-mcp-development.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 | $0.00057 | $0.02052 |
| Opus 5.5 | $0.00023 | $0.00821 |
| Sonnet 5.5 | $0.00011 | $0.00410 |
| Haiku 4.5 | $0.00006 | $0.00205 |
Grade A, and why
container-manager-mcp-development 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 today.
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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
container-manager-mcp development
This skill is the repository contract for the container-manager-mcp connector. The
package owns the Docker, Podman, Swarm, and Kubernetes calls and their MCP content;
transport, release rendering, generated ontology artifacts, and shared validation
come from agent-connector-sdk and pipelines.
Repository workflow
- Start from a real worktree based on
origin/main; keep the canonical checkout and other worktrees untouched. - Find the owning row with
git grep -n "<term>" -- specsbefore changing behavior. - Keep changes in the connector boundary. Use the SDK for MCP construction, governed HTTP, credentials, TLS, and packaged content discovery.
- Run the narrow test or gate that proves the changed behavior, then run
uvx pre-commit run --all-filesbefore opening a PR. - Let the shared pipelines render Docker/compose files and generate connector ontology artifacts during release. Those generated files are not committed here.
Container-manager checks
Use the locked project environment (uv sync --locked) when it is already available.
Focused tests can select one backend or tool family, for example:
uv run --frozen pytest -q tests/test_call_context.py
uv run --frozen pytest -q tests/test_mcp_server.py
Do not call a real container engine or Kubernetes cluster from a unit test. Mock the manager boundary and prove context selection, refusal, and serialization. Keep credentials, hostnames, kubeconfigs, and private paths out of fixtures and receipts.
Rapid delivery: the 5-minute contract
Specs are already designed. The work is implementation, delivered in very small, continuously landed slices.
Extend first (anti-sprawl)
- Before any code change, find the spec row that owns the behavior:
git grep -n "<term>" -- specs. Cite its ID in the commitSpec:trailer. - Before any new spec text, extend the owning spec: a child row (
R012.4), a new rollup at the end of that spec, or a dated entry in theplan.mdsection "Amendments". Create a new spec only for a capability that no spec owns, and record the search in "Why a new spec". - Audits, reviews, gap analyses and carry-overs never get a spec directory. Their findings land in the spec that owns the row; a finding against another repository lands in that repository's spec.
- Before any new function, module, planner, selector or store, search for the existing one and reuse it. A second implementation of an owned capability is a defect, not a delivery.
- The rules are in
specs/README.md. Thespec-standardgate enforces the names, file set, title and index.
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.
- today First seen · 112 lines · 57 tokens per session scan A f3f4548289f4
container-manager-mcp-development is a skill published in the GitHub repository Knuckles-Team/container-manager-mcp (6 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 2,052 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-27.
Other skills, from other repositories
docker-compose-generator
Generate Docker Compose configurations for development environments - auto-detect project stack, configure services with dependencies, volumes, networking, and health checks.
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…
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…
relay-docker
Build production-ready Dockerfiles with multi-stage builds, security hardening, and docker-compose for local dev. Use when asked to "create Dockerfile", "optimize container", or "dockerize this".
docker-compose
Containerização com Docker e Docker Compose: configuração para desenvolvimento com hot reload, produção com health checks, multi-stage builds, Docker networks e gestão de secrets e variáveis de ambiente.