Containerization Assist is an MCP server that helps create, inspect, and deploy Docker containers and Kubernetes applications. Developers use it for Dockerfile generation, image scanning, Kubernetes manifest creation, security checks, policy-based configuration, and deployment workflows.
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 Azure/containerization-assist --skill analyze-repogit clone --depth 1 https://github.com/Azure/containerization-assistWrote 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/azure/containerization-assist/analyze-repo)<a href="https://agentmods.dev/skills/azure/containerization-assist/analyze-repo"><img src="https://agentmods.dev/badge/skills/azure/containerization-assist/analyze-repo/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/azure/containerization-assist/analyze-repo"><img src="https://agentmods.dev/badge/skills/azure/containerization-assist/analyze-repo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.03521 |
| Opus 5 | $0.00000 | $0.01760 |
| Sonnet 5 | $0.00000 | $0.00704 |
| Haiku 4.5 | $0.00000 | $0.00352 |
Grade A, and why
analyze-repo 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 10d 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 — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze Repository
Produce a structured stack report for a repository by reading its manifest
files. This is a deterministic, read-only procedure — do not guess, do
not invoke language models against source code, and do not modify anything.
Use file-reading tools available in the chat environment (read_file, file
search, directory listing) to perform every step.
Inputs
| Field | Required | Description |
|---|---|---|
repositoryPath |
yes | Absolute path. Default to the workspace root if the user did not specify one. Normalize Windows paths to forward slashes. |
If the user provided a modules[] array, skip detection and use it verbatim.
Otherwise, run the full procedure.
Procedure
Step 1 — Walk the repository
- Start at
repositoryPath, recurse to maximum depth 3. - Skip these directory names at any depth:
node_modules,.git,.vscode,.idea,dist,build,target,bin,obj. - Cap total files scanned at 100. Stop once you reach this.
- Record a flat directory tree (first 30 entries) for context.
Step 2 — Identify config files
Match file basenames against this set (case-sensitive):
| Ecosystem | Files |
|---|---|
| Node | package.json |
| Java – Maven | pom.xml |
| Java – Gradle | build.gradle, build.gradle.kts |
| Python | requirements.txt, pyproject.toml |
| Rust | Cargo.toml |
| .NET | *.csproj, *.fsproj, *.vbproj |
| Go | go.mod |
| PHP | composer.json |
| Ruby | Gemfile |
| Container | Dockerfile, docker-compose.yml, docker-compose.yaml |
| Spring | application.properties, application.yml, application.yaml |
| Env templates | .env.example, .env.sample, .env.template |
Read each match, truncate at 1000 characters, and remember the (path, content) pair.
Step 3 — Parse each config
Per file type, extract the following fields. If a field is absent, leave it unset — do not invent.
| File | Extract |
|---|---|
package.json |
language = typescript if typescript in devDeps or tsconfig.json exists, else javascript; framework from deps (express, next, nestjs, fastify, koa, react, etc.); frameworkVersion from dep range; dependencies = keys of dependencies + devDependencies; languageVersion from engines.node; entryPoint from main or scripts.start; ports from any literal port in scripts.start. buildSystem.type = npm / yarn / pnpm based on lockfile sibling. |
pom.xml |
language = java; framework from <artifactId> patterns (spring-boot-starter* → Spring Boot); languageVersion from <maven.compiler.source> or <java.version>; dependencies = <groupId>:<artifactId> list; buildSystem.type = maven. |
build.gradle[.kts] |
language = java (or kotlin if .kts + kotlin plugin); framework from plugins { id 'org.springframework.boot' } etc.; languageVersion from sourceCompatibility / jvmToolchain; dependencies = the strings inside implementation '…' / api '…'; buildSystem.type = gradle. |
requirements.txt |
language = python; dependencies = one per line stripped of version pin; framework from deps (flask, django, fastapi, tornado); buildSystem.type = pip. |
pyproject.toml |
language = python; read [project] dependencies, [tool.poetry.dependencies], or [tool.pdm]; framework from deps; languageVersion from requires-python; buildSystem.type = poetry / pdm / setuptools based on [build-system].build-backend. |
Cargo.toml |
language = rust; framework from deps (actix-web, axum, rocket, tonic); dependencies = keys of [dependencies]; entryPoint = [package].name; buildSystem.type = cargo. |
*.csproj |
language = dotnet; languageVersion from <TargetFramework>; framework = ASP.NET Core if any Microsoft.AspNetCore.* package ref; dependencies = PackageReference Include="…" values; buildSystem.type = dotnet. |
go.mod |
language = go; languageVersion from go <version> line; dependencies = require (...) module list; framework from deps (gin-gonic/gin, labstack/echo, fiber, chi); buildSystem.type = go-modules. |
composer.json |
language = other (PHP); dependencies = keys of require; framework from deps (laravel/framework, symfony/*); buildSystem.type = composer. |
Gemfile |
language = other (Ruby); dependencies = gem "…" names; framework from deps (rails, sinatra); buildSystem.type = bundler. |
Dockerfile |
Note its existence — do NOT treat as a module config; affects "recommended next step". |
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.
- 10d ago First seen · 248 lines · 0 tokens per session scan A bcefb5fdb7f9
analyze-repo is a skill published in the GitHub repository Azure/containerization-assist (41 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,521 tokens. 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 2026-08-30.
Other skills, from other repositories
azd-deployment
Deploy containerized frontend + backend applications to Azure Container Apps with remote builds, managed identity, and idempotent infrastructure.
openshell-cli
Guide agents through using the OpenShell CLI (openshell) for sandbox management, gateway registration, provider configuration and refresh, policy iteration, settings, service exposure, BYOC workflows, and inference routing. Covers basic through advanced multi-step workflows. Trigger keywords - openshell, sandbox…
langbot-deploy
Deploy and configure a LangBot instance — Docker / Docker Compose, Kubernetes, the config.yaml model, the Box sandbox runtime, the plugin runtime, and the global API key. Use when installing, deploying, upgrading, or configuring LangBot in production or self-hosted environments. Triggers on "deploy langbot", "langbot…
compute-env-setup
Set up a compute environment on a remote provider so Claude Science jobs can run there. Covers direct SSH/conda hosts, Slurm clusters, container-via-bridge runners, and managed-API providers (Modal, GCP, RunPod). Use when standing up a new provider, porting an env to a different backend, adding a tool that needs its…
azure-cloud-migrate
Assess and migrate cross-cloud workloads to Azure with reports and code conversion. Supports Lambda→Functions, Beanstalk/Heroku/App Engine→App Service, Fargate/Kubernetes/Cloud Run/Spring Boot→Container Apps. WHEN: migrate Lambda to Functions, AWS to Azure, migrate Beanstalk, migrate Heroku, migrate App Engine, Cloud…
atmos-helmfile
Helmfile orchestration: sync/apply/destroy/diff, Kubernetes deployments, varfile generation, EKS integration, source management.