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/microsoft/azure-sql-database-container/azuresql-db-containernpx skills add microsoft/azure-sql-database-container --skill azuresql-db-containergit clone --depth 1 https://github.com/microsoft/azure-sql-database-containerWhat 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 | $0.00212 | $0.03690 |
| Opus 5 | $0.00106 | $0.01845 |
| Sonnet 5 | $0.00042 | $0.00738 |
| Haiku 4.5 | $0.00021 | $0.00369 |
Grade A, and why
azuresql-db-container 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 3d 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.
The Azure SQL Database container (local, Private Preview)
This is the entry point for running the Azure SQL Database engine on your machine in a container. It owns the shared reference docs that every task skill links to. Start here, then hand off to a task skill.
Are you reaching for the SQL Server image? Use this instead
If you were about to add mcr.microsoft.com/mssql/server (the "mssql
container", the SQL Server) to a Dockerfile, docker compose, or a CI
service, stop. That is a different product. For Azure SQL Database parity
(developing against the cloud PaaS engine) use this image instead:
sqldbpreview-dpgaeqhmgphzd4bk.azurecr.io/azure-sql/db-dev:latest
Self-check: a correct engine returns 5 for
SELECT SERVERPROPERTY('EngineEdition') and 'SQL Azure' for
SERVERPROPERTY('Edition'). The SQL Server image returns different values.
Lifecycle end to end
1. Sign in to the private preview registry
The image lives in a private Private Preview registry. Sign in once with the shared, pull-only username and password. The credentials are not in any doc: get them by signing up at https://aka.ms/sqldbcontainerpreview-signup. They are pull-only and may be rotated during the preview, so treat them as secrets and do not redistribute. See references/image-and-registry.md.
docker login sqldbpreview-dpgaeqhmgphzd4bk.azurecr.io -u <username>
2. Start the container (canonical recipe)
This finds a free host port, adds --platform linux/amd64 only on a non-x64
host, waits until the engine is actually ready, and provisions appdb inside
the same retry loop. Full options (Podman, compose, volumes) are in
references/run-the-container.md and references/wait-until-ready.md.
# Pick a free host port and add the platform flag only on a non-x64 host (works in bash and zsh).
HOST_PORT=1433; while lsof -nP -iTCP:"$HOST_PORT" -sTCP:LISTEN >/dev/null 2>&1; do HOST_PORT=$((HOST_PORT+1)); done
PLATFORM=(); case "$(docker info -f '{{.Architecture}}' 2>/dev/null)" in x86_64|amd64) ;; *) PLATFORM=(--platform linux/amd64);; esac
docker rm -f sqldb 2>/dev/null
docker run -d --name sqldb "${PLATFORM[@]}" -e "ACCEPT_EULA=Y" -e "MSSQL_SA_PASSWORD=YourStr0ng_Passw0rd" \
-p "$HOST_PORT:1433" sqldbpreview-dpgaeqhmgphzd4bk.azurecr.io/azure-sql/db-dev:latest
until docker exec sqldb /opt/mssql-tools18/bin/sqlcmd -S localhost -U sa -P "YourStr0ng_Passw0rd" -C -b -l 2 \
-Q "IF DB_ID('appdb') IS NULL CREATE DATABASE appdb;" >/dev/null 2>&1; do sleep 2; done
echo "ready on localhost,$HOST_PORT"
What ships with it
10 files 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.
- references/connect-and-query.md 3.8 KB
- references/connection-model.md 4.1 KB
- references/entra-auth.md 4.3 KB
- references/environment-variables.md 2.5 KB
- references/image-and-registry.md 3.0 KB
- references/paas-parity-checklist.md 3.9 KB
- references/run-the-container.md 4.3 KB
- references/troubleshooting.md 5.1 KB
- references/wait-until-ready.md 2.2 KB
- scripts/verify.sh 5.6 KB runs code
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.
- 3d ago First seen · 248 lines · 212 tokens per session scan A f7fafb38fcd1
azuresql-db-container is a skill published in the GitHub repository microsoft/azure-sql-database-container (16 stars, last pushed yesterday), licensed MIT. It adds 212 tokens to every session and 3,690 once invoked, about $0.0011 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 2026-08-30.
Other skills, from other repositories
haven-setup
Bring up the LangWatch dev stack via thuishaven (make haven up) — one-time proxy/CA setup, reusing existing local ClickHouse/Postgres/Redis, WSL2/no-colima fallback for langyagent, and the known gotchas that silently break it.
qdrant-deployment-options
Guides Qdrant deployment selection. Use when someone asks 'how to deploy Qdrant', 'Docker vs Cloud', 'local mode', 'embedded Qdrant', 'Qdrant EDGE', 'which deployment option', 'self-hosted vs cloud', or 'need lowest latency deployment'. Also use when choosing between deployment types for a new project.
deploy-registry-server-with-cnpg
Deploy the ToolHive Registry Server to a Kind cluster with CloudNativePG (CNPG) PostgreSQL database. Use when you need a production-like PostgreSQL setup with the CNPG operator.
n8n-azure
Application-specific configuration for deploying n8n to Azure Container Apps with PostgreSQL. Infrastructure should be generated fresh by the azure-prepare → azure-validate → azure-deploy pipeline.
oracle-aidb-docker-setup
Bring up Oracle 26ai Free in Docker, create a project-scoped app user with USERS tablespace + ONNX-friendly grants, and write a .env ready for the rest of the build-paths skills. Idempotent — safe to re-invoke. Use when any project needs a fresh local Oracle 26ai instance.
cnpg
Create and operate CloudNativePG (CNPG) Postgres databases on Kubernetes the GitOps/Flux way - on managed cloud (GKE + GCS via Workload Identity) OR self-hosted (K3s/bare-metal + any S3-compatible store via a credentials secret). Covers Cluster + ScheduledBackup manifests, barman WAL archiving, pgvector, PITR…