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 pbc-os/smb-starter-kit --skill data-lake-startergit clone --depth 1 https://github.com/pbc-os/smb-starter-kitWrote 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/pbc-os/smb-starter-kit/data-lake-starter)<a href="https://agentmods.dev/skills/pbc-os/smb-starter-kit/data-lake-starter"><img src="https://agentmods.dev/badge/skills/pbc-os/smb-starter-kit/data-lake-starter/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/pbc-os/smb-starter-kit/data-lake-starter"><img src="https://agentmods.dev/badge/skills/pbc-os/smb-starter-kit/data-lake-starter.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 | $0.00068 | $0.04160 |
| Opus 5 | $0.00034 | $0.02080 |
| Sonnet 5 | $0.00014 | $0.00832 |
| Haiku 4.5 | $0.00007 | $0.00416 |
Grade A, and why
data-lake-starter 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.
How it starts
The opening of the file, as written. The whole thing — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Lake Starter — A Secure Home for All Your Business Data
Start here. This is the first skill in the foundation tier. It builds the secure, empty lake that every other skill in this kit reads from and writes to.
How to use this skill
Don't run these steps by hand. Hand them to an AI agent and let it drive.
This skill is written to be run by an agent on your behalf — Claude Code or Claude Desktop — not copy-pasted into a terminal by you. That's not just easier; it's how the lake gets set up securely: the agent runs each gcloud / terraform command with judgment, explains every security choice as it goes, checks its own work, and never writes a secret to disk.
Getting started (about 5 minutes):
- Install an agent. Claude Desktop is the no-terminal option; Claude Code is the CLI version.
- Add this skill. Clone the kit and copy this folder into your agent's skills directory:
(Not comfortable with git? Download the repo as a ZIP from GitHub and copy the folder. On Windows the skills directory isgit clone https://github.com/pbc-os/smb-starter-kit.git cp -r smb-starter-kit/skills/tier-1-foundation/data-lake-starter ~/.claude/skills/data-lake-starter%APPDATA%\Claude\skills\.) - Ask the agent to run it. Open the agent and say: "Use the data-lake-starter skill to build my data lake — walk me through it."
New to all of this? Start with the repo README. The rest of this document is written for the agent — you're welcome to read along, but you don't have to run anything yourself.
1. The Vision: You Already Have the Data
Every small business is already generating enterprise amounts of data. Your POS, your accounting, your email tool, your ad accounts, your reviews — each one is quietly piling up thousands of rows about your business. The problem was never having the data. It's that the data lives in twenty different tools that don't talk to each other, and stitching it together used to require a data team only big companies could afford.
What ships with it
14 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/connecting.md 4.7 KB
- references/cost.md 3.6 KB
- references/hardening.md 6.6 KB
- templates/terraform/.gitignore 452 B
- templates/terraform/budget.tf 1.0 KB
- templates/terraform/datasets.tf 2.9 KB
- templates/terraform/iam.tf 2.1 KB
- templates/terraform/main.tf 1.3 KB
- templates/terraform/outputs.tf 1.0 KB
- templates/terraform/README.md 3.4 KB
- templates/terraform/security.tf 2.7 KB
- templates/terraform/terraform.tfvars.example 1.2 KB
- templates/terraform/variables.tf 2.2 KB
- templates/terraform/versions.tf 467 B
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.
- 9d ago First seen · 279 lines · 68 tokens per session scan A dc87851eecdd
data-lake-starter is a skill published in the GitHub repository pbc-os/smb-starter-kit (10 stars, last pushed 3mo ago), licensed MIT. It adds 68 tokens to every session and 4,160 once invoked, about $0.0003 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
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
cloud-architect
Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost…