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 nodnarbnitram/claude-code-extensions --skill cloudflare-vpc-servicesgit clone --depth 1 https://github.com/nodnarbnitram/claude-code-extensionsWrote 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/nodnarbnitram/claude-code-extensions/cloudflare-vpc-services)<a href="https://agentmods.dev/skills/nodnarbnitram/claude-code-extensions/cloudflare-vpc-services"><img src="https://agentmods.dev/badge/skills/nodnarbnitram/claude-code-extensions/cloudflare-vpc-services/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/nodnarbnitram/claude-code-extensions/cloudflare-vpc-services"><img src="https://agentmods.dev/badge/skills/nodnarbnitram/claude-code-extensions/cloudflare-vpc-services.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 | $0.00061 | $0.02018 |
| Opus 5.5 | $0.00024 | $0.00807 |
| Sonnet 5.5 | $0.00012 | $0.00404 |
| Haiku 4.5 | $0.00006 | $0.00202 |
Grade B, and why
cloudflare-vpc-services scanned grade B with 2 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 1mo 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
const response = await env.PRIVATE_API.fetch( "https://internal-api.company.local/users", { method: "POST", Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
async fetch(request, env) { How it starts
The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloudflare VPC Services
Enable Workers to securely access private APIs and services through encrypted tunnels without public internet exposure.
⚠️ BEFORE YOU START
This skill prevents 5 common errors and saves ~60% tokens.
| Metric | Without Skill | With Skill |
|---|---|---|
| Setup Time | 45+ min | 10 min |
| Common Errors | 5 | 0 |
| Token Usage | ~8000 | ~3000 |
Known Issues This Skill Prevents
dns_errorfrom outdated cloudflared version or wrong protocol- Requests leaving VPC due to using public hostnames instead of internal
- Port mismatch - fetch() port is ignored, service config port is used
- Missing absolute URLs in fetch() calls
- Incorrect tunnel ID or service binding configuration
Quick Start
Step 1: Verify Tunnel Requirements
# Check cloudflared version on remote infrastructure (K8s, EC2, etc.)
# Must be 2025.7.0 or later
cloudflared --version
# Verify QUIC protocol is configured (not http2)
# Check tunnel config or Cloudflare dashboard
Why this matters: Workers VPC requires cloudflared 2025.7.0+ with QUIC protocol. Older versions or http2 protocol cause dns_error.
Step 2: Create VPC Service
# Use Cloudflare API or dashboard to create VPC service
# See templates/vpc-service-ip.json or templates/vpc-service-hostname.json
Why this matters: The VPC service defines the actual target (IP/hostname) that the tunnel routes to. The fetch() URL only sets Host header and SNI.
Step 3: Configure Wrangler Binding
// wrangler.jsonc
{
"vpc_services": [
{
"binding": "PRIVATE_API",
"service_id": "<YOUR_SERVICE_ID>",
"remote": true
}
]
}
Why this matters: The binding name becomes the environment variable used in Worker code: env.PRIVATE_API.fetch().
Critical Rules
✅ Always Do
- ✅ Use absolute URLs with protocol, host, and path in fetch()
- ✅ Use internal VPC hostnames, not public endpoints
- ✅ Ensure cloudflared is 2025.7.0+ with QUIC protocol
- ✅ Allow UDP port 7844 outbound for QUIC connections
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.
- README.md 2.9 KB
- references/api-patterns.md 5.0 KB
- references/README.md 525 B
- scripts/list-vpc-services.sh 244 B runs code
- scripts/README.md 816 B
- scripts/set-api-token.sh 669 B runs code
- scripts/tail-worker.sh 606 B runs code
- templates/vpc-service-hostname.json 190 B
- templates/vpc-service-ip.json 161 B
- templates/wrangler-vpc.jsonc 780 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.
- 1mo ago First seen · 281 lines · 61 tokens per session scan B 8f2fc6d0789a
cloudflare-vpc-services is a skill published in the GitHub repository nodnarbnitram/claude-code-extensions (16 stars, last pushed 6mo ago), licensed MIT. It adds 61 tokens to every session and 2,018 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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-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 generating K8s YAML manifests (use gke-manifest-generation) or disaster recovery…
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running security audits (auditcluster.sh), enforcing Network Policies (default-deny and Dataplane V2 logging), isolating high-risk pods inside GKE Sandbox (gVisor), enforcing Pod…
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…
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".