Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/idjohnson/aiskillsnpx agentmods add skills/idjohnson/aiskills/temptunnelsWrote 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/idjohnson/aiskills/temptunnels)<a href="https://agentmods.dev/skills/idjohnson/aiskills/temptunnels"><img src="https://agentmods.dev/badge/skills/idjohnson/aiskills/temptunnels/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/idjohnson/aiskills/temptunnels"><img src="https://agentmods.dev/badge/skills/idjohnson/aiskills/temptunnels.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 | $0.00092 | $0.04070 |
| Opus 5.5 | $0.00037 | $0.01628 |
| Sonnet 5.5 | $0.00018 | $0.00814 |
| Haiku 4.5 | $0.00009 | $0.00407 |
Grade A, and why
temptunnels 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 yesterday.
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 — 354 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Temporary Tunnels (temptunnels) Skill
This skill guides the AI agent in adding temporary public tunnel containers—supporting both Ngrok (ngrok) and Cloudflare Quick Tunnels (cloudflared)—to Kubernetes Helm charts and Docker Compose (docker-compose.yml / docker-compose.yaml) files so applications can be exposed publicly without requiring DNS, public LoadBalancers, or Ingress controllers.
When to Use This Skill
Activate this skill when the user wants to:
- Add an Ngrok (
ngrok/ngrok) or Cloudflare (cloudflare/cloudflared) tunnel sidecar container to a Helm chart (deployment.yaml,values.yaml,NOTES.txt,secret.yaml). - Create or update a Docker Compose file (
docker-compose.yml/docker-compose.yamland.env/.env.example) with an Ngrok or Cloudflare (cloudflared) tunnel companion service. - Expose a Kubernetes or Docker Compose service temporarily via a public HTTPS URL (
*.ngrok-free.app/*.ngrok.appor*.trycloudflare.com). - Configure tunnel ports, metrics/health probes, target URLs, or authentication tokens/secrets in Helm or Docker Compose.
Choosing Between Ngrok and Cloudflare (cloudflared)
| Feature | Option 1: Ngrok (ngrok/ngrok) |
Option 2: Cloudflare (cloudflare/cloudflared) |
|---|---|---|
| Public URL Domain | *.ngrok-free.app / *.ngrok.app |
*.trycloudflare.com (Quick Tunnel) |
| Required Secrets / Tokens | Requires authtoken (--authtoken or NGROK_AUTHTOKEN) |
None required for Quick Tunnels (optional TUNNEL_TOKEN for Named Tunnels) |
| Target URL (Helm / K8s Pod) | http://localhost:<service.targetPort> |
http://localhost:<service.targetPort> via --url |
| Target URL (Docker Compose) | http://<app-service>:<port> (or http://localhost:<port> with network_mode: "service:<app-service>") |
http://<app-service>:<port> via --url (or http://localhost:<port> with network_mode: "service:<app-service>") |
| Container / Sidecar Ports | Optional 4040/TCP (Inspector UI/API) |
2000/TCP (cf-metrics) for --metrics & /ready livenessProbe |
| Outbound Ports | 443/TCP (TLS to Ngrok edge) |
443/TCP (HTTPS) & 7844/TCP+UDP (QUIC/HTTP2 to Cloudflare edge) |
What ships with it
4 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.
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.
- yesterday First seen · 354 lines · 92 tokens per session scan A fbbf0dd27d9f
temptunnels is a skill published in the GitHub repository idjohnson/aiskills (2 stars, last pushed yesterday), licensed MIT. It adds 92 tokens to every session and 4,070 once invoked, about $0.0004 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 2026-10-18.
Other skills, from other repositories
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
bdd-container-update
Update the BDD test container image when its dependencies or runtime change. Determines version bump (major vs minor vs patch), rebuilds the Docker image, pushes to GitLab registry, and updates the image tag in starttest.sh. Test source (tests/, features/, scripts/, data/, conftest.py) is bind-mounted from the host…
docker-socket-mount
Docker / containerd socket mounted into a container → host RCE. Common in CI runners, GitOps controllers (ArgoCD, Flux), and 'Docker-in-Docker' setups. Single-command escape via docker run --rm --privileged -v /:/host alpine chroot /host.
securing-kubernetes-on-cloud
This skill covers hardening managed Kubernetes clusters on EKS, AKS, and GKE by implementing Pod Security Standards, network policies, workload identity, RBAC scoping, image admission controls, and runtime security monitoring. It addresses cloud-specific security features including IRSA for EKS, Workload Identity for…
detecting-privilege-escalation-in-kubernetes-pods
Detect and prevent privilege escalation in Kubernetes pods by monitoring security contexts, capabilities, and syscall patterns with Falco and OPA policies.
polar-local-environment
This skill should be used when setting up or managing Polar local development environment with Docker.