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 enwong93-sketch/devspace-ultra --skill devspace-network-setupgit clone --depth 1 https://github.com/enwong93-sketch/devspace-ultraWrote 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/enwong93-sketch/devspace-ultra/devspace-network-setup)<a href="https://agentmods.dev/skills/enwong93-sketch/devspace-ultra/devspace-network-setup"><img src="https://agentmods.dev/badge/skills/enwong93-sketch/devspace-ultra/devspace-network-setup/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/enwong93-sketch/devspace-ultra/devspace-network-setup"><img src="https://agentmods.dev/badge/skills/enwong93-sketch/devspace-ultra/devspace-network-setup.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 | $0.00005 | $0.01766 |
| Opus 5 | $0.00003 | $0.00883 |
| Sonnet 5 | $0.00001 | $0.00353 |
| Haiku 4.5 | $0.00001 | $0.00177 |
Grade A, and why
devspace-network-setup 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DevSpace Ultra network setup
Use this Skill when the user asks to install, set up, upgrade, reconnect, publish, expose, or repair DevSpace Ultra, Local Gateway, DuckDNS/DDNS, Caddy, Cloudflare tunnel, OAuth, router forwarding, or the public MCP URL.
Operating principle
Work as an installation guide and local executor:
- Execute every safe local inspection and setup command yourself through DevSpace workspace/shell tools.
- Ask the user to act only for account ownership, masked secret entry, router administration, ISP/CGNAT decisions, or a browser authorization screen that should remain under the user's control.
- After each user action, re-run a concrete verification. Never accept “I clicked it” as proof by itself.
- Keep the existing Local Gateway state and OAuth data unless a migration gate proves replacement is safe.
- Do not restart an unrelated application runtime such as Blender while repairing network ingress.
Route decision
Choose exactly one route from current evidence:
- DuckDNS/DDNS + Caddy — preferred
- The machine has a publicly routable IPv4/IPv6 address.
- The user can forward TCP 80 and 443 on the router.
- A stable DuckDNS hostname can point to the current WAN address.
- Cloudflare named tunnel — fallback
- The ISP uses CGNAT, router forwarding is unavailable, or the user cannot expose 80/443.
- Use a stable named tunnel and hostname, not a temporary Quick Tunnel.
- State clearly that any Worker relay in the path is governed by the selected Workers plan and its current request allowance.
- Local only — diagnostics
- Suitable for backend development only; it is not a public ChatGPT MCP endpoint.
Do not pick Cloudflare merely because it is easier. Diagnose the direct route first.
Phase 1 — inspect without changing state
- Open the installed DevSpace package workspace.
- Read
package.json,install.ps1,scripts/devspace-ultra-setup.ps1, andscripts/devspace-local-ingress.ps1from the installed version. - Run syntax/static setup gates before executing the installer.
- Read current config and health without printing secret values:
- Gateway
http://127.0.0.1:7678/healthz - active Core memory endpoint on 7688/7689
- Scheduled Task state
- current public base URL and ingress mode
- Gateway
- Inspect WAN/public-address evidence and compare it with the router's WAN address when available. A private or carrier-grade WAN address is a CGNAT warning.
- Inspect listeners and port ownership. Gateway/Core and application MCP ports must remain loopback-only.
What ships with it
1 file 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 Changed 33fa42a767a1
- 2d ago Changed fca8c1eeb1b6
- 4d ago Changed 9496e22384f2
- 6d ago First seen · 163 lines · 5 tokens per session scan A 06780256331d
devspace-network-setup is a skill published in the GitHub repository enwong93-sketch/devspace-ultra (51 stars, last pushed yesterday), licensed MIT. It adds 5 tokens to every session and 1,766 once invoked, about $0.0000 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 2026-09-10.
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 disaster recovery setup or full cluster backups (use gke-backup-dr instead).
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…
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…