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 kurtosis-tech/kurtosis --skill gatewaygit clone --depth 1 https://github.com/kurtosis-tech/kurtosisWrote 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/kurtosis-tech/kurtosis/gateway)<a href="https://agentmods.dev/skills/kurtosis-tech/kurtosis/gateway"><img src="https://agentmods.dev/badge/skills/kurtosis-tech/kurtosis/gateway/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/kurtosis-tech/kurtosis/gateway"><img src="https://agentmods.dev/badge/skills/kurtosis-tech/kurtosis/gateway.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00057 | $0.00439 |
| Opus 5 | $0.00028 | $0.00219 |
| Sonnet 5 | $0.00011 | $0.00088 |
| Haiku 4.5 | $0.00006 | $0.00044 |
Grade A, and why
gateway 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.
What it actually says
Gateway
The Kurtosis gateway creates local port forwards to the engine and services running in a Kubernetes cluster.
When you need it
The gateway is required when running Kurtosis on Kubernetes. Without it, the local CLI cannot reach the engine pod in the cluster.
Not needed when using Docker backend.
Start the gateway
# Run in the background
kurtosis gateway &
# Or in a separate terminal
kurtosis gateway
Verify it's working
kurtosis engine status
If this returns engine info, the gateway is working. If it says "No Kurtosis engine is running" but you know the engine pod is up, the gateway isn't running.
Stop the gateway
pkill -f "kurtosis gateway"
How it works
The gateway:
- Finds the engine pod in the
kurtosis-engine-*namespace - Creates a local port forward to the engine's gRPC port
- When services are accessed, creates additional port forwards to service pods
- Port mappings shown in
kurtosis enclave inspectpoint to localhost via the gateway
Common issues
| Symptom | Fix |
|---|---|
No engine running but engine pod is up |
Start the gateway: kurtosis gateway & |
| Gateway crashes or disconnects | Restart: pkill -f "kurtosis gateway"; kurtosis gateway & |
| Port conflicts | Kill old gateway first: pkill -f "kurtosis gateway" |
| Services unreachable after gateway restart | Re-inspect enclave for new port mappings |
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 · 60 lines · 57 tokens per session scan A 4ff02f94be5a
gateway is a skill published in the GitHub repository kurtosis-tech/kurtosis (551 stars, last pushed 6d ago), licensed Apache-2.0. It adds 57 tokens to every session and 439 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 2026-08-30.
Other skills, from other repositories
synapse
Use when the user needs to inspect or manage Synapse-managed Docker/Compose infrastructure via flux, or SSH/local host files, processes, logs, ZFS, and allowlisted commands via scout. Prefer MCP tools first, CLI second, REST last; use write or confirmation-gated actions only when explicitly requested or necessary.
xcloud-docker-deploy
Skill "xcloud-docker-deploy" from Asif2BD/xCloud-Docker-Deploy-Skill, covering xcloud docker deploy v1.4.1, start here, how xcloud works, current xcloud api + agent skills context and api token flow.
harbor-daytona
Use Harbor's Daytona sandbox platform for computer use — creating sandboxes, taking screenshots, sending mouse/keyboard input, and building agent loops. Use when the user wants to interact with a GUI, automate a desktop, do computer use, control a browser visually, or run Claude computer use against a Daytona sandbox.
boost-modules
Skill "boost-modules" from av/harbor, covering harbor boost custom modules, module structure, quick reference, output methods and stream text to client.
ecspresso
ECS deployment tool - deploy, manage, and troubleshoot ECS services.
cloudflare-deploy
Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or set up a project on Cloudflare.