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 rohitg00/kubectl-mcp-server --skill k8s-browsergit clone --depth 1 https://github.com/rohitg00/kubectl-mcp-serverWrote 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/rohitg00/kubectl-mcp-server/k8s-browser)<a href="https://agentmods.dev/skills/rohitg00/kubectl-mcp-server/k8s-browser"><img src="https://agentmods.dev/badge/skills/rohitg00/kubectl-mcp-server/k8s-browser/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/rohitg00/kubectl-mcp-server/k8s-browser"><img src="https://agentmods.dev/badge/skills/rohitg00/kubectl-mcp-server/k8s-browser.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 | $0.00041 | $0.01274 |
| Opus 5 | $0.00020 | $0.00637 |
| Sonnet 5 | $0.00008 | $0.00255 |
| Haiku 4.5 | $0.00004 | $0.00127 |
Grade A, and why
k8s-browser 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 10d 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Automation for Kubernetes
Automate Kubernetes web UIs using kubectl-mcp-server's browser tools (26 tools).
When to Apply
Use this skill when:
- User mentions: "dashboard", "Grafana", "ArgoCD UI", "web interface", "screenshot"
- Operations: navigating K8s dashboards, capturing screenshots, automating web UIs
- Keywords: "browser", "click", "screenshot", "web", "UI automation"
Priority Rules
| Priority | Rule | Impact | Tools |
|---|---|---|---|
| 1 | Enable MCP_BROWSER_ENABLED first | CRITICAL | Environment variable |
| 2 | Open URL before interactions | HIGH | browser_open |
| 3 | Wait for elements before clicking | HIGH | browser_wait_for_selector |
| 4 | Take screenshots for verification | MEDIUM | browser_screenshot |
Quick Reference
| Task | Tool | Example |
|---|---|---|
| Open URL | browser_open |
browser_open(url) |
| Click element | browser_click |
browser_click(selector) |
| Take screenshot | browser_screenshot |
browser_screenshot(path) |
| Wait for element | browser_wait_for_selector |
browser_wait_for_selector(selector) |
Prerequisites
- Browser Tools Enabled: Required
export MCP_BROWSER_ENABLED=true
Enable Browser Tools
export MCP_BROWSER_ENABLED=true
# Optional: Cloud provider
export MCP_BROWSER_PROVIDER=browserbase # or browseruse
export BROWSERBASE_API_KEY=bb_...
Basic Navigation
# Open URL
browser_open(url="http://localhost:8001/api/v1/namespaces/kubernetes-dashboard/services/https:kubernetes-dashboard:/proxy/")
# Open with auth headers
browser_open_with_headers(
url="https://grafana.example.com",
headers={"Authorization": "Bearer token123"}
)
# Navigate
browser_navigate(url="https://argocd.example.com/applications")
# Go back/forward
browser_back()
browser_forward()
# Refresh
browser_refresh()
Screenshots and Content
# Take screenshot
browser_screenshot(path="dashboard.png")
# Full page screenshot
browser_screenshot(path="full-page.png", full_page=True)
# Get page content
browser_content()
# Get page title
browser_title()
# Get current URL
browser_url()
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.
- 10d ago First seen · 221 lines · 41 tokens per session scan A a9b0e9133da9
k8s-browser is a skill published in the GitHub repository rohitg00/kubectl-mcp-server (956 stars, last pushed 5mo ago), licensed MIT. It adds 41 tokens to every session and 1,274 once invoked, about $0.0002 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
securing-helm-chart-deployments
Secure Helm chart deployments by validating chart integrity, scanning templates for misconfigurations, and enforcing security contexts in Kubernetes releases.
test-app
Verify a running Mendix app in a browser with Playwright, with OQL for data assertions. Use when asked to test or validate the app end to end, or to confirm that generated pages actually render.
nvcf-explore-stack
Navigate and explain the NVCF self-hosted stack inside the monorepo. Maps helmfile releases to their charts, image-source subtrees, helm hooks, namespaces, and needs: dependency chains. Reads deploy/stacks/self-managed/helmfile.d/.yaml.gotmpl and deploy/stacks/nvcf-compute-plane/helmfile.d/.yaml.gotmpl as the source…
helm-expert
Expert-level Helm 3 package management, chart development, templating, and production operations. Use when the user mentions Kubernetes, package manager, charts, templates, or deployment, or when the task involves Helm Architecture, Chart Structure, Values.yaml, or Helm Hooks.
kubernetes
Kubernetes operations playbook for deploying services: core objects, probes, resource sizing, safe rollouts, and fast kubectl debugging.
ui-harness-cli
Run the Agentweaver persona-driven Playwright UI evidence harness. Use for a specific persona's deployed browser flow, end-to-end UI validation, or investigation of a UI-reported issue.