k8s-browser

k8s-browser is a skill for Claude Code, Codex from yindia/rootcause. It costs 0 tokens per session (2,155 once invoked), scanned A, original, MIT.

A browser-automation guide for Kubernetes-related web interfaces, such as dashboards, Grafana, and Argo CD. It covers opening pages, interacting with them, and collecting visual or exported evidence.

In plain words
What is it for?
Testing ingress URLs, checking Kubernetes-facing UIs, reproducing interface bugs, automating login steps, and capturing screenshots or PDFs.
Why use it?
It helps investigate issues that cannot be confirmed from command-line or API data alone, such as an inaccessible ingress page or a broken dashboard flow.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/yindia/rootcause/k8s-browser
Any agent
npx skills add yindia/rootcause --skill k8s-browser
Clone the repo
git clone --depth 1 https://github.com/yindia/rootcause

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for k8s-browser

README.md
[![agentmods](https://agentmods.dev/badge/skills/yindia/rootcause/k8s-browser.svg)](https://agentmods.dev/skills/yindia/rootcause/k8s-browser)
Your own site
<a href="https://agentmods.dev/skills/yindia/rootcause/k8s-browser"><img src="https://agentmods.dev/badge/skills/yindia/rootcause/k8s-browser.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,155 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.02155
Opus 5 $0.00000 $0.01077
Sonnet 5 $0.00000 $0.00431
Haiku 4.5 $0.00000 $0.00215

Measured 4d ago against content hash 4de6de256036, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 4d 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.

skills/claude/k8s-browser/SKILL.md · 285 lines

How it starts

The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: k8s-browser

Browser automation skill for Kubernetes-facing UIs, ingress validation, dashboard evidence capture, interactive troubleshooting, and incident artifact export.

Prerequisites

Before using this skill, ensure:

  • browser tools are enabled in RootCause runtime.
  • target URL is reachable from browser execution environment.
  • required credentials are available for login flows.
  • if SSO is used, allow extra waiting and redirect checks.

If browser tools are disabled, report it immediately and continue with non-browser alternatives only when requested.

Trigger Phrases

Use this skill when the user mentions:

  • test ingress URL
  • take screenshot
  • capture grafana dashboard
  • check kubernetes dashboard UI
  • validate argocd UI
  • reproduce ui bug
  • automate login form
  • export page as pdf
  • verify web health check
  • gather visual evidence

Browser Tool Catalog (All 26)

Session and navigation

Tool Purpose Typical Parameters
browser_open Open URL in session url, optional session
browser_new_tab Create new tab optional url, session
browser_switch_tab Switch active tab tab, session
browser_close_tab Close selected tab optional tab, session
browser_close Close browser session optional session

Validation and waiting

Tool Purpose Typical Parameters
browser_health_check URL check with optional text assertion url, optional contains
browser_test_ingress Ingress URL validation with evidence url
browser_wait_for Wait for selector to appear selector
browser_wait_for_url Wait for exact/expected URL url

Interaction

Tool Purpose Typical Parameters
browser_click Click element selector
browser_fill Fill input directly selector, text
browser_type Type text events into input selector, text
browser_press Keyboard key action key
browser_select Select option in dropdown selector, value
browser_hover Hover element selector
browser_check Check checkbox/radio selector
browser_uncheck Uncheck checkbox selector
browser_upload Upload file selector, path
browser_drag Drag and drop source, target

Read the full file on GitHub · 285 lines

Changes

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.

  1. 4d ago First seen · 285 lines · 0 tokens per session scan A 4de6de256036

Subscribe to this mod's changes

k8s-browser is a skill published in the GitHub repository yindia/rootcause (42 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,155 tokens. 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.