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 atagon-GmbH/kogiqa-mcp --skill browser-debuggit clone --depth 1 https://github.com/atagon-GmbH/kogiqa-mcpWrote 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/atagon-gmbh/kogiqa-mcp/browser-debug)<a href="https://agentmods.dev/skills/atagon-gmbh/kogiqa-mcp/browser-debug"><img src="https://agentmods.dev/badge/skills/atagon-gmbh/kogiqa-mcp/browser-debug/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/atagon-gmbh/kogiqa-mcp/browser-debug"><img src="https://agentmods.dev/badge/skills/atagon-gmbh/kogiqa-mcp/browser-debug.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 | $0.00045 | $0.00323 |
| Opus 5.5 | $0.00018 | $0.00129 |
| Sonnet 5.5 | $0.00009 | $0.00065 |
| Haiku 4.5 | $0.00005 | $0.00032 |
Grade A, and why
browser-debug 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 2d 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
Debug a web app in the browser
Use the kogiQA browser tools to reproduce, inspect, and diagnose front-end problems. The browser is selector-free: describe what you want in natural language, then act on the tool results.
Workflow
browser_navigateto the page under test.browser_get_console_logto read the current console messages. Clear the picture by revisiting the page after a reload if the log is stale.browser_get_network_historyto spot failed requests (4xx/5xx) and slow endpoints.- Reproduce the issue with
browser_click,browser_type,browser_scroll,browser_hover, andbrowser_keypress. - Inspect layout with
browser_check_structureon the element that looks wrong, andbrowser_resizeto test other viewport widths. browser_screenshotonly when you need a visual record; prefer text tools to save tokens.
Reporting
Report findings in this order: the repro steps, the observed behavior, the likely cause, and a concrete fix. When you edit source files, keep the change minimal and re-run the repro with the browser tools to confirm the fix.
Never invent console output or network responses. Only report what the tools returned.
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.
- 2d ago First seen · 31 lines · 45 tokens per session scan A 2e8c27bde0c6
browser-debug is a skill published in the GitHub repository atagon-GmbH/kogiqa-mcp (96 stars, last pushed 2d ago), licensed MIT. It adds 45 tokens to every session and 323 once invoked, about $0.0002 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 2026-10-14.
Other skills, from other repositories
interacting-with-project-runtime
Interacting with a project's JVM runtime through the Kotlin REPL to execute focused probes against project classes and dependencies. Activate when behavior must be observed by running code; use using-gradle for build inspection or task execution.
using-gradle
Using Gradle MCP tools to inspect and run existing builds, including projects, tasks, properties, dependencies, and build results. Activate for Gradle build operation and diagnosis; use authoring-gradle-builds when the build definition itself must change.
qa-use
E2E testing and browser automation with qa-use CLI. Use when the user needs to run tests, verify features, automate browser interactions, or debug test failures.
error-handling
Read the error codes these tools raise and decide whether to retry, fix the call, or stop.
chrome-bridge
Recipes for the user's real, logged-in Chrome through the chrome-bridge MCP tools and the zero-token chrome-bridge CLI. Use when a browser task needs a multi-step recipe — a form "until the email arrives", a checkout with a test card, a pixel/GTM check, a cookie-banner audit, redirects after a migration, a page…
wcode
Use the wcode plugin and its MCP tools for repository coding, review, debugging, refactoring, architecture, Graph/Design inspection, safe edits, command execution, and verification. Trigger whenever wcode is installed or named, even when its tools are lazily registered or omitted from the host's initial tool list.