# dogfood

> Claude/Codex skill by [@nousresearch](https://omgskills.com/library/nousresearch/index.md) · 263k stars · Updated 2026-11-13

Exploratory QA of web apps: find bugs, evidence, reports.

Tags: ai, ai-agent, ai-agents, anthropic, chatgpt, claude, claude-code, codex, hermes, hermes-agent, llm, nous-research, openai

## Install

```sh
git clone https://github.com/NousResearch/hermes-agent /tmp/hermes-agent && ln -s /tmp/hermes-agent/skills/software-development/dogfood ~/.claude/skills/dogfood
```

## From README

Dogfood: Systematic Web Application QA Testing Overview This skill guides you through systematic exploratory QA testing of web applications with browserexec. You will navigate the application, interact with elements, capture evidence of issues, and produce a structured bug report. Prerequisites The browser toolset must be enabled (browserexec). browserexec runs Python with pre-imported helpers (newtab, gotourl, waitforload, pageinfo, js, fillinput, clickatxy, capturescreenshot, cdp); browser state persists across calls, Python variables do not. A target URL and testing scope from the user Inputs The user provides: Target URL — the entry point for testing Scope — what areas/features to focus on (or "full site" for comprehensive testing) Output directory (optional) — where to save screenshots and the report (default: ./dogfood-output) Workflow Follow this 5-phase systematic workflow: Phase 1: Plan Create the output directory structure: Identify the testing scope based on user input.

## Links

- HTML page: https://omgskills.com/library/nousresearch/hermes-agent/dogfood/
- GitHub: https://github.com/NousResearch/hermes-agent
- Author: [@nousresearch](https://omgskills.com/library/nousresearch/index.md)