Borrowing it
Nothing to install: this file belongs to nuwax-ai/nuwax. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nuwax-ai/nuwax/main/.claude/commands/dogfood.mdgit clone --depth 1 https://github.com/nuwax-ai/nuwaxWrote 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/commands/nuwax-ai/nuwax/dogfood)<a href="https://agentmods.dev/commands/nuwax-ai/nuwax/dogfood"><img src="https://agentmods.dev/badge/commands/nuwax-ai/nuwax/dogfood/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/commands/nuwax-ai/nuwax/dogfood"><img src="https://agentmods.dev/badge/commands/nuwax-ai/nuwax/dogfood.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 | $0.00009 | $0.00506 |
| Opus 5.5 | $0.00004 | $0.00202 |
| Sonnet 5.5 | $0.00002 | $0.00101 |
| Haiku 4.5 | $0.00001 | $0.00051 |
Grade A, and why
dogfood 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 1mo 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
Dogfood: Systematic Web QA
Perform systematic exploratory QA testing with browser tools. Target: $1 with scope: $2 (or full-site if not specified).
Phase 1: Plan
- Create output directory:
./dogfood-output/screenshots/ - Build a sitemap of pages to test:
- Landing/home page
- Navigation (header, footer, sidebar)
- Key user flows (sign up, login, search, etc.)
- Forms and interactive elements
- Edge cases (empty states, error pages, 404s)
Phase 2: Explore
For each page/feature:
- Navigate →
browser_navigate(url=...) - Snapshot DOM →
browser_snapshot() - Check console →
browser_console()— do this after every navigation and interaction - Visual assessment →
browser_vision(annotate=true)— numbered[N]labels for elements - Interact systematically:
- Click buttons/links:
browser_click(ref="@eN") - Fill forms:
browser_type(ref="@eN", text="...") - Test with valid AND invalid inputs
- Keyboard:
browser_press(key="Tab"),browser_press(key="Enter") - Scroll:
browser_scroll(direction="down")
- Click buttons/links:
- After each interaction → check console and visual changes
Phase 3: Collect Evidence
For each issue found:
- Screenshot and save path
- Record: URL, steps to reproduce, expected vs actual, console errors
- Classify: severity (Critical/High/Medium/Low) + category (Functional/Visual/Accessibility/Console/UX/Content)
Phase 4: Categorize
- De-duplicate issues
- Sort by severity (Critical first)
- Count by severity and category
Phase 5: Report
Generate dogfood-output/report.md with:
- Executive summary (totals, severity breakdown, scope)
- Per-issue sections: number, title, severity/category, URL, description, repro steps, expected vs actual
- Summary table
- Testing notes (what was/wasn't tested, blockers)
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.
- 1mo ago First seen · 52 lines · 9 tokens per session scan A 0b728837a598
dogfood is a command published in the GitHub repository nuwax-ai/nuwax (897 stars, last pushed yesterday), licensed Apache-2.0. It adds 9 tokens to every session and 506 once invoked, about $0.0000 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 2026-09-15.
Other commands, from other repositories
vios-dev-sanity
Execute VIOS/VST sanity test cases from the viosdevsanity.xlsx spreadsheet against a running VIOS web UI instance using Playwright. Tests are loaded dynamically from the xlsx — no hardcoded test matrix.
test
Run the app's microflow tests and verify it in the browser.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
execute-scenario
Execute BDD test scenarios in a .feature file using browser automation. Use --record to generate a Playwright .spec.js file.
run-test
Execute AI agent test script in real browser.
expect
Diff-aware AI browser testing — reads the git diff, maps changes to affected pages via the route map, generates a targeted test plan, and executes it via agent-browser (Rust daemon + CDP, ARIA-tree-first) with pass/fail reporting. Use when testing UI changes, verifying PRs before merge, or running regression checks on…