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 kevinnft/ai-agent-skills --skill dogfoodgit clone --depth 1 https://github.com/kevinnft/ai-agent-skillsWrote 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/kevinnft/ai-agent-skills/dogfood)<a href="https://agentmods.dev/skills/kevinnft/ai-agent-skills/dogfood"><img src="https://agentmods.dev/badge/skills/kevinnft/ai-agent-skills/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/skills/kevinnft/ai-agent-skills/dogfood"><img src="https://agentmods.dev/badge/skills/kevinnft/ai-agent-skills/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 | $0.00018 | $0.01479 |
| Opus 5 | $0.00009 | $0.00740 |
| Sonnet 5 | $0.00004 | $0.00296 |
| Haiku 4.5 | $0.00002 | $0.00148 |
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 9d 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.
This is a copy
89% identical to dogfood — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dogfood: Systematic Web Application QA Testing
Overview
This skill guides you through systematic exploratory QA testing of web applications using the browser toolset. You will navigate the application, interact with elements, capture evidence of issues, and produce a structured bug report.
Prerequisites
- Browser toolset must be available (
browser_navigate,browser_snapshot,browser_click,browser_type,browser_vision,browser_console,browser_scroll,browser_back,browser_press) - 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:
{output_dir}/ ├── screenshots/ # Evidence screenshots └── report.md # Final report (generated in Phase 5) - Identify the testing scope based on user input.
- Build a rough sitemap by planning which pages and features to test:
- Landing/home page
- Navigation links (header, footer, sidebar)
- Key user flows (sign up, login, search, checkout, etc.)
- Forms and interactive elements
- Edge cases (empty states, error pages, 404s)
Phase 2: Explore
For each page or feature in your plan:
-
Navigate to the page:
browser_navigate(url="https://example.com/page") -
Take a snapshot to understand the DOM structure:
browser_snapshot() -
Check the console for JavaScript errors:
browser_console(clear=true)Do this after every navigation and after every significant interaction. Silent JS errors are high-value findings.
-
Take an annotated screenshot to visually assess the page and identify interactive elements:
browser_vision(question="Describe the page layout, identify any visual issues, broken elements, or accessibility concerns", annotate=true)The
annotate=trueflag overlays numbered[N]labels on interactive elements. Each[N]maps to ref@eNfor subsequent browser commands.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 167 lines · 18 tokens per session scan A c0715950a621
dogfood is a skill published in the GitHub repository kevinnft/ai-agent-skills (14 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 1,479 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to dogfood, differing in 8 lines, and is treated as a copy.
Other skills, from other repositories
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…
flake-triage
Decide whether a preview the visual-diff bot flagged actually regressed or is simply nondeterministic, using a repeat-render oracle at a single commit. Use when a PR's preview diff reports a changed preview whose source the PR does not touch, or when a render, GIF or filmstrip is suspected of being unstable.
running-bug-review-board
Runs real-user QA, manual test plans, UX bug hunts, build sign-off, bug filing, and bug triage for web or iOS/iPadOS apps. Use when asked "QA this", "is this ready to ship?", or similar. Produces P0/P1/P2 bug reports, YES/NO phase sign-off, tracker sync guidance, and an HTML QA dashboard; keeps Interactive BRB triage…
frontend-visual-qa
Verify rendered frontend evidence after implementation, including screenshot comparison, responsiveness, overflow, visible states, and scoped visual regression. Use available browser tooling only; exclude static lookup, routine code review, lint, builds, onboarding, and tool detection.
playwright-debugging
Diagnostic Playwright workflows for flaky or failing tests, including trace analysis, UI mode, and state isolation.
Flaky Test Detangler
Root-causes intermittently failing tests and eliminates the hidden dependency at its source instead of retrying around it. Use when a test passes locally but fails in CI, goes green on a CI re-run, fails roughly one run in ten, or is already tagged "flaky." Do NOT use when the task is to design the fake or stub that…