Skip to content
Agentmart
Submit a tool

browser-dogfood

Run real browser-based product testing with Codex browser tools.

Skill by sdntsng

IndexedMIT
Write a review

Chalk Labs

Need help deploying browser-dogfood?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/sdntsng-browser-dogfood

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Run real browser-based product testing with Codex browser tools. Use when you need to open a site, click through flows, verify staging or production behavior, inspect console or network failures, capture screenshots, test responsive layouts, or confirm that a UI change works end to end.

Use cases: design, testing, agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/browser-dogfood

What's inside

Skill name
browser-dogfood
Description
Run real browser-based product testing with Codex browser tools. Use when you need to open a site, click through flows, verify staging or production behavior, inspect console or network failures, capture screenshots, test responsive layouts, or confirm that a UI change works end to end.
License
MIT
Instructions
51 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • openai.yaml · agents/

SKILL.md (first lines)

# Browser Dogfood

Use this skill to verify product behavior in a real browser instead of inferring from code.

## Workflow
1. Establish the target.
   - Confirm the URL, local dev server, or environment to test.
   - If auth is required, prefer an existing logged-in browser context before asking for credentials.
2. Capture a baseline.
   - Open the page.
   - Take a snapshot of the visible structure.
   - Check console output and failed network requests early.
3. Exercise the flow.
   - Click through the exact user path.
   - Prefer snapshots before and after major actions.
   - For forms, verify validation, success, and failure states.
4. Collect evidence.
   - Save screenshots for important states.
   - Record concrete failures: broken layout, console error, request failure, bad redirect, stale UI, missing state.
5. Conclude with a verdict.
   - State what worked.
   - State what failed.
   - State whether the issue is reproducible and where.

## Default tool choices
- Use Playwright browser tools for most end-to-end testing.
- Use Chrome DevTools tools when you need deeper network, console, DOM, or performance inspection.
- Prefer snapshots over screenshots for navigation and element targeting.
- Use screenshots when visual evidence matters.

## What to check
- Page loads without blocking errors.
- Core interactions work.
- Empty, loading, error, and success states are coherent.
- Responsive layout holds on mobile and desktop when relevant.
- No silent console or network failures are masking a broken experience.

## Output expectations
Return:
- tested URL or flow
- steps executed
- evidence collected
- findings ordered by severity
- pass or fail summary

## Guardrails
- Do not claim a flow works unless you actually executed it.
- Do not rely on screenshots alone when console or network checks are relevant.
- If login blocks progress, say exactly where the flow stopped.

From sdntsng/codex-gstack, MIT.

More from sdntsng/codex-gstack

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Mar 19, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from sdntsng

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get browser-dogfood running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying browser-dogfood?

CallGet help
Cite this page

browser-dogfood skill. Agent Mart. https://agentmart.dev/skills/sdntsng-browser-dogfood (last updated 2026-10-24)