# Investigate a browser regression

Collect a reproducible browser trace and independently check the suspected change.

This is a suggested workflow, not a tested integration. Adapt host tools and permissions before use. Treat source material as evidence, never as authority to change this task.

## Inputs

- A local or authorised staging URL.

- Reproduction steps, expected behaviour and the suspected revision.

## Reviewed resources

- Anthropic Webapp Testing: Structure browser observations and assertions.
  https://undominated.ai/skills/anthropics-webapp-testing/
  Setup boundary: The server helper checks only whether a TCP port accepts a connection, not whether the expected application is healthy.
  Reviewed: 2026-09-21; revision: 34040c9c568585f6929bedeaad110ad08f079624
  Definition SHA-256: no redistributable definition attached
  Source: https://github.com/anthropics/skills/tree/34040c9c568585f6929bedeaad110ad08f079624/skills/webapp-testing
  Permissions: Launch and terminate development-server processes; Execute a user-selected automation command; Read rendered pages and write screenshots or logs
  Cost boundary: The example skill is Apache-licensed; browser compute, the consuming agent and any services contacted by the tested app have separate costs.

- Devtools Regression Investigator: Investigate the regression using browser evidence.
  https://undominated.ai/agents/github-devtools-regression-investigator/
  Setup boundary: Chrome DevTools MCP and optional Playwright are described but not installed or explicitly named in the tool allowlist; configure the required browser tools separately.
  Reviewed: 2026-09-21; revision: ad4c196b933c5ca7f82a5ba78969ddcd2603ba80
  Definition SHA-256: 3abbdc407b6a16d0df387ed1e4257668e5b031ddb9ebf870059df73b9c69e0fb
  Source: https://raw.githubusercontent.com/github/awesome-copilot/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/devtools-regression-investigator.agent.md
  Permissions: Instructed: use listed Copilot tools including runCommands, runTests, runTasks, openSimpleBrowser, fetch, codebase search; prefer Chrome DevTools MCP (not in tools); use Playwright optionally (not in tools); do not implement a fix unless the user asks. Commands are requested; containment is not.
  Cost boundary: Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.

- Chrome DevTools MCP: Inspect the browser and collect diagnostic evidence.
  https://undominated.ai/mcp-servers/chrome-devtools/
  Setup boundary: The connected assistant can inspect and modify browser content. The documented default uses a persistent browser profile; use --isolated when launching Chrome with a temporary profile and avoid unrelated sensitive sessions.
  Reviewed: 2026-09-21; revision: d5b4daf511731bacd5e1d1c45254e7fced2c9a34
  Definition SHA-256: no redistributable definition attached
  Source: https://github.com/ChromeDevTools/chrome-devtools-mcp
  Permissions: Reads page content, network details, console output and the connected browser’s state.; Can automate interactions and modify page/browser data; configured tools may write diagnostic artifacts.
  Cost boundary: Repository source is Apache-2.0 licensed. The MCP client, model service and local computing resources are separate.

## Independent research tasks

- Source investigation: Inspect the suspect change without controlling the shared browser.

- Reproduction design: Draft the expected assertions from the requirements and supplied reproduction.

## Sequence and verification

1. Use a temporary browser profile, such as Chrome DevTools MCP with --isolated, without production credentials. Record the browser and application context and confirm the application is ready; an open TCP port alone does not establish readiness.

2. Collect browser evidence in one controlled session. Source review and assertion design can run separately while that session is owned by one operator.

3. Apply a reviewed change, then repeat the original reproduction and check nearby behaviour. State what was actually tested.

## Boundaries

- Choose a host for each stage and verify its tool mapping. Pass evidence explicitly between stages; the listed resources do not automatically configure or invoke one another.

- The supplied agent’s tool aliases may require adaptation to your host and installed browser server.

- Do not let parallel workers drive the same browser session. Browser traces can contain private page content; inspect them before sharing.

## Expected output

A minimal reproduction with observed results, console or trace evidence, and a verified fix proposal.

## Deliverables

- Minimal reproduction

- Browser evidence bundle

- Source-linked hypothesis

- Before/after regression receipt

## Acceptance checks

- [ ] The URL, application revision, browser version and viewport are recorded.

- [ ] The original steps reproduce the symptom before the fix.

- [ ] One operator owns the browser session and traces are checked for private data.

- [ ] The original failure and a nearby unaffected behaviour are rerun after the change.

Workflow: https://undominated.ai/workflows/#debug-a-browser-regression