Add browser investigation agents for performance, regressions, and ru…

[proflead]

Pull Request Checklist

• I have read and followed the CONTRIBUTING.md guidelines.
• I have read and followed the Guidance for submissions involving paid services.
• My contribution adds a new instruction, prompt, agent, skill, or workflow file in the correct directory.
• The file follows the required naming convention.
• The content is clearly structured and follows the example format.
• I have tested my instructions, prompt, agent, skill, or workflow with GitHub Copilot.
• I have run npm start and verified that README.md is up to date.
• I am targeting the staged branch for this pull request.

---

Description

Adds three new specialized browser-focused agents for runtime investigation workflows:

• frontend-performance-investigator.agent.md
• devtools-regression-investigator.agent.md
• accessibility-runtime-tester.agent.md

These agents are intentionally narrower than existing general browser/testing/debug agents and focus on evidence-backed runtime analysis with Chrome DevTools MCP-
style workflows.

Summary of each agent:

• Frontend Performance Investigator: runtime web-performance diagnosis for Core Web Vitals, Lighthouse regressions, layout shifts, long tasks, and slow network
  paths.
• DevTools Regression Investigator: browser regression reproduction and triage for broken user flows, with console/network evidence and likely root-cause
  narrowing.
• Accessibility Runtime Tester: runtime accessibility validation for keyboard flows, focus management, dialog behavior, form errors, and browser-observed WCAG
  issues.

This also regenerates docs/README.agents.md so the new agents appear in the catalog.

---

Type of Contribution

• New agent file.
• Update to existing instruction, prompt, agent, plugin, skill, or workflow.

---

Additional Notes

These are not intended to be generic browser testers.

The goal is to add more focused runtime investigation agents in areas that are valuable to users and explicitly in scope for the repository:

• performance optimization
• testing and quality assurance
• accessibility and inclusive design

I tried to keep overlap low by making each agent centered on a distinct investigation workflow rather than a general-purpose testing persona.

Validation performed:

• Ran npm ci
• Ran npm run build
• Ran bash scripts/fix-line-endings.sh

---

By submitting this pull request, I confirm that my contribution abides by the Code of Conduct and will be licensed under the MIT License.

[github-actions]

⚠️ This PR targets main, but PRs should target staged.

The main branch is auto-published from staged and should not receive direct PRs.
Please close this PR and re-open it against the staged branch.

You can change the base branch using the Edit button at the top of this PR,
or run: gh pr edit 1265 --base staged

[proflead]

Updated the PR base branch to staged.

[Copilot]

Copilot wasn't able to review this pull request because it exceeds the maximum number of files (300). Try reducing the number of changed files and requesting a review from Copilot again.