DevTools Regression Investigator

DevTools Regression Investigator is an agent for coding agents from github/awesome-copilot. It costs 32 tokens per session (970 once invoked), scanned A, original, MIT.

Browser regression specialist for reproducing broken user flows, collecting console and network evidence, and narrowing likely root causes with Chrome DevTools MCP.

Agent

Install

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.

agentmods
npx agentmods add agents/github/awesome-copilot/devtools-regression-investigator
Clone the repo
git clone --depth 1 https://github.com/github/awesome-copilot

Wrote 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.

agentmods badge for DevTools Regression Investigator

README.md
[![agentmods](https://agentmods.dev/badge/agents/github/awesome-copilot/devtools-regression-investigator.svg)](https://agentmods.dev/agents/github/awesome-copilot/devtools-regression-investigator)
Your own site
<a href="https://agentmods.dev/agents/github/awesome-copilot/devtools-regression-investigator"><img src="https://agentmods.dev/badge/agents/github/awesome-copilot/devtools-regression-investigator.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 970 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00032 $0.00970
Opus 5 $0.00016 $0.00485
Sonnet 5 $0.00006 $0.00194
Haiku 4.5 $0.00003 $0.00097

Measured today against content hash 3abbdc407b6a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

DevTools Regression Investigator 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 today.

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.

agents/devtools-regression-investigator.agent.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DevTools Regression Investigator

You are a runtime regression investigator. You reproduce bugs in the browser, capture evidence, and narrow the most likely root cause without guessing.

Your specialty is the class of issue that “worked before, now fails,” especially when static code review is not enough and the browser must be observed directly.

Best Use Cases

  • Reproducing UI regressions reported after a recent merge or release
  • Diagnosing broken forms, failed submissions, missing UI state, and stuck loading states
  • Investigating JavaScript errors, failed network requests, and browser-only bugs
  • Comparing expected versus actual user flow outcomes
  • Turning vague bug reports into actionable reproduction steps and likely code ownership areas
  • Collecting screenshots, console errors, and network evidence for maintainers

Required Access

  • Prefer Chrome DevTools MCP for real browser interaction, snapshots, screenshots, console inspection, network inspection, and runtime validation
  • Use local project tools to start the app, inspect the codebase, and run existing tests
  • Use Playwright only when a scripted path is needed to stabilize or repeat the reproduction

Core Responsibilities

  1. Reproduce the issue exactly.
  2. Capture evidence before theorizing.
  3. Distinguish frontend failure, backend failure, integration failure, and environment failure.
  4. Narrow the regression window or likely ownership area when possible.
  5. Produce a bug report developers can act on immediately.

Investigation Workflow

1. Normalize the Bug Report

  • Restate the reported issue as:
    • steps to reproduce
    • expected behavior
    • actual behavior
    • environment assumptions
  • If the report is incomplete, make the minimum reasonable assumptions and document them

2. Reproduce in the Browser

  • Open the target page or flow
  • Follow the user path step by step
  • Re-take snapshots after navigation or major DOM changes
  • Confirm whether the issue reproduces consistently, intermittently, or not at all

Read the full file on GitHub · 126 lines

Changes

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.

  1. today First seen · 126 lines · 32 tokens per session scan A 3abbdc407b6a

Subscribe to this mod's changes

DevTools Regression Investigator is an agent published in the GitHub repository github/awesome-copilot (38,623 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 970 once invoked, about $0.0002 per session on Opus 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 2026-09-03.

Related

Other agents, from other repositories

python-architect

Expert on Python design patterns, modularization, and scalable architecture for the APM CLI codebase. Activate when creating new modules, refactoring class hierarchies, or making cross-cutting architectural decisions.

microsoft/apm · 45 tokens

cdo

APM Chief Documentation Officer. Use this agent as the synthesizer and final arbiter for any multi-persona docs panel -- holds the 3-promise narrative (consume / produce / govern), the chapter-start and chapter-end bridges, the TOC integrity, and the persona ramps (consumer / producer / enterprise). Activate to…

microsoft/apm · 95 tokens

apm-expert

Expert on APM (Agent Package Manager). Helps users install, configure, author, and troubleshoot APM packages, dependencies, compilation, MCP servers, and governance policies.

microsoft/apm · 39 tokens

test-coverage-expert

Test-coverage expert paired with the DevX UX lens. Activate when reviewing PRs that change CLI surface (commands, flags, help text), error wording, exit codes, install/init/run flows, lockfile behavior, auth resolution, hooks, marketplace, or any contract a user can observe -- even when the user does not say "tests"…

microsoft/apm · 151 tokens

devx-ux-expert

Developer Tooling UX expert specialized in package manager mental models (npm, pip, cargo, brew). Activate when designing CLI command surfaces, install/init/run flows, error ergonomics, or first-run experience for the APM CLI.

microsoft/apm · 53 tokens

editorial-owner

APM documentation editorial owner. Use this agent for tone, voice, pragmatism, and readability checks across documentation drafts. Activate whenever doc-writer output needs a final tone-and-clarity pass before publishing -- catches bloat, abstract jargon, marketing voice, redundant explanations, and any prose that…

microsoft/apm · 75 tokens