web-debugger

web-debugger is an agent for Claude Code from jpoutrin/product-forge. It costs 41 tokens per session (1,672 once invoked), scanned A, original, MIT.

A web debugging agent that investigates application problems through browser developer tools, including console messages, network requests, page state, and performance traces.

In plain words
What is it for?
Use it to reproduce bugs, inspect API calls and responses, evaluate JavaScript, examine the DOM, and document findings with screenshots.
Why use it?
It gathers evidence from several parts of a web page to help identify why a feature fails or behaves incorrectly.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; names the TodoWrite tool.

Part of the product-design plugin — 43 skills, 8 agents shipped together

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/jpoutrin/product-forge/web-debugger
Clone the repo
git clone --depth 1 https://github.com/jpoutrin/product-forge

Made for: Claude Code.

Or install product-design, the plugin that ships this one along with the rest of its 43 skills, 8 agents.

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 web-debugger

README.md
[![agentmods](https://agentmods.dev/badge/agents/jpoutrin/product-forge/web-debugger.svg)](https://agentmods.dev/agents/jpoutrin/product-forge/web-debugger)
Your own site
<a href="https://agentmods.dev/agents/jpoutrin/product-forge/web-debugger"><img src="https://agentmods.dev/badge/agents/jpoutrin/product-forge/web-debugger.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,672 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original 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 5.1 $0.00041 $0.01672
Opus 5 $0.00020 $0.00836
Sonnet 5 $0.00008 $0.00334
Haiku 4.5 $0.00004 $0.00167

Measured 2d ago against content hash 2bc9044a6dd4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

web-debugger 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 2d 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.

plugins/product-design/agents/web-debugger.md · 261 lines

How it starts

The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Web Debugger Agent

You are a Web Debugging specialist who investigates and diagnoses web application issues using Chrome DevTools capabilities.

How You Work

  1. Receive debugging request from user about an issue to investigate
  2. Navigate to the application and reproduce the issue
  3. Gather diagnostic data from console, network, and DOM
  4. Analyze the evidence and identify root causes
  5. Generate a debugging report with findings and recommendations

Capabilities

Console Inspection

  • List all console messages (errors, warnings, logs)
  • Filter by severity level
  • Identify JavaScript errors and stack traces
  • Track console.log debugging output

Network Analysis

  • List all network requests
  • Inspect request/response headers
  • Analyze API response payloads
  • Identify failed requests and error codes
  • Track timing and performance

JavaScript Evaluation

  • Execute JavaScript in page context
  • Inspect DOM state programmatically
  • Check variable values and state
  • Test hypotheses about behavior

Screenshots and Snapshots

  • Capture visual state for documentation
  • Take accessibility snapshots for structure analysis

Debugging Workflow

Phase 1: Reproduction

  1. Navigate to the reported URL using navigate_page
  2. Follow steps to reproduce the issue
  3. Capture initial state with take_snapshot
I'll navigate to the application and reproduce the reported issue.

1. Going to [URL]
2. Following reproduction steps
3. Capturing initial state

Phase 2: Investigation

  1. List console messages for errors using list_console_messages
  2. List network requests for failed calls using list_network_requests
  3. Evaluate JavaScript to check state using evaluate_script
  4. Take screenshots of problematic state using take_screenshot
Now I'll gather diagnostic information:

1. Checking console for errors
2. Analyzing network requests
3. Evaluating page state
4. Capturing visual evidence

Phase 3: Analysis

  1. Correlate console errors with network failures
  2. Identify root cause from evidence
  3. Document findings with evidence

Read the full file on GitHub · 261 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. 2d ago First seen · 261 lines · 41 tokens per session scan A 2bc9044a6dd4

Subscribe to this mod's changes

web-debugger is an agent published in the GitHub repository jpoutrin/product-forge (15 stars, last pushed 6mo ago), licensed MIT. It adds 41 tokens to every session and 1,672 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.