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.
npx agentmods add skills/serkan-ozal/browser-devtools-claude/web-debuggingnpx skills add serkan-ozal/browser-devtools-claude --skill web-debugginggit clone --depth 1 https://github.com/serkan-ozal/browser-devtools-claudeWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00044 | $0.00752 |
| Opus 5 | $0.00022 | $0.00376 |
| Sonnet 5 | $0.00009 | $0.00150 |
| Haiku 4.5 | $0.00004 | $0.00075 |
Grade A, and why
web-debugging 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Debugging Skill
Debug web applications by inspecting console logs, network requests, JavaScript errors, and using non-blocking tracepoints/logpoints.
When to Use
This skill activates when:
- User reports a bug or error on a web page
- User asks to debug JavaScript issues
- User wants to inspect API calls or network requests
- User needs to troubleshoot page loading issues
- User mentions console errors or warnings
- User wants to trace code execution without pausing
Capabilities
Console Inspection
- Get all console messages (
o11y_get-console-messages) - Filter by log level (error, warn, info, debug)
- Identify JavaScript exceptions and stack traces
Network Analysis
- Monitor HTTP requests (
o11y_get-http-requests) - Inspect request/response headers
- Check response status codes and timing
- Identify failed or slow requests
JavaScript Debugging
- Execute diagnostic code in the page: use execute with
page.evaluate()(e.g.return await page.evaluate(() => document.querySelectorAll('script').length)). - Inspect DOM state and element properties
- Check localStorage, sessionStorage, cookies
- Verify JavaScript variables and state
Non-Blocking Debugging (Advanced)
- Tracepoints (
debug_put-tracepoint): Capture call stack and local variables at specific code locations without pausing - Logpoints (
debug_put-logpoint): Evaluate and log expressions at code locations - Exceptionpoints (
debug_put-exceptionpoint): Capture snapshots when exceptions occur - Watch Expressions (
debug_add-watch): Evaluate expressions at every tracepoint hit - Get snapshots:
debug_get-probe-snapshots(types: tracepoint, logpoint, exceptionpoint; returns tracepointSnapshots, logpointSnapshots, exceptionpointSnapshots)
For Node.js backend debugging, use PLATFORM=node and see the node-debugging skill. Node platform adds debug_get-logs; use execute for batch tool calls (no page on Node).
Error Investigation
- Use ARIA snapshot for page structure: after navigation, go-to/go-back-or-forward/reload return refs by default; otherwise call
a11y_take-aria-snapshot. Then screenshot for visual verification. - Annotated screenshot (
content_take-screenshotwithannotate: true) when you need labeled elements - HTML snapshot, check for 404s
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.
- 2d ago First seen · 73 lines · 44 tokens per session scan A 7effc66743fe
web-debugging is a skill published in the GitHub repository serkan-ozal/browser-devtools-claude (8 stars, last pushed 5mo ago), licensed MIT. It adds 44 tokens to every session and 752 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 2026-08-31.
Other skills, from other repositories
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
traceway-setup
Analyze and instrument repositories for Traceway observability. Use when the user wants to plan, add, migrate, or verify Traceway or OpenTelemetry monitoring for backend, browser, full-stack, mobile or iOS, or AI-agent software, including project topology and user-approved setup-plan creation. Backends use OTLP/HTTP…
southwest
Search Southwest Airlines fares and points pricing via Patchright browser automation. SW is not in any GDS or API. Covers all fare classes, Companion Pass value, and fare drop monitoring.