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/aryanduntley/pwa-debug-layer/chrome-devtools-coexistencenpx skills add aryanduntley/pwa-debug-layer --skill chrome-devtools-coexistencegit clone --depth 1 https://github.com/aryanduntley/pwa-debug-layerWrote 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.
[](https://agentmods.dev/skills/aryanduntley/pwa-debug-layer/chrome-devtools-coexistence)<a href="https://agentmods.dev/skills/aryanduntley/pwa-debug-layer/chrome-devtools-coexistence"><img src="https://agentmods.dev/badge/skills/aryanduntley/pwa-debug-layer/chrome-devtools-coexistence.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00067 | $0.01740 |
| Opus 5 | $0.00034 | $0.00870 |
| Sonnet 5 | $0.00013 | $0.00348 |
| Haiku 4.5 | $0.00007 | $0.00174 |
Grade A, and why
chrome-devtools-coexistence 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 5d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pwa-debug and chrome-devtools-mcp are two separate MCP servers. pwa-debug
exposes framework/store/DOM state; chrome-devtools-mcp drives the browser
(snapshots, input, performance). They share one browser: pdl_launch_browser
spawns it with the debug port live, and chrome-devtools-mcp attaches to that
port via --browserUrl. This skill covers making chrome-devtools-mcp's tools
appear after you register it, and preserving context across the restart that
sometimes requires.
When to use
- Right after
pdl_register_chrome_devtools(or a manualclaude mcp add chrome-devtools …). - When the user reports that chrome-devtools tools are not available even though the registration looks correct.
- When
pdl_check_setupreports chrome-devtools-mcp as not registered, unpinned (no--browserUrl→ it spawns its own isolated browser instead of attaching to the pwa-debug browser), or pointed at the wrong port.
The one rule that drives everything
A newly added or re-pinned MCP server only takes effect when Claude Code (re)connects it. How you trigger that depends on the install mode:
| Install mode | How chrome-devtools tools (re)load | Full restart? | Context lost? |
|---|---|---|---|
Direct MCP (claude mcp add …) |
/mcp → reconnect the server, or restart Claude Code |
Usually no (reconnect) | Only if you full-restart — see handoff |
| Plugin (bundled MCP server) | Enable in /plugins, then run /reload-plugins |
No (same session) | No |
/mcp reconnect picks up a changed registration. Verified in practice: after
claude mcp remove chrome-devtools + claude mcp add … --browserUrl http://127.0.0.1:<port>,
a /mcp → reconnect on chrome-devtools reloaded it with the new --browserUrl
and it attached to the pwa-debug browser — no full restart, no context loss.
Try /mcp reconnect first. If the client doesn't show it connected (some clients
won't load a brand-new server without a restart), fall back to a full restart and
do the context handoff below first. Plugin installs always prefer
/reload-plugins.
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.
- 5d ago First seen · 110 lines · 67 tokens per session scan A 10dccde2b751
chrome-devtools-coexistence is a skill published in the GitHub repository aryanduntley/pwa-debug-layer (0 stars, last pushed 2mo ago), licensed MIT. It adds 67 tokens to every session and 1,740 once invoked, about $0.0003 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
chrome-devtools-cli
Use this skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Chrome DevTools via CLI.
cookie-debugging
Uses Chrome DevTools MCP for inspecting, debugging, and testing cookies, session state, authentication issues, and cookie consent compliance. Use when diagnosing 401/403 errors, authentication redirects, session expiration, Cookie/Set-Cookie header issues, cookie banner consent conformance, or third-party…
a11y-debugging
Uses Chrome DevTools MCP for accessibility (a11y) debugging and auditing based on web.dev guidelines. Use when testing semantic HTML, ARIA labels, focus states, keyboard navigation, tap targets, and color contrast.
chrome-devtools
Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to --slim mode (MCP configuration).
opencli-autofix
Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.
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…