Chromium Browser
SkillWeb & browsingUse Chrome DevTools through PRB's shared attach-only Chromium browser for browsing, debugging, automation, visual inspection, console or network analysis, performance or memory profiling, screencasts, and Wayback Machine research.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the Chromium Browser skill
What this skill tells your AI
The instructions your AI receives, as published by paulrberg/agent-skills in skills/chromium-browser/SKILL.md and read by ahel’s review.
Operate the configured Chrome DevTools MCP against the existing shared browser without disrupting unrelated tabs or authenticated state.
Environment Contract
- Treat
~/.local/libexec/mcp/chrome-devtoolsand the tools exposed in the current session as authoritative. The wrapper owns server versioning, flags, logging, and browser attachment; do not run the MCP package directly. - The MCP attaches to an existing remote-debugging browser. Never launch a fallback browser or create another profile when attachment fails.
- Treat the browser as shared, authenticated, and concurrently used by the user and other agents. Inspect only pages relevant to the task and do not surface unrelated tab titles or content.
- Trust the live tool inventory; an absent tool is unavailable in this session. Do not advise editing client MCP configuration as a troubleshooting shortcut.
Reference Routing
For Wayback Machine capture discovery or replay research, read references/wayback-machine.md before making any Wayback
request. Otherwise do not load it. Discover captures through serialized APIs outside Chromium, then open only the
selected replay when rendered inspection adds evidence.
Page Ownership
- Call
list_pagesbefore interacting and preserve the initial pages as pre-existing state. - Prefer
new_pagewithbackground: truewhen a fresh page satisfies the task. Record the exactpageIdreturned by every page this task creates; never infer ownership from a later page-list difference. - Pass an explicit
pageIdto every page-scoped tool. Do not rely on selected-page state; useselect_pageonly when deliberately bringing a page to the foreground. - Navigate or mutate a pre-existing page only when the task explicitly depends on that page's current state. Never close a pre-existing page.
- At completion, close only the recorded pages created by this task unless the user asked to leave one open.
Interaction and Evidence
- On one page, navigate, wait for a useful known signal, take a fresh snapshot, then interact with identifiers from that snapshot. Refresh it after navigation or meaningful DOM changes.
- Prefer
take_snapshotfor structure and automation,take_screenshotfor visual evidence, andevaluate_scriptfor information absent from the accessibility tree. Accept wrapper screenshot defaults unless the task requires lossless or full-resolution output. - Keep action responses small with
includeSnapshot: falseunless the updated state is immediately needed. Paginate and filter console, network, memory, and other high-volume results. - When a cookie consent popup appears, select only necessary or essential cookies by default, including through its settings when needed. If no such option is available, accept all cookies and continue.
- Use
filePathfor large screenshots, snapshots, traces, recordings, or response bodies, writing only to a task-authorized workspace path or a temporary location. Unrestricted path capability is not write authorization. - Parallelize independent pages when useful, but preserve causal order for calls targeting the same page.
Authority and Privacy
- Read-only inspection of task-relevant authenticated state is allowed when the task calls for it. Submitting forms, changing accounts, installing extensions, making purchases, or causing another external mutation requires the same authority that action would require outside the browser.
- Network-header redaction is an intentional server boundary. Do not bypass it or seek credentials through page or process introspection.
Troubleshooting
- On attachment or transport failure, distinguish the browser endpoint from the MCP process: check the debugging
endpoint at
http://127.0.0.1:${PRB_AGENT_CHROMIUM_PORT:-9222}/json/version, then inspect the newest per-process log under$XDG_CACHE_HOME/chrome-devtools-mcp/logs/or, when unset,~/.cache/chrome-devtools-mcp/logs/. - Expect Chromium to remain healthy when an MCP transport drops. Report which layer failed and the supporting evidence; do not launch another browser, edit client configuration, or change wrapper flags unless the user explicitly requests configuration work.
- When a requested capability is missing, confirm the current tool inventory and wrapper configuration, then report the boundary. Do not invent a fallback that weakens the configured privacy or concurrency defaults.
Completion requires fresh tool evidence for the requested outcome and confirmation that task-created pages were either closed or intentionally left open.
Signals
- GitHub stars
- 70
- Forks
- 3
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
chromium-browser- Source
- github.com/paulrberg/agent-skills