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/msapps-mobile/claude-plugins/chrome-devtools-mcp-cleanupnpx skills add MSApps-Mobile/claude-plugins --skill chrome-devtools-mcp-cleanupgit clone --depth 1 https://github.com/MSApps-Mobile/claude-pluginsWrote 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/msapps-mobile/claude-plugins/chrome-devtools-mcp-cleanup)<a href="https://agentmods.dev/skills/msapps-mobile/claude-plugins/chrome-devtools-mcp-cleanup"><img src="https://agentmods.dev/badge/skills/msapps-mobile/claude-plugins/chrome-devtools-mcp-cleanup.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 | $0.00109 | $0.01592 |
| Opus 5 | $0.00055 | $0.00796 |
| Sonnet 5 | $0.00022 | $0.00318 |
| Haiku 4.5 | $0.00011 | $0.00159 |
Grade C, and why
chrome-devtools-mcp-cleanup scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Don't `rm -rf ~/.cache/chrome-devtools-mcp/chrome-profile/` while a session is active — corrupts the running Chromium's state. How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
chrome-devtools-mcp wedge cleanup
Different server from Claude-in-Chrome. This is for
chrome-devtools-mcp(DevTools Protocol; toolsnew_page,take_snapshot,navigate_page,evaluate_script,lighthouse_audit). Not the Claude-in-Chrome extension (mcp__Claude_in_Chrome__*). Both can be down independently — see the sibling/fix-chrome-connectionskill for the extension.
Symptom
list_pages works (read-only) but every state-changing tool errors with:
The browser is already running for /Users/michalshatz/.cache/chrome-devtools-mcp/chrome-profile. Use --isolated to run multiple browser instances.
Root cause: ≥2 concurrent chrome-devtools-mcp@latest parents, each spawning Chromium pinned to the shared profile dir. The Chrome that the current MCP tries to start collides with one started by a stale MCP parent from an earlier session.
The permanent fix landed in ~/.claude.json (per-user MCP config) — the chrome-devtools server now passes --isolated so each session gets its own profile. This skill is the one-time cleanup for hosts where stale parents accumulated before that fix.
When to invoke
Use deliberately — NOT from a scheduled-task runner. Killing processes on a shared Mac is destructive; the user must opt in.
Trigger phrases: "fix chrome-devtools-mcp", "chrome-devtools wedged", "browser is already running for chrome-profile", "stale chrome-devtools parents", "card #223 cleanup".
Diagnosis
# 1. List all chrome-devtools-mcp parent processes
ps -eo pid,etime,command | awk '/chrome-devtools-mcp@latest/ && !/awk/'
# 2. List Chromium children spawned by them (pinned to chrome-profile)
ps -eo pid,ppid,etime,command \
| awk '/chrome-devtools-mcp\/chrome-profile/ && !/awk/'
# 3. Show the lock file holder
ls -la ~/.cache/chrome-devtools-mcp/chrome-profile/SingletonLock 2>/dev/null
If only ONE parent shows up: the wedge is unrelated to staleness — verify the new --isolated flag is in ~/.claude.json:
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 · 132 lines · 109 tokens per session scan C f5d345e67763
chrome-devtools-mcp-cleanup is a skill published in the GitHub repository MSApps-Mobile/claude-plugins (9 stars, last pushed 9d ago), licensed MIT. It adds 109 tokens to every session and 1,592 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
qa
Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).
web-fetch
Fetch and extract one public web source, optionally restrict its hosts, and return the content by digest with full provenance.
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…
legal-iros-registry-automation
대법원 인터넷등기소(IROS, iros.go.kr)에서 법인·부동산 등기부등본(등기사항증명서)을 여러 건 일괄 발급할 때 안전한 작업 순서와 로컬 자동화 방법을 안내합니다. 로그인·인증·결제는 사용자가 브라우저에서 직접 처리하고, 본 스킬은 장바구니 담기· 결제 후 열람·저장·종합 리포트 생성을 보조합니다. 다음과 같은 요청 시 반드시 이 스킬을 사용하세요: "법인등기부등본 100개 한번에 떼야 해", "회사 100개 등기부 정리해줘" "고객사 등기부등본 일괄 발급", "실사 대상 법인 등기 묶음 처리" "인터넷등기소 자동화", "iros.go.kr 일괄 발급"…
browser-testing
Test and debug browser code with Chrome DevTools MCP. Use when building or debugging browser UI, inspecting the DOM, capturing console errors, analyzing network requests, or verifying visual output.
vibe-behavioral-test-capture
Builds an executable safety net of characterization tests by integrating browser flow recording, API payload snapshotting, DOM state captures, network traces, and mock fixture generation.