auto-chrome-mcp-doctor

auto-chrome-mcp-doctor is a skill for Claude Code, Codex from cw02326/auto-chrome-mcp. It costs 569 tokens per session (4,822 once invoked), scanned B, original, MIT.

A troubleshooting skill for the chrome-mcp-scalemaker server, its browser extension, bridge, and tool calls. It checks the installed fork and investigates problems across the connected components.

In plain words
What is it for?
Diagnosing the server, fixing supported issues, creating a copied issue report, routing multiple Chrome profiles by port, and using the extension’s focus controls.
Why use it?
It helps locate and repair setup or connection problems without asking you to run the diagnostic commands yourself.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code.

Good fit Diagnosing the server, fixing supported issues, creating a copied issue report, routing multiple Chrome profiles by port, and using the extension’s focus controls.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cw02326/auto-chrome-mcp/skill
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.

Any agent
npx skills add cw02326/auto-chrome-mcp --skill skill
Clone the repo
git clone --depth 1 https://github.com/cw02326/auto-chrome-mcp

Made for: Claude Code, Codex.

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 auto-chrome-mcp-doctor

README.md
[![agentmods](https://agentmods.dev/badge/skills/cw02326/auto-chrome-mcp/skill.svg)](https://agentmods.dev/skills/cw02326/auto-chrome-mcp/skill)
Your own site
<a href="https://agentmods.dev/skills/cw02326/auto-chrome-mcp/skill"><img src="https://agentmods.dev/badge/skills/cw02326/auto-chrome-mcp/skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 569 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,822 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00569 $0.04822
Opus 5 $0.00284 $0.02411
Sonnet 5 $0.00114 $0.00964
Haiku 4.5 $0.00057 $0.00482

Measured 3d ago against content hash ca3962b0a091, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

auto-chrome-mcp-doctor scanned grade B 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 3d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

| **Installation** | 패키지가 PATH 에 없음 | `npm install -g auto-chrome-mcp-bridge` 실행 권유 (사용자가 sudo 필요할 수 있어 Claude 가 직접 실행 X) |
app/native-server/skill/SKILL.md · 263 lines

How it starts

The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.

auto-chrome-mcp doctor

이 스킬은 사용자가 auto-chrome-mcp (hangwin/mcp-chrome fork) 의 MCP 서버, 확장, bridge, 또는 도구 호출과 관련된 문제를 보고할 때 자동으로 진단·복구합니다.

모든 명령은 Bash tool 로 직접 실행하고 stdout/stderr 를 캡처해서 해석한 뒤 사용자에게 자연어로 답변하세요. "이 명령어를 직접 쳐주세요" 라고 사용자에게 넘기지 마세요.

먼저 auto-chrome-mcp-bridge -V 로 auto-chrome-mcp fork 인지 확인하세요. 명령이 없거나 다른 패키지 (mcp-chrome-bridge 등) 면 이 스킬은 종료하고 사용자에게 fork 안내만 합니다.


(A) Architecture in 1 minute

사용자 증상 듣고 어느 layer 가 깨졌는지 분류용 mental model:

Claude Code session                              ← 사용자가 작업하는 곳
   ↓ (stdio, .mcp.json 의 env 가 여기서 적용)
mcp-server-stdio.js                              ← bridge npm 패키지의 일부
   ↓ (HTTP fetch, URL = CHROME_PORT env override)
http://127.0.0.1:<port>/mcp                      ← bridge HTTP listener (chrome profile 별 분리)
   ↓ (in-process)
bridge (Native Messaging Host process)           ← Chrome 이 connectNative 로 spawn
   ↑ (chrome.runtime.connectNative)
extension service worker                         ← profile-scoped (각 chrome profile 마다 1개)
   ↑ (popup ↔ service worker, chrome.runtime.sendMessage)
popup UI                                         ← port 입력, 강제포커스 토글, 강제 재연결

핵심 invariant:

  • stdio-config.json 의 url 은 hardcoded 이고, mcp-server-stdio.jsprocess.env.CHROME_PORT 가 있으면 그 port 로 override (v1.0.27+)
  • chrome profile 별로 bridge process 가 분리 spawn 됨 (각자 다른 port listen)
  • popup 의 port 입력 → service worker → connectNative → bridge 가 그 port 로 listen
  • 강제포커스 토글 (chrome.storage.localforceFocusOnToolCall, default false) = chrome.windows.update({focused:true}) 게이트

(B) Diagnostic playbook — 증상 → 명령 (Claude 가 직접 실행)

중요: 모든 명령은 Bash tool 로 Claude 가 직접 실행. 사용자에게 "이거 한 번 쳐보세요" 하지 마세요. stdout/stderr 캡처해서 해석한 뒤 자연어로 답합니다.

분기 알고리즘

  1. 증상 listening → 아래 trigger 표에서 최초 매칭 1개 골라 1st command 실행.
  2. stdout 캡처doctor 결과면 (B-doctor-output) 표 따라 ❌ 항목별 후속 결정.
  3. 후속 명령 실행 후 사용자에게 결과 요약 ('doctor 결과 권한 항목 빨간불. --fix 실행해서 chmod 755 적용함. 이제 popup 다시 열어봐줄래?' 같이).
  4. 3회 시도 후 미해결 → (E) escalate → report --copy + GH Issue URL 안내.

Read the full file on GitHub · 263 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. 3d ago Changed ca3962b0a091
  2. 4d ago Changed b79111677ffe
  3. 7d ago First seen · 263 lines · 569 tokens per session scan B 1a1b633b6c0d

Subscribe to this mod's changes

auto-chrome-mcp-doctor is a skill published in the GitHub repository cw02326/auto-chrome-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 569 tokens to every session and 4,822 once invoked, about $0.0028 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

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…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

systematic-debugging

Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.

open-metadata/OpenMetadata · 37 tokens

diagnose

Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.

emdash-cms/emdash · 43 tokens

repro-admin

Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.

emdash-cms/emdash · 48 tokens

log-error-digest

Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…

zebbern/claude-code-guide · 71 tokens

byted-util-volcengine-detect-retry

An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.

bytedance/agentkit-samples · 101 tokens