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/fix-chrome-connectionnpx skills add MSApps-Mobile/claude-plugins --skill fix-chrome-connectiongit 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/fix-chrome-connection)<a href="https://agentmods.dev/skills/msapps-mobile/claude-plugins/fix-chrome-connection"><img src="https://agentmods.dev/badge/skills/msapps-mobile/claude-plugins/fix-chrome-connection.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 | $0.00025 | $0.00514 |
| Opus 5 | $0.00013 | $0.00257 |
| Sonnet 5 | $0.00005 | $0.00103 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
fix-chrome-connection 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 4d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This is an automated run of a scheduled task. The user is not present to answer questions. Make reasonable choices autonomously and note them in your output. For "write" actions, only take them if explicitly required by the task. When in doubt, produce a report of what you found.
You are fixing a broken Chrome MCP connection. Work through these steps in order, stopping as soon as the connection works.
Step 1: Test current connection
Call tabs_context_mcp with createIfEmpty: false.
- If it responds (any response other than a connection error) → report "Chrome is already connected!" and stop.
- If it fails with a connection error → note it and continue.
Step 2: Screenshot the current desktop state
screencapture -x /tmp/chrome_check.png
sips -Z 1920 /tmp/chrome_check.png --out /tmp/chrome_check_small.png
Copy to workspace and Read it. Note what's visible (Chrome open? which app is in focus? any errors?).
Step 3: Open Chrome
open -a "Google Chrome"
sleep 3
Retry connection test. If connected → report success and stop.
Step 4: Quit and relaunch Chrome ← MOST RELIABLE FIX
Do NOT attempt to click UI elements on chrome://extensions — the Claude desktop app steals focus from Chrome, making coordinate-based clicking fail. Go straight to quit+relaunch:
osascript -e 'tell application "Google Chrome" to quit'
sleep 5
open -a "Google Chrome"
sleep 8
Retry connection test. If connected → report success and stop.
Step 5: Report failure and ask the user
If all automated steps failed, report:
- Every step attempted and what happened
- Current state of Chrome (from last screenshot)
- Ask: "Are you logged into the correct Chrome profile? After switching macOS users, Chrome may open under a different profile where the extension isn't installed."
Step 6: Last resort
If the profile check doesn't help, suggest reinstalling the Claude in Chrome extension: open chrome://extensions → remove Claude in Chrome → reinstall from Chrome Web Store.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 68 lines · 25 tokens per session scan A 90e769c85b32
fix-chrome-connection is a skill published in the GitHub repository MSApps-Mobile/claude-plugins (9 stars, last pushed 8d ago), licensed MIT. It adds 25 tokens to every session and 514 once invoked, about $0.0001 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
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.
consult-gov-grant
나에게 맞는 정부·공공기관 지원사업을 찾아주고, 심사 기준에 맞춘 사업계획서·신청서 초안을 만들어 드립니다(Word·한글·Excel 파일까지). 창업자·소상공인·중소기업·연구자·비영리단체·개인 누구나 쓸 수 있습니다. 다음과 같은 요청 시 사용하세요: "정부 지원사업 찾아줘" "우리 상황에 맞는 지원금 있어?" "사업계획서 초안 써줘" "지원서 작성 도와줘" "이 신청서 심사 기준으로 검토해줘" "마감 전에 뭐 준비해야 해?" "예비창업패키지 신청서 만들어줘" "지원금 어떻게 쓰는지 모르겠어" 지원사업 탐색·신청서 작성·서류 검토·일정 관리까지 도와주며, 마지막에…
data-realestate
국토교통부 실거래가 신고 데이터로 아파트·오피스텔·연립다세대·단독다가구·상업업무용 부동산의 매매·전월세 시세를 조회해 드립니다(별도 API 키 없이 바로 사용). 다음과 같은 요청 시 사용하세요: "잠실 리센츠 2024년 매매 실거래가 찾아줘" "강남구 아파트 실거래가 알려줘" "마포구 아파트 전세 실거래 보여줘" "성수동 오피스텔 월세 시세 조회해줘" "용산구 상업업무용 건물 거래내역 찾아줘" "전세 보증금 추이 알려줘" "이 단지 평형별 시세 비교해줘" 지역·단지·거래년월로 실거래를 조회해 중위값·최소·최대와 대표 거래를 요약하고, 입지 분석이나 투자 검토로…