Borrowing it
Nothing to install: this file belongs to TranHuyQn/cc-chrome-extension. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/TranHuyQn/cc-chrome-extension/claude/claude-code-chrome-extension-q9a5sg/.claude/commands/ccchrome.mdgit clone --depth 1 https://github.com/TranHuyQn/cc-chrome-extensionWrote 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/commands/tranhuyqn/cc-chrome-extension/ccchrome)<a href="https://agentmods.dev/commands/tranhuyqn/cc-chrome-extension/ccchrome"><img src="https://agentmods.dev/badge/commands/tranhuyqn/cc-chrome-extension/ccchrome/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/tranhuyqn/cc-chrome-extension/ccchrome"><img src="https://agentmods.dev/badge/commands/tranhuyqn/cc-chrome-extension/ccchrome.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00024 | $0.02064 |
| Opus 5 | $0.00012 | $0.01032 |
| Sonnet 5 | $0.00005 | $0.00413 |
| Haiku 4.5 | $0.00002 | $0.00206 |
Grade C, and why
ccchrome scanned grade C with 2 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 9d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://github.com/TranHuyQn/cc-chrome-extension/releases/latest/download/install.sh | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Bash(curl:*), Bash(claude mcp:*), Bash(cat:*), Bash(node:*), Bash(bash:*), Bash(tail:*), Bash(uname:*), Read, Write How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bạn đang quản lý Claude Code Chrome Bridge chạy như một dịch vụ nền trên chính máy này (cài bằng
scripts/install.sh, xem README mục Cài đặt). Không còn server dùng chung/VPS, không còn pairing
secret — mỗi máy tự chạy bridge riêng, mỗi bridge một token riêng.
File trạng thái: ~/.ccchrome.json — nội dung {"token": "...", "port": 23949}, do install.sh tạo.
Thư mục cài đặt: ~/.cc-chrome-bridge/ (mã nguồn, logs/, service-unit.sh, tokens.json).
Subcommand người dùng gõ: $ARGUMENTS (không có thì coi là status).
status
Mục tiêu: báo bridge có đang chạy không và extension đã nối vào chưa.
- Đọc
~/.ccchrome.jsonbằngcat. Không có file này → báo "chưa cài — chạy/ccchrome install" rồi dừng lại, không làm các bước dưới. - Lấy
porttừ file đó (mặc định23949nếu thiếu trường này). Gọi:curl -sS --max-time 5 http://127.0.0.1:<port>/health- Không có phản hồi / connection refused → bridge không chạy. Báo vậy và gợi ý
/ccchrome restart(dịch vụ nền có thể đã bị dừng hoặc crash). - Có phản hồi JSON
{"ok":true,"version":"...","extensionsConnected":N,"mcpSessions":M}→ bridge đang sống. ĐọcextensionsConnected:0→ extension chưa nối. Nhắc người dùng: bấm icon extension trong Chrome, kiểm tra "Địa chỉ MCP server" đã đúngws://127.0.0.1:<port>/ws?token=<token trong ~/.ccchrome.json>chưa, bấm "Lưu & kết nối lại" nếu cần.> 0→ extension đã nối, báo thành công.
- Không có phản hồi / connection refused → bridge không chạy. Báo vậy và gợi ý
- Kiểm tra thêm
claude mcp get chromeđể xác nhận MCP serverchromeđã đăng ký cho Claude Code (registered bởiinstall.sh). Chưa có → gợi ý chạy lại/ccchrome install. - Tóm tắt ngắn gọn: bridge sống/chết, extension nối/chưa, MCP đã đăng ký/chưa.
install
Mục tiêu: chỉ đường, không tự chạy gì cả — cài đặt ghi vào $HOME và cài một dịch vụ nền, việc đó
người dùng phải tự quyết định chạy khi nào.
In ra đúng lệnh sau và dừng, không thực thi:
curl -fsSL https://github.com/TranHuyQn/cc-chrome-extension/releases/latest/download/install.sh | bash
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.
- 9d ago First seen · 130 lines · 24 tokens per session scan C 2057eeb21dda
ccchrome is a command published in the GitHub repository TranHuyQn/cc-chrome-extension (4 stars, last pushed 9d ago), licensed MIT. It adds 24 tokens to every session and 2,064 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
qa
Dispatch a verifiable browser task to the qa-tester subagent. Use for regression checks, smoke tests, and any task with a clean pass/fail outcome. Supports an EXHAUSTIVE mode that verifies every control behind an honesty gate.
playbook
Manage Mochi playbooks (list, show, run, delete). Plays through the browser MCP tools.
unschedule-playbook
Cancel a scheduled playbook routine.
check-browser
Use Real Browser MCP to check what's currently showing in my browser.
design-qa
Agent-driven design QA — walk the running app, judge design/UX, and drop a Comment-Mode comment on every issue (visible to the human as pins). Then read the session back and fix everything in bulk. Optional focus argument steers the pass.
checkpoint
Write a new link in the continuum chain summarizing decisions/changes since the last link.