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 skills add southlab-ai/Claude-Plugin-Marketplace --skill cv-helpgit clone --depth 1 https://github.com/southlab-ai/Claude-Plugin-MarketplaceWrote 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/southlab-ai/claude-plugin-marketplace/cv-help)<a href="https://agentmods.dev/skills/southlab-ai/claude-plugin-marketplace/cv-help"><img src="https://agentmods.dev/badge/skills/southlab-ai/claude-plugin-marketplace/cv-help/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/skills/southlab-ai/claude-plugin-marketplace/cv-help"><img src="https://agentmods.dev/badge/skills/southlab-ai/claude-plugin-marketplace/cv-help.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 | $0.00000 | $0.00794 |
| Opus 5 | $0.00000 | $0.00397 |
| Sonnet 5 | $0.00000 | $0.00159 |
| Haiku 4.5 | $0.00000 | $0.00079 |
Grade A, and why
cv-help 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 11d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CV Plugin Help
Show available Computer Vision tools and usage examples.
Available Tools
| Tool | Description |
|---|---|
cv_list_windows |
List all visible windows with HWND, title, process, rect |
cv_screenshot_window |
Capture a specific window by HWND |
cv_screenshot_desktop |
Capture the entire desktop (all monitors) |
cv_screenshot_region |
Capture a rectangular region of the screen |
cv_focus_window |
Bring a window to the foreground |
cv_mouse_click |
Click at screen coordinates (left/right/double/middle/drag) |
cv_type_text |
Type text into the foreground window |
cv_send_keys |
Send key combinations (Ctrl+S, Alt+Tab, etc.) |
cv_move_window |
Move/resize a window or maximize/minimize/restore |
cv_ocr |
Extract text from a window or region with bounding boxes and confidence |
cv_find |
Find elements by natural language query (UIA + OCR fuzzy search) |
cv_get_text |
Extract all visible text from a window (UIA primary, OCR fallback) |
cv_list_monitors |
List all monitors with resolution, DPI, and position |
cv_read_ui |
Read the UI accessibility tree of a window |
cv_wait_for_window |
Wait for a window matching a title pattern to appear |
cv_wait |
Simple delay (max 30 seconds) |
Quick Start Examples
Find and click an element by description:
cv_find(query="Submit button", hwnd=<HWND>)— finds matching elements- Click the returned bbox center with
cv_mouse_click
Extract text from any app:
cv_get_text(hwnd=<HWND>)— UIA for native apps, OCR fallback for Chrome/Electron
List windows and take a screenshot:
- Call
cv_list_windowsto see all open windows - Find the HWND of the window you want
- Call
cv_screenshot_windowwith that HWND
Click a button in an app:
cv_screenshot_windowto see the current state- Identify the button coordinates from the screenshot
cv_mouse_clickat those coordinates
Drag and drop (works with WebView, UWP, Electron, WPF apps):
cv_mouse_click(x=<END_X>, y=<END_Y>, start_x=<START_X>, start_y=<START_Y>, hwnd=<HWND>)— drag from start to end- Optionally tune speed with
drag_duration_ms(default 300ms)
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.
- 11d ago First seen · 62 lines · 0 tokens per session scan A afeff1842a59
cv-help is a skill published in the GitHub repository southlab-ai/Claude-Plugin-Marketplace (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 794 tokens. 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
dingtalk_channel_connect
A browser-based setup guide for connecting a MateClaw assistant to DingTalk, a Chinese workplace messaging platform. It creates and configures a DingTalk application, then publishes the configuration.
browser_cdp
A health check for Python code that produces a score, letter grade, and measures of issues such as complexity, duplication, dead code, dependencies, and architecture.
browser_visible
Instructions for starting and controlling a real web browser either visibly or in the background. A visible browser shows its window so a person can watch, log in, or help with a task.
shogun-screenshot
A screenshot tool for getting images from a computer or web page and then cropping, resizing, or masking sensitive information. Playwright is a browser-automation tool used here to capture web pages.
browser-doctor
Read-only health check on browser-control setup. Verifies browser binary, Playwright MCP Bridge extension presence, token file mode/contents, AIWG MCP registration, provider config injection, and optional workspace allow-list. Outputs pass/fail per check with remediation commands.
browser_scripts
Visual browser automation script editor & manager for TubeCLI.