command_line_tools

A set of command-line project tools, including an image processor and a webpage-to-Markdown converter. They are run from a terminal after installing dependencies and setting any required API keys.

In plain words
What is it for?
It helps optimize images by removing backgrounds, resizing, changing formats, and setting quality. It also helps scrape webpage content and convert HTML into Markdown.
Why use it?
It keeps common file and webpage conversion tasks in repeatable commands instead of requiring manual work or separate scripts. Some tasks may need a Replicate API token stored in the project environment.

Cursor rule for Cursor

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.

agentmods
npx agentmods add rules/lastbotinc/cursor-rules-tools/command_line_tools
Clone the repo
git clone --depth 1 https://github.com/LastBotInc/cursor-rules-tools

Made for: Cursor.

Per session 4,606 This file is loaded in full into every session.
When invoked 4,606 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.04606 $0.04606
Opus 5 $0.02303 $0.02303
Sonnet 5 $0.00921 $0.00921
Haiku 4.5 $0.00461 $0.00461

Measured yesterday against content hash 7e939218b8bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

command_line_tools 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 yesterday.

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.

.cursor/rules/command_line_tools.mdc · 373 lines

How it starts

The opening of the file, as written. The whole thing — 373 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<command_line_tools>

Project-Specific Tools: Execute these using run_terminal_cmd.

🔧 Setup: Run npm install and configure API keys in .env.local (see .env.example)

{ "tools": { "image-optimizer": { "description": "Optimizes images with background removal, resizing, and format conversion using Sharp and Replicate's remove-bg model", "tool": "run_terminal_cmd", "command": "npm run optimize-image", "status": "✅ Tested and working", "options": { "input": "Path to input image", "output": "Path to output image", "remove-bg": "(Optional) Remove image background using AI", "resize": "(Optional) Resize image (format: WIDTHxHEIGHT, e.g. 800x600)", "format": "(Optional) Convert to format (png, jpeg, or webp)", "quality": "(Optional) Set output quality (1-100, default: 80)" }, "requires": [ "REPLICATE_API_TOKEN in .env.local (for background removal)", ], "example": "npm run optimize-image -- -i input.png -o output.webp --resize 512x512 --format webp --quality 90", "note": "Use -i and -o flags for input/output. Background removal requires Replicate API token." }, "html-to-md": { "description": "Scrapes a webpage and converts its HTML content to Markdown format using Turndown service", "tool": "run_terminal_cmd", "command": "npm run html-to-md", "status": "✅ Tested and working", "options": { "url": "URL of the webpage to scrape", "output": "(Optional) Output file path for the markdown (default: output.md)", "selector": "(Optional) CSS selector to target specific content" }, "requires": [ ], "example": "npm run html-to-md -- --url https://example.com --output docs/scraped.md --selector main" }, "gemini": { "description": "Interacts with Google's Gemini API for text generation, chat, multimodal tasks, document analysis, and grounded search", "tool": "run_terminal_cmd", "command": "npm run gemini", "status": "✅ Tested and working", "options": { "prompt": "Text prompt or question for the model", "model": "(Optional) Model to use: 'gemini-2.0-flash' (default), 'gemini-2.5-pro-exp-03-25'", "temperature": "(Optional) Sampling temperature between 0.0 and 1.0 (default: 0.7)", "max-tokens": "(Optional) Maximum tokens to generate (default: 2048)", "image": "(Optional) Path to image file for vision tasks", "file": "(Optional) Path to local file (PDF, DOCX, TXT, etc.) for document analysis", "url": "(Optional) URL to a document to analyze (PDF, DOCX, TXT, etc.)", "mime-type": "(Optional) MIME type of the file (e.g., application/pdf, default: auto-detected)", "chat-history": "(Optional) Path to JSON file containing chat history", "stream": "(Optional) Stream the response (default: false)", "safety-settings": "(Optional) JSON string of safety threshold configurations", "schema": "(Optional) JSON schema for structured output", "json": "(Optional) Return structured JSON data. Available types: recipes, tasks, products, custom", "ground": "(Optional) Enable Google Search grounding for up-to-date information (default: false)", "show-search-data": "(Optional) Show the search entries used for grounding (default: false)" }, "requires": [ "GOOGLE_AI_STUDIO_KEY or GEMINI_API_KEY in .env.local", "@google/generative-ai package (auto-installed with npm install)", "node-fetch package (auto-installed with npm install)"

Read the full file on GitHub · 373 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. yesterday First seen · 373 lines · 4,606 tokens per session scan A 7e939218b8bd

Subscribe to this mod's changes

command_line_tools is a cursor rule published in the GitHub repository LastBotInc/cursor-rules-tools (3 stars, last pushed 1y ago), licensed MIT. It adds 4,606 tokens to every session, about $0.0230 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.