cursor-tools

A command-line tool for asking AI models questions and generating implementation plans from a code repository. A command-line tool is a program operated by typing commands in a terminal.

In plain words
What is it for?
Use it to ask supported AI models questions, plan changes such as adding authentication, identify relevant repository files, and choose providers for file analysis or plan generation.
Why use it?
It helps when a direct AI question lacks code context or when you need a plan based on the files and structure of a project. The planning command identifies relevant files and uses their contents to produce a plan.

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/instructa/viber3d/cursor-tools
Clone the repo
git clone --depth 1 https://github.com/instructa/viber3d

Made for: Cursor.

Per session 3,032 This file is loaded in full into every session.
When invoked 3,032 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 $0.03032 $0.03032
Opus 5 $0.01516 $0.01516
Sonnet 5 $0.00606 $0.00606
Haiku 4.5 $0.00303 $0.00303

Measured yesterday against content hash 2e90f49bf5dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursor-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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.cursor/rules/cursor-tools.mdc · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cursor-tools is a CLI tool that allows you to interact with AI models and other tools. cursor-tools is installed on this machine and it is available to you to execute. You're encouraged to use it.

Direct Model Queries: cursor-tools ask "<your question>" --provider <provider> --model <model> - Ask any model from any provider a direct question (e.g., cursor-tools ask "What is the capital of France?" --provider openai --model o3-mini). Note that this command is generally less useful than other commands like repo or plan because it does not include any context from your codebase or repository.

Implementation Planning: cursor-tools plan "<query>" - Generate a focused implementation plan using AI (e.g., cursor-tools plan "Add user authentication to the login page") The plan command uses multiple AI models to:

  1. Identify relevant files in your codebase (using Gemini by default)
  2. Extract content from those files
  3. Generate a detailed implementation plan (using OpenAI o3-mini by default)

Plan Command Options: --fileProvider=: Provider for file identification (gemini, openai, anthropic, perplexity, modelbox, or openrouter) --thinkingProvider=: Provider for plan generation (gemini, openai, anthropic, perplexity, modelbox, or openrouter) --fileModel=: Model to use for file identification --thinkingModel=: Model to use for plan generation --debug: Show detailed error information

Web Search: cursor-tools web "<your question>" - Get answers from the web using a provider that supports web search (e.g., Perplexity models and Gemini Models either directly or from OpenRouter or ModelBox) (e.g., cursor-tools web "latest shadcn/ui installation instructions") when using web for complex queries suggest writing the output to a file somewhere like local-research/.md.

Web Command Options: --provider=: AI provider to use (perplexity, gemini, modelbox, or openrouter) --model=: Model to use for web search (model name depends on provider) --max-tokens=: Maximum tokens for response

Repository Context: cursor-tools repo "<your question>" [--subdir=<path>] - Get context-aware answers about this repository using Google Gemini (e.g., cursor-tools repo "explain authentication flow"). Use the optional --subdir parameter to analyze a specific subdirectory instead of the entire repository (e.g., cursor-tools repo "explain the code structure" --subdir=src/components)

Documentation Generation: cursor-tools doc [options] - Generate comprehensive documentation for this repository (e.g., cursor-tools doc --output docs.md) when using doc for remote repos suggest writing the output to a file somewhere like local-docs/.md.

GitHub Information: cursor-tools github pr [number] - Get the last 10 PRs, or a specific PR by number (e.g., cursor-tools github pr 123) cursor-tools github issue [number] - Get the last 10 issues, or a specific issue by number (e.g., cursor-tools github issue 456)

ClickUp Information: cursor-tools clickup task <task_id> - Get detailed information about a ClickUp task including description, comments, status, assignees, and metadata (e.g., cursor-tools clickup task "task_id")

Model Context Protocol (MCP) Commands: Use the following commands to interact with MCP servers and their specialized tools: cursor-tools mcp search "<query>" - Search the MCP Marketplace for available servers that match your needs (e.g., cursor-tools mcp search "git repository management") cursor-tools mcp run "<query>" - Execute MCP server tools using natural language queries (e.g., cursor-tools mcp run "list files in the current directory" --provider=openrouter). The query must include sufficient information for cursor-tools to determine which server to use, provide plenty of context.

The search command helps you discover servers in the MCP Marketplace based on their capabilities and your requirements. The run command automatically selects and executes appropriate tools from these servers based on your natural language queries. If you want to use a specific server include the server name in your query. E.g. cursor-tools mcp run "using the mcp-server-sqlite list files in directory --provider=openrouter"

Read the full file on GitHub · 166 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 · 166 lines · 3,032 tokens per session scan A 2e90f49bf5dd

Subscribe to this mod's changes

cursor-tools is a cursor rule published in the GitHub repository instructa/viber3d (623 stars, last pushed 1y ago), licensed MIT. It adds 3,032 tokens to every session, about $0.0152 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 2026-08-30.