cursor-tools-mastery

cursor-tools-mastery is a cursor rule for Cursor from madebyaris/advance-minimax-m3-cursor-rules. It costs 36 tokens per session (2,255 once invoked), scanned A, original, MIT.

A guide to Cursor 3.7’s agent workspace, including model selection, isolated worktrees, the built-in browser, and parallel agent sessions.

In plain words
What is it for?
Opening the Agents Window, selecting a model and environment, working across repositories, using isolated worktrees, verifying interfaces in the browser, and coordinating agents.
Why use it?
It helps keep work in the correct project and environment while making concurrent work easier to coordinate. It also explains how to hand off tasks with the needed context.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions subagents; names the TodoWrite tool.

Good fit Opening the Agents Window, selecting a model and environment, working across repositories, using isolated worktrees, verifying interfaces in the browser, and coordinating agents.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/madebyaris/advance-minimax-m3-cursor-rules/cursor-tools-mastery
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.

Clone the repo
git clone --depth 1 https://github.com/madebyaris/advance-minimax-m3-cursor-rules

Made for: Cursor.

Wrote 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.

agentmods badge for cursor-tools-mastery

README.md
[![agentmods](https://agentmods.dev/badge/rules/madebyaris/advance-minimax-m3-cursor-rules/cursor-tools-mastery/github.svg)](https://agentmods.dev/rules/madebyaris/advance-minimax-m3-cursor-rules/cursor-tools-mastery)
Your own site
<a href="https://agentmods.dev/rules/madebyaris/advance-minimax-m3-cursor-rules/cursor-tools-mastery"><img src="https://agentmods.dev/badge/rules/madebyaris/advance-minimax-m3-cursor-rules/cursor-tools-mastery/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.

agentmods 80×15 button for cursor-tools-mastery

Your own site · 80×15
<a href="https://agentmods.dev/rules/madebyaris/advance-minimax-m3-cursor-rules/cursor-tools-mastery"><img src="https://agentmods.dev/badge/rules/madebyaris/advance-minimax-m3-cursor-rules/cursor-tools-mastery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,255 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00036 $0.02255
Opus 5 $0.00018 $0.01128
Sonnet 5 $0.00007 $0.00451
Haiku 4.5 $0.00004 $0.00226

Measured 11d ago against content hash ceab44766fef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

cursor-tools-mastery 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.

.cursor/rules/cursor-tools-mastery.mdc · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cursor 3.7 Tools Mastery

Keep durable behavior in the core rule. Use this file for current Cursor 3.7 tool-selection patterns and the Agents Window surface.

Cursor 3.7 workspace

In Cursor 3.7, agent work is centered in the Agents Window. Open it from the command palette: Cmd+Shift+P -> Agents Window on macOS (per the Cursor 3 announcement; 3.7 changelog at cursor.com/changelog). The classic three-pane editor is still available; switch between them at any time.

  • Multi-workspace / multi-repo: the Agents Window can surface several workspaces at once. Name the repo or root path when handing off work, opening files, or running commands so edits land in the intended tree.
  • Per-session execution environment: each agent tab picks its own environment — local working tree, isolated worktree (/worktree), cloud sandbox, or remote SSH. State the environment in the handoff contract; it is the unit of isolation.
  • Per-session model picker: the model picker lives in the agent tab header (e.g. composer-2.5, MiniMax-M3, auto). Name the model in the handoff contract.
  • Integrated browser: prefer the IDE's built-in browser for local UI verification when it is exposed in your session; it matches the "snapshot-first" flow in Browser Guidance below. Cursor 3.7 adds Design Mode (multi-select elements, voice input) — user selections there are ground truth for UI edits.
  • Canvases: live React artifacts beside the chat for dashboards, reports, and structured analyses; load the canvas skill before .canvas.tsx work.

Golden Rule

For significant actions:

Check what exists
Choose the smallest correct tool
Act
Validate with the lightest useful verification

Default Tool Map

Cursor 3.7 / Composer-style agents (typical names in current desktop agents) — the session usually exposes something close to:

Step Tool / command Notes
Read a path Read Prefer over shell cat/sed
Search by pattern Grep Ripgrep-backed; use for exact symbols and strings
Search by meaning SemanticSearch "Where does X happen?" not exact text
List paths Glob File discovery by pattern
Edit in place StrReplace Surgical edits; read the file first
Create or replace whole file Write Use when there is no stable old_string to patch
Remove file Delete
Terminal Shell Builds, tests, git, installs
Web WebSearch, WebFetch
Ask user AskQuestion
Track steps TodoWrite
Delegate branch work Task Subagent-style runs (types such as explore, debugger, verifier — see schema)
Wait for background work Await Wait for a background shell, subagent, or a specific output token (e.g. Ready, Error)
Isolated worktree /worktree Run a session in its own git worktree so concurrent edits do not collide
Parallel model compare /best-of-n Run the same task across N models in parallel worktrees, then compare
MCP servers call_mcp_tool (+ resource helpers if present) Read MCP tool descriptors before calling
Plan mode SwitchMode When the product exposes a planning mode
Images GenerateImage Only when the user asks for generated images
Notebooks EditNotebook .ipynb cell edits
Lint diagnostics ReadLints After substantive edits when available
Multimodal inputs Read against attached image/video paths M3 native multimodal — treat as first-class inputs
Interactive artifact Canvas (.canvas.tsx) Dashboards, reports, MCP tabular output — load canvas skill first
Context diagnostics Context usage report canvas 3.7 — token breakdown across prompt, tools, rules, skills

Read the full file on GitHub · 173 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. 11d ago First seen · 173 lines · 36 tokens per session scan A ceab44766fef

Subscribe to this mod's changes

cursor-tools-mastery is a cursor rule published in the GitHub repository madebyaris/advance-minimax-m3-cursor-rules (125 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 2,255 once invoked, about $0.0002 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.