cursorrules

Repository rules for a project that uses Cursor, an AI coding editor, to recommend Claude models for prompts. They define which shared rules apply and what kinds of files belong in the repository.

In plain words
What is it for?
Use them when adding or changing hook scripts, configuration, technical documentation, test harnesses, and examples for the model-selection tool.
Why use it?
They keep contributions consistent with the project's Git, security, documentation, and public-content requirements. They also clarify that marketing and unrelated business material should stay out of the code repository.

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/coyvalyss1/model-matchmaker/cursorrules
Clone the repo
git clone --depth 1 https://github.com/coyvalyss1/model-matchmaker

Made for: Cursor.

Per session 1,515 This file is loaded in full into every session.
When invoked 1,515 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 $0.01515 $0.01515
Opus 5 $0.00758 $0.00758
Sonnet 5 $0.00303 $0.00303
Haiku 4.5 $0.00152 $0.00152

Measured 2d ago against content hash 1e072b765672, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules 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 2d 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.

.cursorrules · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Model Matchmaker - Cursor AI Rules

Shared Rules (ALWAYS apply these)

This project is independent but follows Valyss ecosystem standards. Apply ALL rules from:

  • ~/.cursorrules (global: git safety, secrets, documentation, writing voice, public content security)
  • ~/.cursor/rules/git-workflow.mdc (commit workflow)
  • ~/.cursor/rules/public-content-security.mdc (sanitization for open-source/shared content)

Project Overview

Model Matchmaker is a local Cursor hook that classifies prompts before sending and recommends the right Claude model. Three files: model-advisor.sh, session-init/track-completion hooks.


Repository Content Rules

This repo contains ONLY code and technical documentation.

What Goes in This Repo

  • Hook scripts (.sh files)
  • Configuration files (hooks.json)
  • Technical docs (README.md, AUTO_SWITCH_SETUP.md, troubleshooting)
  • Code comments and API documentation
  • Test harnesses and examples

What Does NOT Go Here

  • Marketing content (release posts, social media copies, promotion materials)
  • Business planning (strategy docs, roadmap justifications, partnerships)
  • Personal drafts (pre-write content, brainstorms, unfinished ideas)

All marketing/business content goes to: a separate private directory outside this repo (e.g., ~/private-docs/model-matchmaker-release/)

This ensures the repo stays technical and doesn't accidentally expose business decisions to the public.

Git Workflow

Commit Early, Commit Often

  • Commit after each logical unit (one feature, one fix, one refactor)
  • Commit messages explain WHY, not just WHAT
  • Format: <type>: <message> where type is one of: feat, fix, refactor, docs, test, chore

Examples

feat: add auto-switch feature for automatic model changing
fix: handle edge case in prompt classification for long analytics strings  
docs: update README with auto-switch setup instructions
refactor: extract keyword lists into separate configuration arrays
chore: update analytics script output format

Read the full file on GitHub · 192 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. 2d ago First seen · 192 lines · 1,515 tokens per session scan A 1e072b765672

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository coyvalyss1/model-matchmaker (167 stars, last pushed 4mo ago), licensed MIT. It adds 1,515 tokens to every session, about $0.0076 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.