smart-entry-points

Context-based routing rules that choose which project rules an AI coding assistant should use from the files and task being worked on.

In plain words
What is it for?
Use them when working on frontend files such as React, Next.js, or stylesheets, or backend Python API and service files, so the relevant rules are selected.
Why use it?
They reduce the need to search through every rule manually and help apply related frontend or backend guidance together with required setup checks.

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/rm2thaddeus/pixel_detective/smart-entry-points
Clone the repo
git clone --depth 1 https://github.com/rm2thaddeus/Pixel_Detective

Made for: Cursor.

Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,171 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00010 $0.02171
Opus 5 $0.00005 $0.01086
Sonnet 5 $0.00002 $0.00434
Haiku 4.5 $0.00001 $0.00217

Measured 2d ago against content hash 5d2539f6142f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

smart-entry-points 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.

.cursor/rules/smart-entry-points.mdc · 320 lines

How it starts

The opening of the file, as written. The whole thing — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Smart Entry Points - Intelligent Rule Routing System

🎯 Context-Aware Rule Activation

This file defines automatic routing logic for AI assistants to apply the right rules based on work context.


Automatic Context Detection Rules

File Pattern → Rule Mapping

Frontend Development Context
file_patterns:
  - "frontend/**/*.tsx"
  - "frontend/**/*.ts" 
  - "frontend/**/*.jsx"
  - "frontend/**/*.js"
  - "frontend/**/*.css"
  - "frontend/**/*.scss"

primary_rule: "@frontend-development-index"
secondary_rules:
  - "@nextjs-hydration-prevention"      # For React components
  - "@react-query-api-integration"      # For API calls
  - "@component-architecture-patterns"  # For component design
  - "@ux-workflow-patterns"            # For UX work
  - "@nextjs-performance-optimization" # For performance

prerequisites:
  - "@sprint-lessons-learned"  # Always check Sprint 10 lessons
  - "@mcp-browser-tools-setup" # Verify MCP setup for frontend work
Backend Development Context
file_patterns:
  - "backend/**/*.py"
  - "src/**/*.py"
  - "**/*api*.py"
  - "**/*service*.py"
  - "**/*model*.py"

primary_rule: "@backend-development-index"
secondary_rules:
  - "@fastapi-dependency-injection"     # For API development
  - "@api-design-patterns"             # For API design
  - "@fastapi-microservice-patterns"   # For service architecture
  - "@ml-service-integration"          # For ML services

prerequisites:
  - "@sprint-lessons-learned"  # Always check Sprint 10 lessons
  - "@use-mcp-servers"        # For Supabase MCP usage
Database Work Context
file_patterns:
  - "**/*.sql"
  - "**/migrations/**"
  - "**/database/**"
  - "**/schemas/**"

primary_rule: "@use-mcp-servers"
focus: "Supabase MCP operations"
secondary_rules:
  - "@api-design-patterns"  # For data modeling
  
prerequisites:
  - "@sprint-lessons-learned"  # Check for database-related lessons
Testing Context
file_patterns:
  - "**/*.test.ts"
  - "**/*.test.tsx"
  - "**/*.test.py"
  - "**/*.spec.*"
  - "**/tests/**"

primary_rule: "@sprint10-testing-patterns"
secondary_rules:
  - "@nextjs-hydration-prevention"    # For frontend tests
  - "@fastapi-dependency-injection"   # For backend tests
  - "@mcp-browser-tools-setup"       # For MCP testing

prerequisites:
  - "@sprint-lessons-learned"  # Apply testing lessons learned

Read the full file on GitHub · 320 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 · 320 lines · 10 tokens per session scan A 5d2539f6142f

Subscribe to this mod's changes

smart-entry-points is a cursor rule published in the GitHub repository rm2thaddeus/Pixel_Detective (21 stars, last pushed 7mo ago), licensed MIT. It adds 10 tokens to every session and 2,171 once invoked, about $0.0001 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.