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.
npx agentmods add rules/girijashankarj/cursor-handbook/core-principlesgit clone --depth 1 https://github.com/girijashankarj/cursor-handbookWrote 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.
[](https://agentmods.dev/rules/girijashankarj/cursor-handbook/core-principles)<a href="https://agentmods.dev/rules/girijashankarj/cursor-handbook/core-principles"><img src="https://agentmods.dev/badge/rules/girijashankarj/cursor-handbook/core-principles.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00603 | $0.00603 |
| Opus 5 | $0.00302 | $0.00302 |
| Sonnet 5 | $0.00121 | $0.00121 |
| Haiku 4.5 | $0.00060 | $0.00060 |
Grade A, and why
core-principles 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Core Architecture Principles
Design Philosophy
- Configuration over code — behavior controlled via
{{CONFIG.paths.configPath}} - Convention over configuration — sensible defaults, override when needed
- Composition over inheritance — prefer small, composable functions
- Explicit over implicit — no magic, clear data flow
- Fail fast — validate early, return clear errors
Code Organization
Directory Structure
{{CONFIG.paths.source}}/
├── {{CONFIG.folderNames.controllers}}/ # Request handlers
├── {{CONFIG.folderNames.services}}/ # Business logic
├── {{CONFIG.folderNames.models}}/ # Data models
├── {{CONFIG.folderNames.middleware}}/ # Middleware
├── {{CONFIG.folderNames.types}}/ # Type definitions
├── {{CONFIG.folderNames.utils}}/ # Utility functions
├── {{CONFIG.folderNames.common}}/ # Shared code
├── {{CONFIG.folderNames.routes}}/ # Route definitions
└── config/ # Configuration
File Naming Conventions
- Use kebab-case for file names:
user-service.ts,order-handler.ts - Use PascalCase for class files that match the class name
- Test files:
*.test.tsor*.spec.ts - Type files:
*.types.tsor in{{CONFIG.folderNames.types}}/directory - Constants:
*.constants.ts
Dependency Rules
- No circular dependencies — use dependency injection or event-based communication
- Unidirectional data flow: Controllers → Services → Models → Database
- Shared types must live in
{{CONFIG.folderNames.common}}/or{{CONFIG.folderNames.types}}/ - Internal packages use
{{CONFIG.packages.internalPrefix}}prefix
Error Handling
- Use centralized error handling middleware
- Define typed error classes extending a base
AppError - Always include: error code, message, HTTP status, correlationId
- Never expose internal error details to API consumers
- Log full error details server-side with structured logging
Logging Standards
- Use structured JSON logging
- Every log entry MUST include
correlationId - Log levels:
error→warn→info→debug - NEVER log PII, secrets, or full request/response bodies
- Include: timestamp, service name, operation, duration for performance logs
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.
- today First seen · 64 lines · 603 tokens per session scan A 81cad9e08481
core-principles is a cursor rule published in the GitHub repository girijashankarj/cursor-handbook (30 stars, last pushed 4d ago), licensed MIT. It adds 603 tokens to every session, about $0.0030 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 2026-09-03.
Other cursor rules, from other repositories
graphstack
GraphStack v4.7.1 — Orchestrated, graph-first, GNAP-tracked AI development (cross-platform).
code-optimization
Guidelines for optimizing duplicate and poorly structured code.
mcp
Guidelines for implementing and interacting with the Task Master MCP Server.
new_features
Guidelines for integrating new features into the Task Master CLI.
commands
Guidelines for implementing CLI commands using Commander.js.
git_workflow
Git workflow integrated with Task Master for feature development and collaboration.