create

create is a cursor rule for Cursor from VoTruongDanh/Skills-Agent. It costs 53 tokens per session (769 once invoked), scanned A, original, MIT.

A set of rules for building new parts of a codebase, such as features, files, components, endpoints, pages, or scripts. It checks the project’s existing structure and routes work to relevant specialist guidance.

In plain words
What is it for?
Use it when adding a new implementation, including an API, user-interface component, database change, test, or deployment configuration.
Why use it?
It helps new code match the project’s conventions and limits unnecessary changes.

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/votruongdanh/skills-agent/create
Clone the repo
git clone --depth 1 https://github.com/VoTruongDanh/Skills-Agent

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 create

README.md
[![agentmods](https://agentmods.dev/badge/rules/votruongdanh/skills-agent/create.svg)](https://agentmods.dev/rules/votruongdanh/skills-agent/create)
Your own site
<a href="https://agentmods.dev/rules/votruongdanh/skills-agent/create"><img src="https://agentmods.dev/badge/rules/votruongdanh/skills-agent/create.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 769 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 $0.00053 $0.00769
Opus 5 $0.00026 $0.00385
Sonnet 5 $0.00011 $0.00154
Haiku 4.5 $0.00005 $0.00077

Measured 3d ago against content hash 1e7e02729618, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create 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 3d 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/create.mdc · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory Protocol

START: Read .ai-memory.md from project root. Check tech stack, coding conventions, existing patterns, architecture decisions, and file structure notes. END: Update .ai-memory.md using Memory Compaction Rules with: what was created, files touched, patterns used, decisions, and follow-ups.

Goal

Create a new implementation cleanly and with minimal disruption.

Agent Routing

  • If creating API/backend → read .kiro/skills/agents/agents/backend-specialist.md and apply its knowledge
  • If creating UI component/page → read .kiro/skills/agents/agents/frontend-specialist.md and apply its knowledge
  • If creating database schema/migration → read .kiro/skills/agents/agents/database-architect.md and apply its knowledge
  • If creating tests → read .kiro/skills/agents/agents/test-engineer.md and apply its knowledge
  • If creating deployment config → read .kiro/skills/agents/agents/devops-engineer.md and apply its knowledge

Socratic Gate

Before creating, verify:

  1. What exactly should be created? (component, page, API, script?)
  2. Does something similar already exist in the project?
  3. What is the expected behavior/output? If any answer is unclear, ASK before proceeding.

Workflow

  1. Read Memory — Load .ai-memory.md for project context, conventions, and patterns.
  2. Understand the requested artifact and the existing project structure.
  3. Identify the smallest complete implementation that satisfies the request.
  4. Create or update the necessary files only.
  5. Reuse existing patterns, naming, and architecture already present in the repo.
  6. Include basic validation and error handling.
  7. Add brief usage notes, edge cases, and follow-up improvements.
  8. Update Memory — Save what was created, patterns used, and follow-up notes to .ai-memory.md.

Checklist

  • Requirement clearly understood
  • Existing patterns/conventions checked
  • Minimal files created/modified
  • Validation and error handling included
  • Project conventions matched (naming, structure)
  • Tests added if test framework exists
  • Usage notes provided
  • Memory file updated

Read the full file on GitHub · 68 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. 3d ago First seen · 68 lines · 53 tokens per session scan A 1e7e02729618

Subscribe to this mod's changes

create is a cursor rule published in the GitHub repository VoTruongDanh/Skills-Agent (2 stars, last pushed 4mo ago), licensed MIT. It adds 53 tokens to every session and 769 once invoked, about $0.0003 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 2026-08-31.