Llm Coding Principles

    1

    Enforce senior-level coding standards (Surgical, Simple, Goal-Driven) on every AI-generated code change.

    Free

    20 uses4.0 (1 review)

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    llm-coding-principles

    Example session with this skill installed

    Add a 'status' field to the User model, but don't touch any other parts of the database schema or the existing API endpoints.

    • Read your context and instructions
    • Compiled the llm-coding-principles

    Approaches: 1. Add nullable column (safest). 2. Add with default 'active'.
    Choosing #2 for immediate utility.

    Success Criteria

    1. migration adds status to users.
    2. User model includes status.

    Diff

    • status = Column(String, default="active")
      Verification: Migration tested; field persists.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Expert Coding Governance for AI Agents

    Does your AI agent sometimes over-engineer simple tasks or make sweeping, unnecessary changes to your codebase? llm-coding-principles is a high-performance directive standard that installs a "Senior Engineer" persona into your agent's workflow. It replaces guesswork with a rigorous four-pillar framework: Think Before Coding, Simplicity First, Surgical Changes, and Goal-Driven Execution.

    What it does

    • Think Before Coding: Forces the agent to surface assumptions and evaluate technical trade-offs before a single line is written.
    • Simplicity First: Eliminates speculative abstractions and "future-proofing" to keep your codebase lean and maintainable.
    • Surgical Changes: Ensures diffs are precise, touching only what is necessary to satisfy the requirements while avoiding unrelated "noise" or style drift.
    • Goal-Driven Execution: Mandates a Red-Green-Refactor cycle where success criteria are defined and verified before the task is marked complete.

    Why use this skill

    Standard LLM prompting often leads to "hallucinated improvements"—refactoring code you didn't ask to change or adding dependencies you don't need. This skill acts as a non-negotiable quality gate. It’s ideal for developers using Cursor, Claude Code, or custom CLI agents who want consistent, production-grade output that mirrors the discipline of a human senior developer. It integrates seamlessly with TDD workflows and systematic debugging.

    • Not suitable for experimental or creative prototyping.
    • May resist large-scale refactors unless explicitly ordered.
    • Requires clear initial requirements to define success criteria.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    4.0
    1 review
    5
    0
    4
    1
    3
    0
    2
    0
    1
    0

    This skill has been used 20 times.

    Trust & safety

    Security scan

    Security scan passed 4 months ago

    • Free with an Agensi account

    Permissions

    No special permissions declared or detected

    Listed4 months ago

    What's inside

    Frequently Asked Questions

    This skill prevents 'AI drift' where agents over-engineer solutions or make unnecessary changes to unrelated files. It enforces a strict senior-level discipline, ensuring code is minimal, surgical, and strictly aligned with your specific goals.

    The skill is designed as a portable directive standard compatible with popular tools like Cursor, Windsurf, and Claude Code, as well as custom-built CLI agents and LLM-based IDE extensions.

    You will receive the complete framework of high-performance directives and the 'Senior Engineer' persona configuration, along with a deployment guide for integrating it into your agent's system prompts or configuration files.

    Simply copy the provided framework into your agent's .cursorrules file, system instructions, or global configuration settings to immediately begin enforcing these standards across your sessions.

    Yes, while the core pillars remain consistent, the framework is designed to satisfy high-level governance requirements across all major programming languages, from Python and JavaScript to Rust and Go.

    Not at all; by discouraging unnecessary refactors and speculative abstractions, the skill actually reduces the volume of code generated, often resulting in lower token usage and faster task completion.

    New in Agents & Orchestration