comol/ai_rules_1c

Rules\skills\subagens for vibecoding in 1C(bsl)

What it solves

This project provides a standardized, portable framework of rules, agent roles, and tools for developing 1C:Enterprise (BSL) software using AI agents. It addresses the challenge of maintaining consistent development standards, testing protocols, and project-specific configurations across various AI coding assistants.

How it works

The project uses a unified installer to deploy a set of rules and instructions into your local development environment. It defines four key operational pillars: Mode (the type of task, e.g., quick fix vs. full cycle), Quality (the depth of code analysis and validation), Orchestration (how tasks are delegated to sub-agents), and UI-Tests (automated interface verification). These settings are managed via slash-commands and a project-specific .dev.env file, ensuring that the AI agent follows the same logic regardless of which coding tool is being used.

Who it’s for

This is designed for 1C developers who use AI-powered coding assistants (such as Cursor, Claude Code, or Cline) and want to enforce strict, repeatable development workflows, automated testing, and code quality gates within their 1C projects.

Highlights

  • Multi-Tool Support: Compatible with a wide range of AI coding assistants including Cursor, Claude Code, Codex, OpenCode, Kilo Code, and others.
  • Configurable SDLC: Offers granular control over development cycles, from simple "quick fixes" to "full cycle" development with automated verification.
  • Automated UI Testing: Integrates with 1C-QA mechanisms to perform automated interface testing without relying on brittle screenshot-based methods.
  • Self-Improving Rules: Includes a mechanism (/evolve) to capture and incorporate user feedback into the agent's behavior over time.
  • Model-Specific Adaptation: Provides profiles to optimize agent behavior based on the specific LLM being used (e.g., Claude Opus, Sonnet, or GPT models).

Related

  • Project
    ai-driven-dev/framework

    An enterprise-grade SDLC framework that integrates standardized workflows, skills, and agents into AI coding tools to automate the path from idea to pull request.

  • Project
    HoangNguyen0403/agent-skills-standard

    A portable SDLC standards layer for AI coding agents that turns engineering rules into modular, version-controlled skills to reduce token usage and ensure consistent code quality.

  • Project
    ai-sdlc-framework/ai-sdlc

    AI‑SDLC is an open‑source decision‑engine framework that orchestrates AI‑assisted software development. It front‑loads human decisions via a Definition‑of‑Ready gate, then automatically runs a 13‑step pipeline (code generation, three independent LLM reviewers, DSSE attestation, PR creation) using an autonomous orchestrator. The system includes a terminal UI, declarative governance resources, and SDKs for TypeScript, Python, and Go. Licensed under Apache 2.0, it targets enterprises and platform teams that need reproducible, governed AI‑driven code pipelines.

  • Dispatch
    Building Effective AI Agents: Anthropic's Guide to Agentic Systems

    Anthropic outlines a framework for building AI agents by prioritizing simple, composable patterns over complex frameworks, distinguishing between predictable workflows and autonomous agents.

  • Dispatch
    Integrating UML Modeling into AI-Driven Development Life Cycles

    An exploration of AI-DLC-UML, a framework designed to bridge the AI-driven software development workflow with structured UML modeling for collaborative design.