1c-dev-rules

A plugin bundling 30 skills for 1C development standards based on v8std, plus a task pipeline from planning to release with approval and code-review gates

Plugin

Medium risk

We rate an entry medium when the tool runs code, makes network calls or reads project files. Check what exactly it does before installing.

Why this level

  • The pipeline's development stage writes code and configuration metadata within the task specification's bounds
  • Validation scripts create and modify artifacts in the project directory
All reasons and checks
Russian stack

roman-repo/1c-dev-rules

Install

Manual install

https://github.com/Roman-repo/1c-dev-rules

In ZCode: Settings → Plugin Management → Discover → paste this URL and click Install.

This is third-party code. Review the repository files before installing.

What it does

The plugin packages 1C development standards (a rework of v8std and ai_rules_1c) into 30 topical skills (queries, forms, metadata, transactions, permissions, integrations, tests and more), each with a mini-checklist and detailed reference cards. A separate group of skills implements a task pipeline: planning, design, approval, development, internal acceptance, code review, external acceptance and release, with artifacts at each stage under docs/delivery. Code review relies on three deterministic layers run by one command: a regex scanner, a BSL Language Server wrapper and an XML metadata parser, together covering part of the checkbsl rule catalog without the model inventing findings.

Who it is for. For 1C development teams that need standards applied on the fly and a managed task process with approval points, not just a rulebook.

Good fit when

  • You need the agent to apply 1C standards by task context, not general memory
  • You need a managed task pipeline with approval and code-review gates
  • You need deterministic code checks on top of BSL Language Server without manually parsing reports

Not a fit when

  • You do not need a full task lifecycle with artifacts, a simple checklist is enough
  • You are not on ZCode, and compatibility with Claude Code, Codex and Cursor is formal and untested by the author in real clients

Example request

Take the task of adding an ИсторияСогласований information register through the pipeline

Limitations

The author states the plugin is tested in ZCode and Kimi; for Claude Code, Codex and Cursor there is formal compatibility, but skill triggers were not verified in real clients. The path there is copying skills/*/ folders into the project's .agents/skills. The BSL Language Server layer needs a separately installed Java 21+ and the bsl-language-server JAR. Deterministic coverage of the checkbsl catalog is still partial, around 46 percent of rules.

How to disable. Disable the plugin via Settings → Plugin Management in ZCode, or delete the copied skills folders from the project's .agents/skills.

Security check

  • The pipeline's development stage writes code and configuration metadata within the task specification's bounds
  • Validation scripts create and modify artifacts in the project directory

README in short

The Russian README describes 30 skills split between the development pipeline and topical code rules, a table of pipeline artifacts from the task brief to release notes, deterministic code-review layers with checkbsl catalog coverage percentages, four connection methods (GitHub plugin, marketplace, local development, Kimi) and an FAQ section for diagnosing missing skills.

FAQ

Is Java required for the plugin to work?

No, without Java and the bsl-language-server JAR, review runs on the regex scanner plus a manual pass, and the AST layer is simply skipped honestly.

How do you toggle the pipeline's automatic mode?

With the plugin commands /auto and /manual, which write a _conveyor-mode.md file in the delivery directory.

Editors’ pick

A skills library that gives coding agents a development process: brainstorming, planning, TDD, subagents and code review

PluginMedium riskNo VPN needed292.5KRepository stars
Editors’ pick

Small composable skills for engineering with agents: plan grilling, TDD, bug diagnosis, code review and architecture

SkillLow risk271.4KRepository stars
Editors’ pick

GitHub toolkit for spec-driven development: the specify CLI adds agent commands and skills to a project, from principles to implementation

CLIMedium riskNo VPN needed139.3KRepository stars

Reference MCP servers

Model Context Protocol servers

Official

Official reference MCP servers: Filesystem, Fetch, Git, Memory, Sequential Thinking, Time and Everything

MCP serverMedium risk90.6KRepository stars
Foxx AI1c-dev-rules

I am Foxx AI and I have already vetted this tool. Ask about install, setup or anything else, and I will keep it simple.