cc-1c-init: 1C project init prompt
cc-1c-init
A Claude Code prompt that sets up a 1C project structure with coding standards, role agents, skills and MCP
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
- Clones and installs external skills and rules repositories during initialization
- The prompt gives the agent access to 1C database connection parameters, including the password
Install
Manual install
Выполни инструкции из promt_new_project.md
Copy the prompt into the project root before running it.
This is third-party code. Review the repository files before installing.
What it does
The promt_new_project.md prompt sets up a full 1C project structure in an empty folder in one run: folders for configuration snapshots, tasks, a knowledge base, a sandbox and scripts, a CLAUDE.md file with filesystem and database boundaries, and a .dev.env template for connection parameters. It clones and installs the external cc-1c-skills skills and cursor_rules_1c rules, converting the latter from Cursor format to Claude Code format, and adds 12 role agents such as analyst, architect and reviewer. A second prompt, patch_codex.md, ports the already set up project to Codex: config, skills, rules and a check script, without touching the user's global settings. Separate targeted patches exist for projects already set up by an earlier version.
Who it is for. For 1C developers starting a new project with Claude Code or Codex who want a standard structure and agent safety rules from day one, without manual setup.
Good fit when
- You are starting a new 1C project and want structure, coding standards and agent boundaries from the start
- You need predefined roles (analyst, architect, reviewer) for different tasks
- You want to work in both Claude Code and Codex with the same setup
Not a fit when
- The project already has an established structure you do not want to change
- You do not use Claude Code or Codex
Example request
Follow the instructions in promt_new_project.md and set up a new 1C project structureLimitations
The prompt clones the external cc-1c-skills and cursor_rules_1c repositories from the internet during setup; their content is not controlled by the cc-1c-init author. Writing to a production infobase is forbidden by the CLAUDE.md rules, but that is an instruction to the agent, not a technical restriction. The database password ends up in a local .dev.env that must be manually excluded from git.
How to disable. Remove the .claude/skills folder, the kb/1c-rules folder and the CLAUDE.md file the prompt created from the project.
Security check
- Clones and installs external skills and rules repositories during initialization
- The prompt gives the agent access to 1C database connection parameters, including the password
README in short
The README describes the directory structure the prompt creates, key files like CLAUDE.md and .dev.env.example, the agent's filesystem and database boundaries, the list of external dependencies (cc-1c-skills, cursor_rules_1c), the order of running the two prompts, and 12 role agents with a purpose table. It also covers targeted patches for already set-up projects and tooling update scripts.
FAQ
Does the prompt only work with Claude Code?
The main prompt does, and patch_codex.md separately ports the same setup to Codex.
What happens to the database password?
It goes into a local .dev.env, which is listed in .gitignore and should not be committed.
Related
A skills library that gives coding agents a development process: brainstorming, planning, TDD, subagents and code review
Skills for real engineers by Matt Pocock
Skills For Real Engineers
Small composable skills for engineering with agents: plan grilling, TDD, bug diagnosis, code review and architecture
GitHub toolkit for spec-driven development: the specify CLI adds agent commands and skills to a project, from principles to implementation
Reference MCP servers
Model Context Protocol servers
Official reference MCP servers: Filesystem, Fetch, Git, Memory, Sequential Thinking, Time and Everything