1C OData skills and bot

1c oData bot

OData and metadata-search skills for AI agents, plus a Telegram and email bot that answers plain-language questions about 1C data

Skill

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

  • Sends data from the 1C database over Telegram and email, so access to the bot should be restricted
  • The external processing publishes the database's OData interface, widening the API surface
All reasons and checks
Russian stack

gybson63/1c-odata-skill

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add skills/1c-odata-bot

Detects the agents on your machine, checks the risk and pins the version.

Other ways to install

Assembled automatically, review before installing.

Run in a terminal in the project folder

npx skills add gybson63/1c-odata-skill --skill odata -a claude-code -y

The skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.

Without third-party tools, from commit 85e8722
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/gybson63/1c-odata-skill.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skills/odata/
git -C "$tmp" checkout 85e8722124c189ebf0df006ef1d0db5bdca77c34
mkdir -p .claude/skills
cp -R "$tmp/skills/odata" .claude/skills/odata

Commands for macOS and Linux, on Windows run them in Git Bash.

Run in a terminal in the project folder

npx skills add gybson63/1c-odata-skill --skill odata -a cursor -y

The skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.

Without third-party tools, from commit 85e8722
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/gybson63/1c-odata-skill.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skills/odata/
git -C "$tmp" checkout 85e8722124c189ebf0df006ef1d0db5bdca77c34
mkdir -p .agents/skills
cp -R "$tmp/skills/odata" .agents/skills/odata

Commands for macOS and Linux, on Windows run them in Git Bash.

Run in a terminal in the project folder

npx skills add gybson63/1c-odata-skill --skill odata -a github-copilot -y

The skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.

Without third-party tools, from commit 85e8722
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/gybson63/1c-odata-skill.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skills/odata/
git -C "$tmp" checkout 85e8722124c189ebf0df006ef1d0db5bdca77c34
mkdir -p .github/skills
cp -R "$tmp/skills/odata" .github/skills/odata

Commands for macOS and Linux, on Windows run them in Git Bash.

Run in a terminal in the project folder

npx skills add gybson63/1c-odata-skill --skill odata -a codex -y

The skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.

Without third-party tools, from commit 85e8722
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/gybson63/1c-odata-skill.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skills/odata/
git -C "$tmp" checkout 85e8722124c189ebf0df006ef1d0db5bdca77c34
mkdir -p .agents/skills
cp -R "$tmp/skills/odata" .agents/skills/odata

Commands for macOS and Linux, on Windows run them in Git Bash.

Run in a terminal in the project folder

npx skills add gybson63/1c-odata-skill --skill odata -a gemini-cli -y

The skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.

Without third-party tools, from commit 85e8722
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/gybson63/1c-odata-skill.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skills/odata/
git -C "$tmp" checkout 85e8722124c189ebf0df006ef1d0db5bdca77c34
mkdir -p .agents/skills
cp -R "$tmp/skills/odata" .agents/skills/odata

Commands for macOS and Linux, on Windows run them in Git Bash.

Run in a terminal in the project folder

tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/gybson63/1c-odata-skill.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skills/odata/
git -C "$tmp" checkout 85e8722124c189ebf0df006ef1d0db5bdca77c34
mkdir -p .devin/skills
cp -R "$tmp/skills/odata" .devin/skills/odata

Commands for macOS and Linux, on Windows run them in Git Bash.

Formerly Windsurf.

Run in a terminal in the project folder

npx skills add gybson63/1c-odata-skill --skill odata -a cline -y

The skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.

Without third-party tools, from commit 85e8722
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/gybson63/1c-odata-skill.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skills/odata/
git -C "$tmp" checkout 85e8722124c189ebf0df006ef1d0db5bdca77c34
mkdir -p .cline/skills
cp -R "$tmp/skills/odata" .cline/skills/odata

Commands for macOS and Linux, on Windows run them in Git Bash.

Run in a terminal in the project folder

npx skills add gybson63/1c-odata-skill --skill odata -a roo -y

The skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.

Without third-party tools, from commit 85e8722
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/gybson63/1c-odata-skill.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skills/odata/
git -C "$tmp" checkout 85e8722124c189ebf0df006ef1d0db5bdca77c34
mkdir -p .roo/skills
cp -R "$tmp/skills/odata" .roo/skills/odata

Commands for macOS and Linux, on Windows run them in Git Bash.

A fork of Roo Code, same .roo folders.

Run in a terminal in the project folder

npx skills add gybson63/1c-odata-skill --skill odata -a opencode -y

The skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.

Without third-party tools, from commit 85e8722
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/gybson63/1c-odata-skill.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skills/odata/
git -C "$tmp" checkout 85e8722124c189ebf0df006ef1d0db5bdca77c34
mkdir -p .agents/skills
cp -R "$tmp/skills/odata" .agents/skills/odata

Commands for macOS and Linux, on Windows run them in Git Bash.

Run in a terminal in the project folder

tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/gybson63/1c-odata-skill.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skills/odata/
git -C "$tmp" checkout 85e8722124c189ebf0df006ef1d0db5bdca77c34
mkdir -p .agents/skills
cp -R "$tmp/skills/odata" .agents/skills/odata

Commands for macOS and Linux, on Windows run them in Git Bash.

Run in a terminal in the project folder

tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/gybson63/1c-odata-skill.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skills/odata/
git -C "$tmp" checkout 85e8722124c189ebf0df006ef1d0db5bdca77c34
mkdir -p .agents/skills
cp -R "$tmp/skills/odata" .agents/skills/odata

Commands for macOS and Linux, on Windows run them in Git Bash.

You will need: Node.js

Checked against the repository on Sep 26, 2026, commit 85e8722.

Text for your agent

Install dependencies with pip install -r requirements.txt, copy env.example.json to env.json and fill in the bot tokens and OData settings, run python -m bot, and for Cursor connect the conf-doc MCP following docs/mcp-setup.md.

Other ways from the author
pip install -r requirements.txt

Install the bot's dependencies.

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

What it does

The project offers two ways to get 1C data over the standard OData protocol. For AI agents there are separate skills: odata builds and runs OData queries, 1cconfinfo parses the configuration structure, conf-doc does semantic search over objects and attributes before the query itself, and conf-doc is also exposed as an MCP server for Cursor. Alongside that, a multi-agent bot runs on Telegram and email: a question in Russian passes through a metadata analyst, an OData agent that builds the query and counts records via $count and $expand, and a formatter that presents the answer as a table or chart. A separate external processing report, EnableODataInterface, publishes the needed catalogs, documents and registers to OData right from the Enterprise mode, without the Configurator.

Who it is for. For 1C developers and analysts who want to give colleagues natural-language access to 1C data, and for anyone who wants OData skills for their own AI agent.

Good fit when

  • You want to let staff without 1C access ask for data through Telegram or email in plain language
  • You need reusable OData and metadata-search skills for an agent in Cursor
  • You want to quickly publish 1C objects to OData without opening the Configurator

Not a fit when

  • 1C's OData interface is not published and publishing it is unsafe for your environment
  • You need to write data into 1C: both the skills and the bot are described as reading data through OData, not changing it
  • You cannot connect an external AI provider for the multi-agent pipeline

Example request

How many customer orders were placed this week and for what total, show it as a table

Limitations

The bot and the analyst agent use their own multi-agent AI pipeline, with tokens and cost tracked per session; the specific model provider is set in configuration and not named explicitly in the README. Domain profiles like ЗУП КОРП are built for specific configurations, and others will need their own profile. The EnableODataInterface external processing publishes OData from Enterprise mode, which widens the database's API surface, and deciding which objects to publish is left to the administrator. The email interface works off an allowed-sender list set in the config.

How to disable. Stop the python -m bot process and disable the database's OData interface through the same EnableODataInterface report or in the Configurator.

Security check

  • Sends data from the 1C database over Telegram and email, so access to the bot should be restricted
  • The external processing publishes the database's OData interface, widening the API surface

README in short

The README lists the features: an email interface with HTML replies and attachments, a Telegram bot with an analyst-OData-formatter multi-agent pipeline, conf-doc semantic search, a separate metadata-analyst mode with domain profiles, optional web search through a self-hosted SearXNG as a fallback, a set of skills for AI agents, and an external OData-publishing processing report. It gives a quick start and a documentation link table for each audience: bot user, setup, MCP in Cursor, SearXNG, bot developer. It notes a development process using feature branches and pre-commit.

FAQ

Can the bot change data in 1C?

The README only describes querying data through OData and counting records; write operations are not documented.

Why is conf-doc needed before the OData query itself?

Semantic search over metadata finds the right objects and attributes upfront, which reduces failed OData queries on the first step.

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 OData skills and bot

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