ytr

A Yandex Tracker CLI built for LLM agents: issues, comments, worklogs, checklists and bulk operations, with an agent skill

CLIHigh riskRussian stack

slavkluev/ytr

Install

brew install slavkluev/tap/ytr

For macOS. On other systems use go install or a release binary.

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

What it does

ytr works with Yandex Tracker from the command line. It creates, searches, views and updates issues, moves them through statuses and shows their changelog. Comments, links, worklogs and checklists are subcommands, and bulk move, update and transition run asynchronously with polling. It covers statuses, priorities, resolutions and issue types, queue field discovery, components and users. Output is predictable: JSON with field selection, jq filtering and meaningful exit codes, and the bundled SKILL.md teaches the agent every command.

Who it is for. For developers and managers who track work in Yandex Tracker and want an agent to handle it.

Good fit when

  • You want the agent to create an issue and log time after work
  • You need to bulk transition or move issues between queues
  • You need issues as JSON for a script or report

Not a fit when

  • You need an MCP server and the agent may not run shell commands
  • The agent must not change anything in Tracker

Example request

Find my open issues in queue PROJ, move PROJ-123 to In Progress and log two hours on it

Limitations

Requires an OAuth token, organization ID and organization type, 360 or cloud. Delete and bulk commands apply immediately and there is no read-only mode. Unofficial project.

How to disable. Run ytr auth logout, remove the binary with brew uninstall ytr and delete the ytr skill folder from the agent's skills directory.

Security check

  • Creates, edits and deletes issues, comments and worklogs in a live Tracker
  • Bulk operations affect many issues at once
  • Stores an OAuth token in a config file

README in short

The README briefly lists CLI features and three install options: Homebrew, go install and release binaries. The quick start shows auth via environment variables and typical commands for issues, comments, worklogs, bulk operations and reference data. It explains auth precedence and links to SKILL.md for agents. MIT licensed.

SKILL.md

---
name: ytr
description: >-
  Yandex Tracker CLI for managing issues, comments, worklogs, and more.
  Use when the user needs to interact with Yandex Tracker: search/filter
  issues, create or update tasks, manage worklogs, bulk operations, etc.
license: MIT
compatibility: Requires ytr binary in PATH
metadata:
  author: slavkluev
  version: "4.0"
---

# ytr -- Yandex Tracker CLI

## Auth

```bash
# Environment variables (recommended for agents)
export YTR_TOKEN="your-oauth-token"
export YTR_ORG_ID="your-org-id"
export YTR_ORG_TYPE="360"   # or "cloud"

# Or interactive login (humans)
ytr auth login

# Or explicit login flags
ytr auth login --token TOKEN --org-id ORG --org-type 360

# Verify authentication
ytr auth status
```

Authentication precedence:

1. Flags: `--token`, `--org-id`, `--org-type`
2. Environment variables: `YTR_TOKEN`, `YTR_ORG_ID`, `YTR_ORG_TYPE`
3. Config file saved by `ytr auth login`

Notes:

- For regular commands, flag-based and env-based auth require all three values together.
- `ytr auth login` is the exception: it can detect the organization type when `--org-type` is omitted.
- Config is stored in `~/.config/ytr/config.yaml`.

FAQ

Which organization type do I set?

360 for Yandex 360 organizations and cloud for Yandex Cloud ones. ytr auth login can detect it.

Where are credentials stored?

After ytr auth login, in ~/.config/ytr/config.yaml. Flags and environment variables override the file.

Editors’ pick

A CLI for every Google Workspace API with JSON output and agent skills: Drive, Gmail, Calendar, Sheets and more

CLIHigh risk31K
Editors’ pick

Local search over Markdown notes, docs and meeting transcripts: keywords, semantic search and reranking, with an MCP server

CLIMedium risk29.7K
Editors’ pick

A task manager for AI-driven development: breaks a PRD into dependent tasks and guides the agent through them via MCP or CLI

MCP serverMedium risk28.1K
Editors’ pick

Anthropic's official plugins for knowledge work roles: sales, support, product, marketing, legal, finance, data and enterprise search

PluginHigh risk24K