trekker

🥈Silver

Trekker is a CLI issue tracker for AI coding agents. It stores tasks, epics, and dependencies in a local SQLite database. No server required. Ideal for operations teams managing AI agent workflows.

5800Updated 1mo ago

Intermediate30min to implementautomation

Saves ~20 min per use

Quick InstallView Source

git clone https://github.com/obsfx/trekker.git

Works with:

Claude

Overview

About This Skill

Trekker is a CLI issue tracker for AI coding agents. It stores tasks, epics, and dependencies in a local SQLite database. No server required. Ideal for operations teams managing AI agent workflows.

How to Use

[{"step":"Install and initialize Trekker CLI","action":"Run `pip install trekker-cli` and initialize the database with `trekker init`. Configure your agent’s task schema using `trekker schema [SCHEMA_FILE.json]`."},{"step":"Add tasks, epics, and dependencies","action":"Create tasks with `trekker add --title \"[TITLE]\" --priority [HIGH/MEDIUM/LOW] --tag [TAG]`. Link dependencies with `trekker link [TASK_ID] [DEPENDENT_TASK_ID]`."},{"step":"Query and manage tasks","action":"Use `trekker list --tag [TAG]` to filter tasks. Add comments with `trekker comment [TASK_ID] \"[TEXT]\"` to track progress or blockers. Update statuses with `trekker update [TASK_ID] --status [OPEN/IN_PROGRESS/BLOCKED/COMPLETE]`."},{"step":"Generate reports","action":"Export workload summaries with `trekker report --format json > workload.json` or use `trekker dashboard` for a visual overview of agent assignments and blockers."},{"step":"Integrate with CI/CD","action":"Automate task creation from GitHub/GitLab issues using a script that parses issue labels/tags and calls `trekker add` with the parsed data."}]

Setup & Installation

Quick Install

No install command available. Check the GitHub repository for manual installation instructions.

Alternative Install (Git Clone)

git clone https://github.com/obsfx/trekker

Requirements

Claude Code or compatible AI agent
Works with: Claude

Quick Start Guide

Install the Skill

Copy the install command above and run it in your terminal.

Open Your AI Agent

Launch Claude Code, Cursor, or your preferred AI coding agent.

Try It Out

Use the prompt template or examples below to test the skill.

Customize

Adapt the skill to your specific use case and workflow.

Usage Examples

Prompt Template

Use the Trekker CLI to manage the AI coding agent's task list. List all open tasks tagged with [TAG] and their dependencies. For each task, add a comment with the command: 'trekker comment [TASK_ID] "[COMMENT_TEXT]"'. Finally, generate a summary of the agent's current workload and highlight any blockers.

Example Output

Here’s the current state of your AI coding agent’s task list, filtered for tasks tagged with **#data-pipeline**:

1. **Task #T-404** - *Optimize SQL query for user analytics* (Priority: High)
   - **Status**: In Progress (Assigned to: Agent-7)
   - **Dependencies**: 
     - Task #T-399 (Complete) - Schema migration for user table
     - Task #T-400 (Blocked) - Missing test data (Blocker: Data team)
   - **Comments**:
     - *Agent-7*: "Query runs 30% faster after indexing user_id. Next: validate with production-like data."

2. **Task #T-405** - *Refactor ETL pipeline for real-time updates* (Priority: Medium)
   - **Status**: Open (Assigned to: Agent-5)
   - **Dependencies**: None
   - **Comments**:
     - *Agent-5*: "Need approval for cloud resource allocation."

3. **Task #T-406** - *Document API changes for v2.1* (Priority: Low)
   - **Status**: Open (Assigned to: Agent-3)
   - **Dependencies**: Task #T-404 (In Progress)

### Summary:
- **Total Open Tasks**: 3
- **Blockers**: 1 (Task #T-400)
- **High-Priority Tasks**: 1
- **Agents Overloaded**: Agent-7 (2 tasks) - Consider reassigning Task #T-406.

**Action Items**:
1. Unblock Task #T-400 by coordinating with the data team.
2. Assign Task #T-406 to Agent-2 to balance workload.
3. Schedule a sync with Agent-7 to review progress on Task #T-404.