@obsfx/trekker 1.2.0 → 1.2.2

package/README.md

@@ -1,6 +1,6 @@
 # Trekker
 
-A CLI issue tracker built for AI coding agents. Stores tasks, epics, and dependencies in a local SQLite database with a built-in kanban board. No server required.
+A CLI issue tracker built for AI coding agents. Stores tasks, epics, and dependencies in a local SQLite database. No server required.
 
 ## Install
 
@@ -24,7 +24,7 @@ My concerns about the future and security of that project led me here. Trekker i
 
 What you get:
 - Task and epic tracking with dependencies
-- Built-in kanban board UI with real-time updates
+- Optional kanban board UI available as a [separate package](https://github.com/obsfx/trekker-dashboard)
 - No special directory required. The .trekker folder stays local to your project.
 - No hook integrations. Just task management.
 
@@ -133,13 +133,26 @@ trekker-dashboard -p 3000  # Start dashboard on port 3000
 
 The dashboard shows tasks grouped by status and reads from the same `.trekker/trekker.db` database.
 
-## JSON Output
+## Claude Code Integration
 
-Add the `--json` flag to any command for structured output:
+For seamless integration with [Claude Code](https://claude.ai/code), install the Trekker plugin:
 
 ```bash
-trekker --json task list
-trekker --json task show TREK-1
+claude /plugin marketplace add obsfx/trekker-claude-code
+claude /plugin install trekker
+```
+
+This gives Claude Code native access to Trekker commands through MCP. The agent can create tasks, update status, and manage dependencies without running CLI commands directly.
+
+See [trekker-claude-code](https://github.com/obsfx/trekker-claude-code) for more details.
+
+## TOON Output
+
+Add the `--toon` flag to any command for structured output in [TOON format](https://github.com/tooners/toon). TOON is a token-efficient serialization format designed for AI agents, using fewer tokens than JSON while remaining machine-readable:
+
+```bash
+trekker --toon task list
+trekker --toon task show TREK-1
 ```
 
 ## Status Values
@@ -175,6 +188,8 @@ Run `trekker quickstart` to see the full guide with best practices for creating
 
 This is my personal workflow for getting the most out of Trekker with AI agents:
 
+- **Install the Claude Code plugin.** I use [trekker-claude-code](https://github.com/obsfx/trekker-claude-code) to give Claude Code direct access to Trekker through MCP. This way, the agent manages tasks natively without running CLI commands.
+
 - **Always mention Trekker in prompts.** I include "use trekker" in my instructions so the agent knows to track its work.
 
 - **Point agents to the quickstart.** I tell the agent it can run `trekker quickstart` to learn how to use Trekker properly. This gives it all the context it needs without me having to explain everything.

package/dist/index.js

@@ -310,7 +310,7 @@ function wipeProject(cwd = process.cwd()) {
   deleteDb(cwd);
 }
 
-// node_modules/.pnpm/@toon-format+toon@2.1.0/node_modules/@toon-format/toon/dist/index.mjs
+// node_modules/@toon-format/toon/dist/index.mjs
 var LIST_ITEM_MARKER = "-";
 var LIST_ITEM_PREFIX = "- ";
 var COMMA = ",";
@@ -2073,7 +2073,7 @@ Seed complete! Created ${epicIds.length} epics, ${taskIds.length} tasks, ${SAMPL
 // package.json
 var package_default = {
   name: "@obsfx/trekker",
-  version: "1.2.0",
+  version: "1.2.2",
   description: "A CLI-based issue tracker built for AI coding agents. Stores tasks, epics, and dependencies in a local SQLite database.",
   type: "module",
   main: "dist/index.js",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@obsfx/trekker",
-  "version": "1.2.0",
+  "version": "1.2.2",
   "description": "A CLI-based issue tracker built for AI coding agents. Stores tasks, epics, and dependencies in a local SQLite database.",
   "type": "module",
   "main": "dist/index.js",