# Unified Task Tracker

> Automatically discovers and queries configured trackers (Jira/atlassian-agent, Plane/plane-agent, or both) to retrieve assigned and stale issues, present a unified schedule dashboard, and push synced updates.

- Skill: `knuckles-team/unified-task-tracker` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add knuckles-team/unified-task-tracker`
- Raw SKILL.md: https://api.skillmd.com/api/skills/knuckles-team/unified-task-tracker/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: Knuckles-Team (https://skillmd.com/u/knuckles-team)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/knuckles-team/unified-task-tracker

---


# Unified Task Tracker Workflow

**CONCEPT:KG-2.12**

Automatically discovers and queries configured trackers (Jira/atlassian-agent, Plane/plane-agent, or both) to retrieve assigned and stale issues, present a unified schedule dashboard, and push synced updates.

## Steps

### Step 0: Atlassian Issue Discovery [skill: atlassian-agent]
**Agent**: `intake-agent`
**Tools**: `graph_query, nc_files`

Detect configuration and query Jira for issues assigned to currentUser() that are active or stale (updated <= -7d) using atlassian_jira_issue tool.
Expected: `jira_issues`

### Step 1: Plane Work-Item Discovery [skill: plane-agent]
**Agent**: `processor-agent`
**Tools**: `graph_analyze, document_tools`

Detect configuration and query Plane for active or stale work items assigned to the user using the plane_work_items tool with list_work_items or search_work_items actions.
Expected: `plane_work_items`

### Step 2: User Interaction
**Agent**: `validator-agent`
**Tools**: `graph_query`

Present a unified dashboard consolidating the active and stale tasks from both Jira and Plane. Prompt the user for progress comments, status updates, or task additions.
Expected: `progress_updates, stale_resolutions`

### Step 3: Atlassian Issue Update [skill: atlassian-agent]
**Agent**: `report-agent`
**Tools**: `graph_write, document_tools`

Push selected comment updates or status changes back to Jira using the atlassian_jira_comment and atlassian_jira_issue tools.
Expected: `jira_update_results`

### Step 4: Plane Work-Item Update [skill: plane-agent]
**Agent**: `intake-agent`
**Tools**: `graph_query, nc_files`

Push selected comment updates or status changes back to Plane using the plane_work_items tool with create_work_item_comment or update_work_item actions.
Expected: `plane_update_results`

### Step 5: KG Persistence [depends_on: Step 4]
**Agent**: `report-agent`
**Tools**: `graph_write`

Persist workflow results as nodes and edges in the Knowledge Graph.
Create appropriate typed nodes with metadata and link to existing domain entities.

## Output
- Unified Task Tracker results persisted in KG
- Structured report (MD/PDF)
- Audit trail with timestamps and agent attributions

## Human Oversight Required
✅ Critical decisions require human review and approval.

## Execution

Run this workflow as a dependency-ordered DAG. Steps with no unmet `depends_on` run in parallel; dependents run after their prerequisites complete.

- **Run first (in parallel):** Step 0 — Atlassian Issue Discovery; Step 1 — Plane Work-Item Discovery; Step 2 — User Interaction; Step 3 — Atlassian Issue Update; Step 4 — Plane Work-Item Update
- **After level 0:** Step 5 — KG Persistence

**Execution:** If graph-os is reachable, offload the whole DAG via `graph_orchestrate action=execute_workflow` (or the `kg-delegate` skill) for true parallel/swarm execution. Otherwise execute the steps natively in dependency order: run steps with no unmet `depends_on` in parallel, then their dependents.