# Workspace Health Check

> Combined workspace + system health validation. Checks repository state alongside system resources.

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

---


# Workspace Health Check Workflow

**CONCEPT:DEV-001**

Combined workspace + system health validation. Checks repository state alongside system resources.

## Steps

### Step 0: Repository Manager Mcp
**Agent**: `scanner-agent`
**Tools**: `rep_rm_workspace, rep_rm_git`

List the available workspace actions and current workspace configuration
Expected: `workspace, list`

### Step 1: collect-system-utilization [skill: systems-manager]
**Agent**: `builder-agent`
**Tools**: `rep_rm_projects`

Get current system memory and CPU utilization
Expected: `memory, cpu`

### Step 2: collect-disk-usage [skill: systems-manager]
**Agent**: `validator-agent`
**Tools**: `rep_rm_projects, gl_pipelines`

Check disk usage for the main workspace partition
Expected: `disk, usage`

### Step 3: KG Persistence [depends_on: Step 1, Step 2]
**Agent**: `validator-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
- Workspace Health Check results persisted in KG
- Structured report (MD/PDF)
- Audit trail with timestamps and agent attributions

## 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 — Repository Manager Mcp; Step 1 — collect-system-utilization; Step 2 — collect-disk-usage
- **After level 0:** Step 3 — 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.