# Workspace Inventory

> Full workspace discovery — list available workspace actions, repositories, and validate project structure.

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

---


# Workspace Inventory Workflow

**CONCEPT:DEV-001**

Full workspace discovery — list available workspace actions, repositories, and validate project structure.

## Steps

### Step 0: list-workspace-actions [skill: repository-manager-mcp]
**Agent**: `scanner-agent`
**Tools**: `rep_rm_workspace, rep_rm_git`

Use the rm_workspace tool to list the available actions for the workspace
Expected: `list, setup`

### Step 1: list-managed-repositories [skill: repository-manager-mcp]
**Agent**: `builder-agent`
**Tools**: `rep_rm_projects`

List all managed repositories in the workspace with their status
Expected: `repository`

### Step 2: KG Persistence [depends_on: Step 0, Step 1]
**Agent**: `builder-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 Inventory 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 — list-workspace-actions; Step 1 — list-managed-repositories
- **After level 0:** Step 2 — 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.