From navgator
Use when user asks to scan architecture, check dependencies, find outdated packages, show project structure, refresh architecture, or run a health check. Navgator scan, status, and staleness check.
How this skill is triggered — by the user, by Claude, or both
Slash command
/navgator:architecture-scanThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Scan project architecture, check health, and monitor staleness using NavGator MCP tools. This skill covers scanning, status display, and health checks.
Scan project architecture, check health, and monitor staleness using NavGator MCP tools. This skill covers scanning, status display, and health checks.
npm install, pip install, or similar dependency operationsUse the navgator scan MCP tool to detect components, connections, AI prompts, and infrastructure.
Options:
quick: true: Package files only, skip code analysis (faster)After scanning, present a smart brevity brief:
Use the navgator status MCP tool to show architecture summary without re-scanning.
Returns: component counts by type/layer, connection counts, AI routing table, last scan timestamp, and staleness indicator.
If no architecture data exists, recommend running a scan first.
Use the navgator scan MCP tool with a follow-up review of the results. Health information is included in scan output:
| User Intent | MCP Tool | Notes |
|---|---|---|
| "Scan my project" | navgator scan | Full scan |
| "Quick scan" | navgator scan (quick: true) | Packages only |
| "What's my stack?" | navgator status | No re-scan needed |
| "Any outdated packages?" | navgator scan | Check health results |
| "Is architecture data fresh?" | navgator status | Check timestamp |
Keep output concise. Do NOT dump raw CLI output. Summarize into a scannable brief.
navgator — architecture tracker
npx claudepluginhub tyroneross/navgator --plugin navgatorGuides completion of development work by verifying tests, detecting environment, and presenting structured options for merge, PR, or cleanup.
Guides creation and editing of skills using test-driven development with pressure scenarios and subagents to verify agent compliance.
Dispatches multiple subagents concurrently for independent tasks without shared state. Use when facing 2+ unrelated failures or subsystems that can be investigated in parallel.