Pitstop Layer-1
Your Claude Code setup has 290 capabilities.
You are using 30.
The first audit tool for Claude Code. Maps every plugin, skill, command, hook, and MCP server, then tells you exactly what to fix.
Audit command
/auditBuilt from our own cleanup: 24 plugins down to 13, MEMORY.md from 247 lines to 78.
Get your free audit score →№ 01Stack creepSymptoms and causes
| Symptom | Root cause |
|---|---|
| Sessions feel slow and unfocused | Context window bloated with phantom MCP tools |
| Which review tool do I use? | Overlapping capabilities with no decision tree |
| Claude forgets context | Memory files grew past the point where they stay useful |
| Hooks fight workflow rules | Automation contradicts branch, commit, or review policy |
| Plugins installed just in case | Unused capabilities eat attention and context budget |
№ 02Audit model
7 phases.
8 dimensions.
- 01Collect
- 02Inventory
- 03Score
- 04Diagnose
- 05Prescribe
- 06Report
- 07Apply
Coverage
Redundancy
Config hygiene
Memory health
Workflow
Command quality
MCP utilization
Security
№ 03Choose your level
Lite
$29
Plugin access and self-service audit report.
Standard
$79
Audit report plus applied optimizations.
Premium
$199
Optimization, custom skills or hooks, and walkthrough.
№ 04Internal benchmark
| Metric | Before | After |
|---|---|---|
| Plugins enabled | 24 | 13 |
| MEMORY.md lines | 247 | 78 |
| Code review methods | 7 | 3 |
| Phantom MCP tools | 39 | 0 |
| Composite score | C | B+ |