gps
Your AI agent favorite directory mapping cli
Install / Use
npx skills add wesbragagt/gpsInstalls into whichever agent you are using.
.windsurfrules
Windsurf/Codeium rules
Quality Score
Category
Development & EngineeringSupported Platforms
Tags
Our assessment of gps
gps scores 59/100 on our quality scale, 3336th of 3,841 Development & Engineering skills we index.
Its .windsurfrules is 3.9 KB long, well organised into 33 sections with 14 code examples: a solid amount of guidance for an agent.
It has no GitHub stars yet, so there is no community track record; judge it on its content.
Maintenance, license and trust
- We could not determine when the repository was last updated.
- Our last check on 2026-08-27 found the source still online.
- No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
- Its trust signals score 68/100, with 3 cautions from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
gps compared with similar skills
All 4 of these similar skills score higher than gps; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| gps (this skill)by wesbragagt | 59 | 0 | — | .windsurfrules |
| ai-job-searchby MadsLorentzen | 100 | 44.5k | today | CLAUDE.md |
| claude-howtoby luongnv89 | 100 | 41.7k | 3d ago | CLAUDE.md |
| algorithmic-artby anthropics | 100 | 177.9k | 7d ago | SKILL.md |
| interview-meby addyosmani | 100 | 98.8k | 7d ago | SKILL.md |
Frequently asked questions
- How do I install gps?
- Run
npx skills add wesbragagt/gps. The install tabs above show the steps for each supported agent. - Which AI agents does gps work with?
- It is written for Windsurf and Zed, as a .windsurfrules file. Other agents that read the same format can often use it too.
- Is gps safe to use?
- It declares no license and scores 68/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is gps still maintained?
- We could not determine when the repository was last updated.
Skill content
View source on GitHubGPS Integration for Windsurf
GPS is a token-optimized CLI tool for project analysis, saving 50-70% tokens vs JSON output.
When to Use GPS
Invoke GPS when:
- Exploring unfamiliar codebase - Get structure before diving in
- Finding entry points - Locate main files quickly
- Module analysis - Focus on specific directories
- Architecture review - Understand layer organization
- Pre-refactoring - Map dependencies before changes
- Token budget constraints - Maximize context efficiency
Essential Commands
# Quick project overview
gps --summary
# Find entry points (main files)
gps --entry-points
# Structure at 2 levels deep
gps -L 2
# Focus on specific directory
gps --focus src/api
# Token-efficient output (skip metadata)
gps --no-meta -L 2
# Combined: focused + efficient
gps --focus internal/auth -L 2 --no-meta
Output Formats
| Format | Flag | Use Case |
|--------|------|----------|
| TOON | -f toon (default) | AI context, 50-70% token savings |
| JSON | -f json | Scripting, CI/CD, jq processing |
| Tree | -f tree | Human-readable, documentation |
| Flat | -f flat | CSV-like, data analysis |
Format Selection:
- Default context →
gps(TOON) - Programmatic access →
gps -f json - Documentation →
gps -f tree - Sorting/filtering →
gps -f flat
Common Patterns
1. Quick Project Understanding
gps --summary && gps --entry-points
2. Focused Module Analysis
gps --focus internal/service -L 3
3. Maximum Token Efficiency
gps -L 2 --no-meta
Examples
Example 1: Project Overview
gps --summary
Output:
project[payment-service]{
type: go
files: 47
size: 312KB
entry: cmd/server/main.go
tests: 12 files
docs: README.md
}
Example 2: Find Entry Points
gps --entry-points
Output:
entry-points{
api: cmd/api/main.go
worker: cmd/worker/main.go
cli: cmd/cli/main.go
}
Example 3: Focused Analysis
gps --focus internal/auth -L 2
Output:
internal/auth[8]{
jwt[3]{
generator.go [4.2KB, 156L, go]
validator.go [3.8KB, 142L, go]
}
middleware[2]{
auth.go [3.2KB, 118L, go]
}
handlers[3]{
login.go [2.9KB, 108L, go]
}
}
Installation
# Linux/macOS
curl -sL https://github.com/wesbragagt/gps/releases/latest/download/gps-$(uname -s)-$(uname -m) -o gps
chmod +x gps
sudo mv gps /usr/local/bin/
# With Go
go install github.com/wesbragagt/gps/cmd/gps@latest
# Verify
gps --version
Advanced Usage
JSON Processing with jq
# Get entry points programmatically
gps -f json | jq '.project.key_files.entry_points[]'
# Count files by type
gps -f json | jq '.project.stats.by_type'
# Extract project type
gps -f json | jq -r '.project.type'
Custom Configuration
Create .gps.yaml in project root:
format: toon
depth: -1
exclude:
- node_modules
- dist
- "*.log"
ext:
- .go
- .md
- .yaml
exclude-ext:
- .log
- .tmp
CI/CD Integration
# Validate structure in pipeline
ENTRY_COUNT=$(gps -f json | jq '.project.key_files.entry_points | length')
[ "$ENTRY_COUNT" -gt 0 ] || exit 1
Integration Tips
- Start minimal - Use
gps --summaryfirst, expand with--focusas needed - Limit depth -
-L 2is often enough; add more only when necessary - Skip metadata -
--no-metawhen you only need structure - Exclude noise -
-I "node_modules,dist,build"for cleaner output - Use focus -
--focus dirsaves 70-90% tokens vs full scan
Token Efficiency Guide
| Command | Token Savings |
|---------|---------------|
| gps vs gps -f json | 60-70% |
| gps -L 2 vs full depth | 40-70% |
| gps --no-meta | 15-25% |
| gps --focus dir | 70-90% |
| gps -d (dirs only) | 50-80% |
Reference
- Full docs:
.claude/skills/gps/reference.md - Real examples:
.claude/skills/gps/examples.md - GitHub: https://github.com/wesbragagt/gps
Related Skills
ai-job-search
44.5kThe job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.
claude-howto
41.7kA visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.
algorithmic-art
177.9kCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems.
interview-me
98.8kExtracts what the user actually wants instead of what they think they should want. Achieves this through one-question-at-a-time interview until ~95% confidence about the underlying intent
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
