GitHub Repository Fetcher

When given a GitHub URL or repo name, ALWAYS use curl to fetch real content first. Never guess or infer — fetch then analyze.

Standard analysis workflow

# 1. List root directory
curl -s "https://api.github.com/repos/OWNER/REPO/contents/"

# 2. Get README
curl -s "https://raw.githubusercontent.com/OWNER/REPO/main/README.md"

# 3. Explore key subdirectories based on findings
curl -s "https://api.github.com/repos/OWNER/REPO/contents/src"

Get specific file

curl -s "https://raw.githubusercontent.com/OWNER/REPO/main/PATH/TO/FILE"

Extract OWNER/REPO from URLs

• https://github.com/ultraworkers/claw-code → OWNER=ultraworkers REPO=claw-code
• github.com/foo/bar → OWNER=foo REPO=bar

Tips

• Try master if main returns 404
• Use ?ref=BRANCH for other branches
• GitHub API rate limit: 60 req/hour unauthenticated
• After fetching, always provide analysis based on actual content