\r

GitHub Repository Fetcher\r

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

Standard analysis workflow\r

# 1. List root directory\r
curl -s "https://api.github.com/repos/OWNER/REPO/contents/"\r
\r
# 2. Get README\r
curl -s "https://raw.githubusercontent.com/OWNER/REPO/main/README.md"\r
\r
# 3. Explore key subdirectories based on findings\r
curl -s "https://api.github.com/repos/OWNER/REPO/contents/src"\r
```\r
\r
## Get specific file\r
```bash\r
curl -s "https://raw.githubusercontent.com/OWNER/REPO/main/PATH/TO/FILE"\r
```\r
\r
## Extract OWNER/REPO from URLs\r
- https://github.com/ultraworkers/claw-code → OWNER=ultraworkers REPO=claw-code\r
- github.com/foo/bar → OWNER=foo REPO=bar\r
\r
## Tips\r
- Try `master` if `main` returns 404\r
- Use `?ref=BRANCH` for other branches\r
- GitHub API rate limit: 60 req/hour unauthenticated\r
- After fetching, always provide analysis based on actual content