VibeCop onboards in four steps: connect your repository, confirm one prompt to run the first scan and graph, a full-repo scan, and your first Architecture Integrity Index.
Sign in and authenticate with GitHub, then select the repository you want VibeCop to analyze. VibeCop registers a webhook on the repo so future pull requests trigger automatic reviews, and reads your default branch to build an initial Pattern Fingerprint of how your codebase solves recurring problems.
Connecting a repo surfaces one confirmation — "Run first scan + graph?" — and confirming kicks off the first scan. The seven hygiene layers then run over the full repository tarball, bounded by size caps, so secret, SAST, IaC, and dependency-CVE findings appear before deep architectural analysis begins.
After the first scan, VibeCop detects your languages, frameworks, and package manager, then shows the detected stack on a card that auto-advances into deep analysis after a few seconds — no manual confirmation required. The Stack Profile it builds calibrates VibeCop's detector agents to your specific technology context.
The full analysis extracts a Pattern Fingerprint from your main branch, runs all detector agents, and computes your first Architecture Integrity Index — a 0-100 score of your codebase's structural health. Every subsequent pull request is reviewed against this baseline, and drift from it is flagged automatically.