Public repo preview for teams using coding agents

Scan a repo for AI agent cost leaks.

Paste a public GitHub repo and get a fast risk preview for Claude Code, Codex, Cursor, and other coding agents. No login, no upload, no private code. The local version can also fail CI when risk rises above your threshold.

Ready.
0 Leak score

Repository

Scan results will appear here.

What the preview catches

Context bloat

Tracked lockfiles, generated folders, large blobs, and missing ignore rules that pull agents away from useful files.

Discovery churn

Repo shapes that make agents repeatedly grep, read, and rediscover the same files before changing code.

Workflow gaps

Missing agent instructions, eval harnesses, or repo maps that leave every new session starting cold.

CI threshold

Use sravan27/context-os@v2.9.0 or the local checker with --max-score to stop new generated noise or missing agent docs before they land.

Drop it into CI

The checker is now a pinned GitHub Action with a green smoke test in context-os CI. Start at a forgiving threshold, then lower it after adding repo guidance, ignore rules, and validation notes.

name: Agent cost leak check
on: [pull_request]

jobs:
  agent-cost-leak:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: sravan27/context-os@v2.9.0
        with:
          max-score: "40"

Need the private version?

The paid audit reviews private repo structure, prompts, agent transcripts, and workflow habits, then ships a report, GitHub Action threshold gate, and one concrete fix path.