Tool-Call X-ray

Your agents burn tokens on calls that go nowhere.

Drop in your Claude Code or Codex transcripts. Your browser finds the failed, repeated and looping tool calls and the context your agents paid to resend, prices it from the token usage in the files, and writes the patch that stops it. It also flags the API keys, secret files and personal data your agents sent to the model.

Runs entirely in this page. Your transcripts never leave your browser: they are not uploaded, stored or sent anywhere. Our usage events tell Google that the page was used and which buttons were clicked, and carry nothing about your files or results.

Drop transcripts or a folder here

Claude Code .jsonl sessions or Codex rollouts. A week of sessions is a good sample; hundreds of files are fine.

What happens to your data

  • Stays in this browser: your transcripts, the findings and the report. They are held in this tab’s memory until you clear the results or close the tab, and are never uploaded or stored.
  • Goes to Google: usage events saying that the page was used and which buttons were clicked, such as that a scan ran or the patch was copied. None of them carries anything about your files or results. Google Analytics also records the standard page-view details our privacy policy lists for every page.
  • Goes to Corveil, only if you sign up: for the report or the daily team X-ray, your email and which of the two you asked for, to our CRM. Your scan summary (a few rounded totals) goes too only if you choose to include it, and you see it before you send. Never the report itself.

Your transcripts were already on your disk before the scan; the X-ray only reads them. If it flags a secret, rotate it: it was sent to the model provider. See our privacy policy.

Where your transcripts are

Already on your laptop.

Every coding agent session is saved as a JSONL file. Point the picker at the folder, or open it in your file manager and drag files in.

On a Mac, the folders are hidden: in the file picker press ⌘ ⇧ G and paste the path, or ⌘ ⇧ . to show hidden folders.

Claude Code~/.claude/projects/
Codex~/.codex/sessions/
Last 7 daysfind ~/.claude/projects ~/.codex/sessions -name '*.jsonl' -mtime -7

The last one copies a week of sessions into ~/Desktop/agent-week so you can drop that one folder in. Dropping the whole ~/.claude/projects folder keeps the per-project breakdown.

For your whole team

Your team does this every day.

This page looks at one laptop, once. With Corveil, your team’s coding agents send their model traffic through one gateway, so the whole team’s usage is in one place. Corveil runs the team X-ray on top of it: the same rules, run every day, with each fix filed as a ticket. We set it up with you.

01

Sessions flow through Corveil.

Claude Code, Codex and Cursor connect to the Corveil gateway today. Every request is logged with its model, tokens and cost, under your team’s keys, budgets and guardrails.

02

A daily scan ranks the waste.

A Corveil Worker runs these rules over your team’s sessions every day, ranks the waste in dollars, and traces each item to its cause: a stale CLAUDE.md, a missing flag, a sandbox rule, a session habit.

03

Each fix is filed as a ticket.

Each fix lands as a GitHub issue with the evidence and the patch attached, so the instruction, tool or permission is fixed once instead of paid for in every session.

Run the X-ray above to see what your team is paying for calls that go nowhere.

What a daily ticket looks like:

Leave your work email and we’ll get in touch to set it up for your team.

## Agent friction: Flag that does not exist (`gh pr view`)

Found: 14 wasted calls, ~2.1M tokens (~$4.80) across 9 sessions
Fix (Missing flag): agents pass `--body` to `gh pr view`, which does not accept it.

Patch: CLAUDE.md
- `gh pr view` has no `--body` flag. Check `gh pr view --help` before adding flags.

Example ticket. The figures are illustrative, not from a real team.