Predictive Debugger

Predicts where your code will fail at runtime, starting with JavaScript and TypeScript. Works with Claude Code, Codex and GitHub Copilot, no API key needed.

Documentation

Fits the way
you already build.

Claude Code

Codex

GitHub Copilot

YOUR CLI.
YOUR MODEL ACCESS.

A little context.A much better review.

From the first signal to the second opinion.
Follow one real bug through the tool.

01

scan_project

Find your starting point.

Scan the project for risk signals. See which files have the most going on, before spending a model call.

02

map_dependencies

Put the code in context.

Follow the imports. See who calls a file and which tests connect to it, so a local change gets a wider review.

03

predict_failures

Ask for the failure.

An independent model checks the code. Here, two concurrent reservations can read the same stock and overwrite each other.

04

predict_failures

Fix it. Check it again.

Move the stock check and decrement before the await. Re-check the file, then test the behavior across the feature.

01 / 04 SCROLL TO CONTINUE

Skip to the film

predictive-debuggerRECORDED SESSION

› scan_project demo/src

FILERISK DENSITY

auditLog.ts 3 async boundaries · 1 branch

0.58

reserveStock.ts 3 async boundaries · 1 branch

0.51

stockStore.ts 1 async boundary · 1 branch

0.35

formatMoney.ts cyclomatic complexity 1

0.05

priceCart.ts cyclomatic complexity 1

0.02

5 source files scanned · no model call

Risk density helps prioritize reading. It is not a probability that a file contains a bug.

Actual v0.8.1 output · Claude provider · September 2026
Read the tool reference

From “looks fine”to “there it is.”

A real project scan. A real race condition.
Watch the tool follow the evidence.

Your browser cannot play this video. Download the demo.

THE ORIGINAL PRODUCT FILM / V0.8 Explore the text walkthrough

Six tools.Better questions.

Local analysis narrows the search.
An independent model gives you another view.

01Local

scan_project

Know where to look.

Rank source files by risk density. Start with the code that deserves a closer read.

02Local

analyze_file

Read the signals.

Inspect complexity, async boundaries, and the signals behind a file’s risk score.

03Local

map_dependencies

Follow the connections.

Trace imports, reverse imports, and connected tests back to their source lines.

04Model call

predict_failures

Get a second opinion.

Ask an independent model for likely runtime failures, with a line number and a reason.

05Local

analyze_logs

Make sense of the logs.

Surface unusual log entries, ranked by severity and unusual wording. Requires Python 3.

06Local

list_providers

Check your connection.

See which supported CLIs are installed and check their sign-in status.

Parameters, outputs, and limits

A useful signal.
Your judgment still matters.

How we evaluate it

Give your agenta second setof eyes.

Add the MCP server. Restart your agent.
Ask it where your code might fail.

Full setup guide

01 / CONNECT THE TOOL

claude mcp add --scope project predictive-debugger -- npx -y predictive-debugger@latest

Adds the server to this project. Use --scope user for every project.

02 / START A CONVERSATION

“Use Predictive Debugger to find the riskiest files in src/.”

Node.js 22+ · A supported CLI, installed and signed in.
Prediction calls use your CLI’s model access and allowance.

Before you start.

Does my code leave my machine?

Static analysis, dependency maps, and log analysis run locally. Predictions send source and bounded dependency context to your CLI’s model provider. Credentials stay with your CLI. See the security model.

Do I need a separate API key?

No. Predictions use the Claude Code, Codex, or GitHub Copilot CLI you are already signed in to, including its usage allowance.

What code can it review?

JavaScript and TypeScript, including JSX, TSX, and decorators. Vue and Svelte single-file components are not supported. Files over 4 MB are rejected, and large predictions may cover selected declarations. See the tool reference.

Does it replace tests or code review?

No. Risk scores and predictions can be wrong. A clean verdict on one file does not prove a feature works. Use the findings to guide your review, then verify behavior with tests and the surrounding code.

Is there a VS Code extension?

There is an experimental extension that can show findings in the Problems panel. It currently requires a local build and is not on the Marketplace. Try the VS Code preview.