NeuralCodeDOCS
Core workflow

Self-review & checks

When an agent finishes, a second agent reviews the diff for bugs and security issues, and your project's tests run automatically. You get a plain traffic-light verdict — and on anything but green, the issues go straight back to the agent to fix.

Self-review Issues
Mostly good. The redirect now guards unauthenticated sessions.
⚠ Validate next to avoid an open-redirect.
checkout.spec.ts fails — null guard missing.
Sent back to the agent to fix · loop 1 of 2 fixing…
The Self-review panel: a color-striped verdict, the findings, and — on amber or red — the auto-fix loop sending issues back to the agent.

Automatic self-review#

With Auto self-review & checks enabled (the default, in Settings → General), every successful run that produced changes triggers a second Claude Code agent. It reads the uncommitted diff and writes a concise, severity-grouped review — and is explicitly told not to make any edits, so it only comments.

Traffic-light verdicts#

The review ends in one of three color-striped verdicts, so you can tell at a glance whether the change is safe:

VerdictMeaning
🟢 All goodNo correctness or security blockers — review when you're ready.
🟡 IssuesMinor problems worth fixing before merge.
🔴 ProblemsReal bugs, failing tests, or security risks.

The auto-fix loop#

On an amber or red verdict, NeuralCode automatically sends the issues back to the main agent to fix, then re-reviews — capped at two loopsso it can't spin forever. A green verdict stops the loop immediately. If it's still not green after two passes, the run hands back to you with the outstanding findings.

Automatic checks#

Alongside the review, NeuralCode detects and runs your test command:

Project typeCommand run
Node (with a real test script)npm test
Rust (Cargo.toml)cargo test
Python (pyproject.toml / pytest.ini)pytest -q

Output is captured and surfaced under a Test output toggle, and the pass/fail result feeds the verdict — a failing suite pushes an otherwise-green review to amber or red. Checks have a generous timeout so long suites still complete.

Catch bugs before you look
Self-review adds a small extra cost per run, but it routinely flags open-redirects, missing validation, and edge cases before they reach your eyes. You can turn it off per preference in Settings.
Note
The review agent itself never edits — it only reports. Any code changes come from the auto-fix loop handing the findings back to the main agent, and you always see the resulting diff before you commit. Prefer to drive fixes yourself? Turn the loop off in Settings and self-review stays advisory-only.