KodaCode
Coming soon
Docs/Settings

Code review

How /review checks a change for vulnerabilities, bugs and best practice. Each review agent's model and instructions live on the Agents screen.

Review agents

How the agents that read the change are run.

Review agents at once

How many review agents run together.

Challenging findings

Every finding is argued against before you see it.

Challenge threshold, challenge each finding separately, check suggested fixes against

Which findings survive, and how suggested patches are checked.

Scanners

Dependency and secret scanning, run before the agents start.

Scanners, refresh the vulnerability database daily

osv-scanner and Betterleaks: where they come from, and how fresh their advisories are.

Defaults and config keys

SettingDefaultconfig.toml
Review agents at once1 (1–4)[review] parts_at_once
Challenge threshold8 of 10[review] threshold
Challenge each finding separatelyTogether[review] challenge_each
Check suggested fixes againstHead commit (or Working tree)[review] patch_base = head_commit, working_tree
ScannersKoda's copies (or From PATH)[review] scanners = managed, path
Refresh the vulnerability database dailyDaily[review] refresh_daily

With Review agents at once at 1, the review's agents run one after another in a fixed order. So one review never sends your provider more than one request at a time. Scanners and advisories shows the scanners' versions and advisory freshness, with Refresh now. The review always checks uncommitted changes against the files on disk. See Code review.