review-radar

English · Español

Claude Code mod and OpenCode plugin · v0.12.1. A review pane for the human in the loop. After the agent builds a feature, review-radar reads your branch diff and shows, with the diff lines and their files, only the changes a person must confirm: business logic, architecture, data and migrations, secrets, third-party services, security, infra, anything that looks like a mistake, and changes nobody asked for. Everything else is listed as "review in the PR". In OpenCode the same review lives in the sidebar and a dialog.

See what changed in each version in the changelog.

The goal: confirm or request changes on what matters without opening files one by one, and leave the routine for the pull request.

What it does

• Runs by itself. At the end of every turn in which files may have changed (Edit, Write, Bash…), it diffs the working tree against where your branch left its base (origin/HEAD, else origin/main, origin/master, main, master). Committed, uncommitted and untracked files are included.
• Judges by what a change does, not by stack. No framework rules: the model classifies each change by its effect. It works the same in TypeScript, Python, Go, Ruby, SQL, YAML or Terraform.
• Shows the change inline. Each critical finding comes with its category, file:line, one sentence on what to check, and the diff hunk that holds it (a window around the line for long hunks).
• Closes the loop. Every finding has two buttons:
  • ✓ Reviewed collapses it. The mark is tied to the code you saw: it holds across re-analyses while that hunk is unchanged.
  • Request changes writes a complete fix request into your prompt: the finding and its category, file:line, the problem it causes, the code under review as a diff, and the instruction to correct it (or revert it if it should not be there) and leave the rest as it is. Add anything of your own and send it: the session fixes it with no more context needed.
• Leaves the rest for the PR. Routine changes (tests, docs, styling, renames, refactors with no behaviour change) are folded under Review in the PR.

Critical categories

Category	What it covers
business-logic	Rules, calculations, pricing, state transitions, domain validation, anything that changes behaviour for users or money
architecture	New modules or layers, changed data flow, moved responsibilities, public API and contract changes
data	Schema and migration changes, backfills, destructive operations, persistence and serialization formats
secrets	Credentials, keys, tokens, config holding them, anything that could leak them
third-party	New or changed calls to external services, SDKs, webhooks, new hosts, new dependencies
security	Authentication and authorization, trust boundaries, crypto, CORS, injection surfaces
infra	Deploy, CI, containers, runtime config, production feature flags
suspicious	Likely mistakes in any file: values inconsistent with their neighbours or other files, copy-paste leftovers, removed things still referenced, flipped conditions
unrequested	Changes Claude made in this session that none of your prompts asked for: an unrelated file touched, behaviour changed beyond the task, a new dependency, a refactor nobody requested. The finding says which request it goes beyond

Changes nobody asked for

AI assistants sometimes do more than asked: a version bump a project rule asked for, a "while I was here" refactor, a dependency added on the way. review-radar compares what you asked for in the session with what Claude actually edited:

• It reads your prompts and the files Claude edited (Edit, Write, NotebookEdit) from the session's own conversation, so it keeps working after a reload or in a resumed session.
• Only files Claude edited in this session are judged: earlier work on the branch is never called unrequested.
• What your request needs to work (imports, types, call sites, tests and docs of the requested code) is not flagged, and later prompts can widen earlier ones.
• It costs no extra model call: your requests travel in the same deep-review prompt.

以上为 README 的开头部分。其余内容请阅读原文。 查看完整 README ↗