ClaudeCodeMod

All shelves / Mods / Review

review-radar

By pedrovelasquez9

review-radar is a Claude Code review mod by pedrovelasquez9.

Reads the branch diff after each turn and draws a pane of only the changes a person must confirm, with diff lines and Reviewed and Request changes buttons.

Draws

Install

The marketplace name is review-radar.

In Claude Code
/plugin install review-radar --marketplace pedrovelasquez9/review-radar
Open the repo

It runs inside the Claude Code process. The side panel is only what the author's README names. Read the repo before you install, or run claude plugin validate on the plugin folder.

Version
0.12.1
License
MIT
Repo stars
5
Last change
2026-11-03

What it can reach

  • Draws in the session
  • Reads this turn's file edits
  • Calls another program on this machine

Claude Code with mod support, in the terminal or in a local session of Claude Desktop's Code tab; the README tested it on Claude Code 2.1.309 on Windows. A git repository: outside one the pane says Not a git repository. Each analysis spends tokens on your account. Answer y to add the marketplace and pick a scope, and already open sessions pick it up after /reload-plugins. From a shell the install is claude plugin install review-radar --marketplace pedrovelasquez9/review-radar. The pane opens by itself after the first turn that leaves changes on the branch, and /review-radar opens it at any time and forces a full analysis, about 20-30 s on a mid-sized branch. Set autoAnalyze to false in /config to analyze only when you ask, and reviewModel to sonnet or haiku to spend less.

The marketplace, review-radar, holds only this plugin. Reviewing what Claude changed on the branch is why this page files it under review. crit-tui opens a pane where you comment on lines of the conversation, the diff, or a file, sends the review to Claude in one go, and threads Claude's replies. change-ledger draws a pane of every file this session touched, with lines added and removed and which agent edited it, beside the git working tree. This one asks a model, Opus by default, to sort the branch diff at the end of each turn into the changes a person must confirm, in nine categories from business logic and secrets to changes nobody asked for, and folds routine ones under Review in the PR. Each finding shows its category, file and line, and the diff hunk, with Reviewed and Request changes buttons, and Request changes writes a full fix request into your prompt. A scan of added lines for literal credentials always marks a hit critical. The repository also holds an OpenCode plugin, which this page does not cover.

Demo

The What it does section of the author's README: it runs by itself at the end of every turn that may have changed files and diffs the working tree against the branch's base; it judges a change by what it does, not by stack; each critical finding shows its category, file:line, what to check and the diff hunk; and every finding has Reviewed and Request changes buttons, the second writing a full fix request into the prompt.
Screenshot of the author's GitHub page.

What it hooks into

  • session.startWhen a session starts
  • command.runWhen you run its slash command
  • tool.callAround a tool call, where it can hold one
  • turn.completeWhen a turn ends
  • ui.renderDraws into the sessionPane

Read from the on() calls in its hook modules. Open its source under Files to check what each one does.

Files

The author's README and source, 4 files. They load when you open them.

Facts

Author
pedrovelasquez9
Category
Review
Marketplace
review-radar
Repo
pedrovelasquez9/review-radar
Version
0.12.1
License
MIT
Repo stars
5
Last change
2026-11-03
Language
TypeScript
Files
60

Other mods in Review

mod-file-treev-amorimDraws a Files panel of what Claude read and changed this session, lit live while it works, with +/- line counts and a replay of the last turn's diffs.mod-transcriptv-amorimRestyles the transcript as chat bubbles, folds each finished turn and each tool row to one line, colors code, and adds a copy button to replies.improve-promptwaltherhuggoDraws an Improve prompt button above the prompt box that rewrites your draft with the session's context; /improve does the same, and you review and send it.done-gatevumichienTells Claude and you, in a toast, when a task is marked done while changed code is untested, and draws the last test run in a band.prompt-enhancervumichienDraws an Enhance button above the prompt: Haiku rewrites your draft to name fitting skills, what to ask first, and what done looks like. It never sends it.assumption-checkvumichienLists the choices Claude made that you did not state after a turn that edited files or ran commands; mark each right or wrong and send the corrections.replay-theaterAnthropicAdds /replay. Steps through the files Claude edited last turn, one diff at a time.review-watchhamzaferDraws one line above the prompt per running code review, with the model, the target, the elapsed time, and Codex's latest output. A toast lists the findings.md-previewhamzaferWhen Claude edits Markdown, draws the before and after beside the session, rendered the way GitHub does.files-touchedSingh-APDraws one line above the prompt for files Claude changed this session, with lines added and removed. /touched pane lists them, and a press inserts @path.change-ledgerarasovicDraws a pane of every file this session touched, with lines added and removed and which agent edited it, beside the git working tree.turn-timelinearasovicDraws the current turn as a timeline: one lane for the main loop, one per subagent, the split between model, tools, and idle, and the three slowest steps.
All 145 in Review