prereview

prereview

Review your own changes — per line — before you push, and hand the comments to an LLM to act on.

_{Select a line range, leave a comment, hand the CSV to Claude.}

A tiny local webapp for per-line review of your working tree — no commit, no PR, no GitHub round-trip. Run prereview in your repo, click the lines you want changed, comment; a CSV is written that you (or an LLM) can act on. It ships as a Claude Code skill, so /prereview launches a session, you comment, hit "Hand off → Claude", and Claude applies the changes. On a remote box it auto-binds your Tailscale address — review from the Claude mobile app over the tailnet, before anything is pushed.

Status: core flow (review → hand-off → LLM applies) works end-to-end and is in daily use; UI still being polished.

Features

• Comment per line, range, file, or image region — two-click range select; whole-file comments; drag a box on a binary image.
• Annotate a live local site (--external) — proxy a running dev server and drag a box on any page to comment.
• Markdown & HTML render — formatted by default, but comments anchor to real source lines and round-trip with the raw view.
• One CSV, atomically written — the source of truth; read it any time without a torn file.
• The hand-off loop — "Hand off → Claude" writes a marker; the skill reads the CSV and applies your comments without leaving the chat.
• Multi-round streaming hand-off (--stream) — emit a continuous JSON event stream the LLM consumes across many rounds (Hand off as often as you like), ending only when you click End session. No re-invocation, no hand-written CSV parser.
• Phone-friendly + Tailscale-aware — on a remote box it binds your tailnet address (never the public internet); review from your phone.
• Single Go binary — every asset embedded; no Node, no JS runtime.

Install

prereview is a single static binary. Prerequisite: git on your $PATH. Pick one:

# Quick install (macOS / Linux) — downloads the latest release, checksum-verified
curl -fsSL https://raw.githubusercontent.com/livetemplate/prereview/main/install.sh | sh

# Homebrew (macOS / Linux)
brew tap livetemplate/prereview https://github.com/livetemplate/prereview
brew trust --formula livetemplate/prereview/prereview   # one-time: brew requires trusting third-party taps
brew install livetemplate/prereview/prereview

# Windows (Scoop)
scoop bucket add prereview https://github.com/livetemplate/prereview
scoop install prereview/prereview

# Go toolchain
go install github.com/livetemplate/prereview@latest

Quick-install knobs: PREREVIEW_INSTALL_DIR=/path, PREREVIEW_VERSION=v0.4.0.

Claude Code skill (for the LLM-driven flow)

The binary embeds the skill — install it with one command:

prereview --install-skill   # → ~/.claude/skills/prereview/SKILL.md (+ reference.md)

Re-run after upgrading to refresh it. Then invoke with /prereview or "review my changes". (If it reports "unknown skill", run /reload.)

mkdir -p .claude/skills/prereview
cp skill/SKILL.md .claude/skills/prereview/SKILL.md

Quick start

cd <your-repo>
prereview                 # standalone: prints READY <url>, shows a Quit button

Open the URL, comment, click Quit. Comments live in .prereview/comments.csv.

prereview --skill "$(pwd)" &   # what the Claude skill runs for you

In skill mode the UI shows "Hand off → Claude": clicking it writes .prereview/DONE; the skill polls for it, reads the CSV, and acts. Or just tell Claude "review my changes" and it drives the whole loop. See skill/SKILL.md and skill/reference.md.

CLI usage

The review target is the positional path (default: current dir); everything else has a sane default, so a bare prereview just works.

prereview                                # current dir (git repo or not) — just works
prereview ./PLAN.md                      # a single file
prereview ./design-docs                  # a non-git directory — every file shown whole
prereview --base origin/main ../service  # a different git repo vs a ref (flags BEFORE the path)
prereview --external http://localhost:5173 --out ./review   # annotate a live local site (dev server)
prereview --skill                        # LLM hand-off mode (path defaults to .)
prereview --skill --stream               # multi-round JSON event stream for an LLM

A non-git directory or single file is auto-detected: it's shown whole (every line commentable), with no diff and no base picker. Flags must come before the path. Full reference — every flag, mode, and combination — in docs/cli.md.

Usage

Comment on lines. Tap a line to anchor, tap another to extend the range (tap again to reseat), then type and save. The gutter line numbers are permalinks — the URL hash tracks your selection so you can share or reopen it.

Comment on a whole file with the Comment on file button — handy for binary, deleted, or unchanged files where no line is clickable. The file drawer defaults to changed files only; the show all toggle exposes the full tree when you want to comment on something that didn't change.

_{Comment a whole file — changed or not.}

Annotate an image region. On a binary image, drag a rectangle to select an area and comment on it; the box is stored as fractions, so it survives re-encoding.

_{Drag a box on an image to annotate a region.}

Markdown & HTML render by default; tap a rendered block (heading, paragraph, list…) to select its source lines, so the comment anchors to real line numbers and round-trips with the raw view. A Preview ⇄ Raw toggle switches to source. Long docs get a table-of-contents sidebar.

_{Markdown renders with a TOC; comment a block, it anchors to source lines.}

See every comment in one place — the All comments chip lists comments across all files (line, file, and area kinds), each with a jump back to its source.

_{Every comment across files in one list.}

Review from your phone. On a remote box prereview binds your Tailscale IP, so the same review + hand-off works from the Claude mobile app over the tailnet.

_{Review and hand off from your phone.}

More: Diff ⇄ File toggles changed-hunks-with-context vs the whole file (line numbers match, so comments resolve across both) · the base dropdown picks HEAD~N, branches, or remotes (pass anything else via --base) · each comment has Edit / Resolve / Delete (Resolve keeps an audit trail; Delete has Undo) · Esc clears a selection.

Output

<repo>/.prereview/comments.csv is the source of truth — RFC-4180 quoted, 13 columns, one row per comment:

id,file,from_line,to_line,side,body,created_at,resolved,anchor,anchor_status,kind,area,url

kind is line (default), file, area, or region (a live-site rectangle from --external, anchored to a url); area carries the rectangle as {x,y,w,h} fractions. See skill/reference.md for the full column docs.

Architecture (at a glance)

• Single binary, embeds all assets (incl. the livetemplate client JS) via //go:embed.
• State held server-side in livetemplate's session storage; WebSocket-driven UI patches. Pure Go server; no Node/npm.
• Atomic CSV writes via tmp+fsync+rename — read at any time without a torn file.
• Server-side syntax highlighting via chroma, cached per file path.

Development

git clone https://github.com/livetemplate/prereview
cd prereview
make sync-client   # copies the latest livetemplate-client.js into internal/assets/client/
go build .
./prereview

E2E tests use chromedp + headless chromium: go test -tags=browser ./.... Regenerate the README screenshots with make screenshots.

License

MIT.