Crit

Reviewing agent output in a terminal is painful. You can't point at a specific line and say "change this." When your agent updates the file, you re-read the whole thing to figure out what changed.

Crit opens your file in a browser with GitHub-style inline comments. Leave feedback, hit Finish, and your agent is notified automatically. When the agent edits, Crit shows a diff between rounds - you see exactly what it addressed.

Works with Claude Code, Cursor, GitHub Copilot, Aider, Cline, Windsurf and any other agent.

Why Crit

Browser UI, not terminal. A persistent tab with rendered markdown and visual diffs. No tmux, no TUI.
Single binary, zero dependencies. brew install and you're done. No Docker, no MCP.
Round-to-round diffs. See exactly what your agent changed between iterations. Previous comments show as resolved or still open.
Works with any agent. Not locked to one editor or AI provider.

Install

brew install tomasz-tomczyk/tap/crit

Also available via Go, Nix, or binary download.

Demo

A 5-minute walkthrough of plan review and branch review.

Usage

crit                          # auto-detect changed files in your repo
crit plan.md                  # review a specific file
crit plan.md api-spec.md      # review multiple files

When you finish a review, Crit writes .crit.json - structured comment data your agent reads and acts on. Add it to your .gitignore:

echo '.crit.json' >> .gitignore

Features

File review

Pass specific files to review them directly: crit plan.md api-spec.md. Markdown files render as formatted documents with per-line commenting. Code files show as syntax-highlighted source. Both support the same inline comment workflow and multi-round iteration.

Git review

Run crit with no arguments. Crit auto-detects changed files in your repo and opens them as syntax-highlighted git diffs. A file tree on the left shows every file with its status (added, modified, deleted) and comment counts. Toggle between split and unified diff views.

Round-to-round diff

After your agent edits the file, Crit shows a split or unified diff of what changed - toggle it in the header.

Split view

Unified view

Inline comments: single lines and ranges

Click a line number to comment. Drag to select a range. Comments are rendered inline after their referenced lines, just like a GitHub PR review.

Suggestion mode

Select lines and use "Insert suggestion" to pre-fill the comment with the original text. Edit it to show exactly what the replacement should look like. Your agent gets a concrete before/after.

Finish review: agent notified automatically

When you click "Finish Review", Crit writes .crit.json and notifies your agent via crit listen. If your agent was listening, it picks up the prompt automatically — no copy-paste needed. A fallback "Copy prompt" button is available if the agent wasn't listening.

Programmatic comments

AI agents can use crit comment to add inline review comments without opening the browser UI or constructing JSON manually:

crit comment src/auth.go:42 'Missing null check'
crit comment src/handler.go:15-28 'Error handling issue'
crit comment --output /tmp/reviews src/auth.go:42 'comment'  # custom output dir
crit comment --clear   # remove .crit.json

Comments are appended to .crit.json - created automatically if it doesn't exist.

Mermaid diagrams

Architecture diagrams in fenced ```mermaid blocks render inline. You can comment on the diagram source just like any other block.

Share for Async Review

Want a second opinion before handing off to the agent? Click the Share button to upload your review and get a public URL anyone can open in a browser, no install needed. Each reviewer's comments are color-coded by author. Unpublish anytime.

You can also share directly from the CLI without starting the browser UI:

crit share plan.md                    # share files and print the URL
crit share plan.md --qr               # also print a QR code in the terminal
crit unpublish                        # remove the shared review

Sharing uses crit.md by default. To self-host, deploy crit-web and point CRIT_SHARE_URL (or --share-url, or share_url in config) at your instance. Set share_url to "" to disable sharing entirely.

GitHub PR Sync

Crit can sync review comments bidirectionally with GitHub PRs. Requires the GitHub CLI (gh) to be installed and authenticated.

Pull comments from a PR

crit pull              # auto-detects PR from current branch
crit pull 42           # explicit PR number

Push comments to a PR

crit push                          # auto-detects PR from current branch
crit push --dry-run                # preview without posting
crit push --message "Round 2"      # add a top-level review comment
crit push 42                       # explicit PR number

Send to agent (experimental)

Click "Send now" on any comment during a review to get an AI agent response in real-time. This feature only appears when agent_cmd is configured. The agent reads the comment context, addresses it (editing code if needed), and replies inline — all while you continue reviewing.

Configure in .crit.config.json:

{"agent_cmd": "claude --dangerously-skip-permissions -p"}

Permission modes

Agents need tool permissions to edit files on your behalf. How you grant them depends on your trust level:

Mode	Command	What the agent can do
Full access	`claude --dangerously-skip-permissions -p`	Read, write, and run any tool. Simplest option — recommended for trusted repos.
Selective access	`claude --allowedTools Edit,Read,Bash,Write,Glob,Grep -p`	Only the listed tools are permitted. Good middle ground.
No permissions	`claude -p`	The agent can respond to comments but cannot edit files. Useful for Q&A-only workflows.

How it works

The agent receives the comment text, quoted text (if text was selected), file path, and line range on stdin.
The agent's stdout is captured and posted as a reply to the comment automatically.
If the agent starts its response with RESOLVED:, the comment is auto-resolved.
If the agent edits files, Crit detects the changes via file watching and updates the UI.

Live threads

After the first agent interaction, the comment becomes a live thread:

Further replies you post in the thread are automatically sent to the agent — no need to click "Send to agent" again.
The agent sees the full conversation history, so it can build on previous context.
Live threads show a ⚡ live badge and green glow — the agent will respond immediately to further replies.

Supported agents

Agent	`agent_cmd` value
Claude Code	`claude -p`
OpenCode	`opencode ask`
Cline	`cline --pipe`
Aider	`aider --message-file -`
Cursor (experimental)	`cursor --pipe`

Tip: Claude Code still prompts for permission in -p mode. To let it edit files freely, use claude --dangerously-skip-permissions -p instead. The other agents already operate without permission prompts in their pipe/non-interactive modes.

You can also specify a model with --model (e.g. claude --model sonnet -p).

Everything else

Draft autosave. Close your browser mid-review and pick up exactly where you left off.
Vim keybindings. j/k to navigate, c to comment, Shift+F to finish. ? for the full reference.
Concurrent reviews. Each instance runs on its own port - review multiple plans at once.
Syntax highlighting. Code blocks are highlighted and split per-line, so you can comment on individual lines inside a fence.
Live file watching. The browser reloads automatically when the source file changes.
Real-time output. .crit.json is written on every comment change (200ms debounce), so your agent always has the latest review state.
Dark/light/system theme. Three-button pill in the header, persisted to localStorage.
Local by default. Server binds to 127.0.0.1. Your files stay on your machine unless you explicitly share.
No analytics or tracking. Crit collects zero telemetry. No usage stats, no crash reports, no phone-home. If we ever add anonymous usage statistics in the future, they will be explicitly opt-in.

Agent Integrations

Crit ships with plugins and configuration files for popular AI coding tools. Each one teaches your agent to write a plan, launch crit for review, and wait for your feedback before implementing.

Per-project install

The fastest way to get started. Installs a /crit slash command plus any integration companion files available for that tool (for example SKILL.md files) into your project:

crit install claude-code   # or: cursor, opencode, windsurf, github-copilot, cline
crit install all           # install all integrations at once

Safe to re-run — existing files are skipped (use --force to overwrite). Good for teams since the files are committed to the repo.

Plugin install (Claude Code)

For the full experience — installs globally with a /crit command plus a crit skill that auto-activates when your agent works with .crit.json, crit comment, crit pull/push, etc:

/plugin marketplace add tomasz-tomczyk/crit
/plugin install crit

See integrations/ for all install methods and details.

`/crit` command

Claude Code, Cursor, OpenCode, and GitHub Copilot support a /crit slash command that automates the full review loop:

/crit              # Auto-detects the current plan file
/crit my-plan.md   # Review a specific file

It launches Crit, waits for your review, reads your comments, revises the plan, and signals Crit for another round.

Configuration

Crit supports persistent configuration via JSON files so you don't have to pass the same flags every time.

File	Scope	Location
`~/.crit.config.json`	Global	Applies to all projects
`.crit.config.json`	Project	Repo root (from `git rev-parse --show-toplevel`)

Project config overrides global. CLI flags and env vars override both.

crit config --generate > ~/.crit.config.json   # scaffold a starter config file
crit config                                    # view resolved config (merged global + project)
crit config --help                             # document all config keys

Example

{
  "port": 0,
  "base_branch": "main",
  "no_open": false,
  "share_url": "https://crit.md",
  "quiet": false,
  "output": "",
  "author": "John",
  "agent_cmd": "claude -p",
  "ignore_patterns": [".crit.json"]
}

All keys are optional - omit any you don't need.

Ignore patterns

Patterns from global and project configs are merged. Supported syntax:

Pattern	Matches
`*.lock`	Files ending in `.lock` anywhere in tree
`vendor/`	All files under `vendor/`
`package-lock.json`	Exact filename anywhere in tree
`generated/*.pb.go`	Path prefix with glob (`filepath.Match` syntax)

Use --no-ignore to temporarily bypass all patterns:

crit --no-ignore

Environment variables

Variable	Description
`CRIT_SHARE_URL`	Enable the Share button (e.g. `https://crit.md` or a self-hosted instance)
`CRIT_PORT`	Default port for the local server
`CRIT_NO_UPDATE_CHECK`	Set to any value to disable the update check on startup

Other Install Methods

Build from Source

Requires Go 1.26+:

git clone https://github.com/tomasz-tomczyk/crit.git
cd crit
go build -o crit .
mv crit /usr/local/bin/

Go

go install github.com/tomasz-tomczyk/crit@latest

Nix

nix run github:tomasz-tomczyk/crit -- --help

Or add it to a flake.nix:

inputs.crit.url = "github:tomasz-tomczyk/crit";

Download Binary

Grab the latest binary for your platform from Releases.

Acknowledgements

Crit embeds the following open-source libraries:

markdown-it: Markdown parser
highlight.js: Syntax highlighting
Mermaid: Diagram rendering

Name		Name	Last commit message	Last commit date
Latest commit History 280 Commits
.claude-plugin		.claude-plugin
.cursor-plugin		.cursor-plugin
.githooks		.githooks
.github/workflows		.github/workflows
e2e		e2e
frontend		frontend
images		images
integrations		integrations
scripts		scripts
test		test
.gitignore		.gitignore
AGENTS.md		AGENTS.md
CLAUDE.md		CLAUDE.md
CONTRIBUTING.md		CONTRIBUTING.md
LICENSE		LICENSE
Makefile		Makefile
README.md		README.md
bun.lock		bun.lock
config.go		config.go
config_test.go		config_test.go
copy-deps.js		copy-deps.js
daemon.go		daemon.go
daemon_e2e_test.go		daemon_e2e_test.go
daemon_test.go		daemon_test.go
diff.go		diff.go
diff_test.go		diff_test.go
flake.lock		flake.lock
flake.nix		flake.nix
gen_integration_hashes.go		gen_integration_hashes.go
git.go		git.go
git_test.go		git_test.go
github.go		github.go
github_test.go		github_test.go
go.mod		go.mod
go.sum		go.sum
integration_hashes_gen.go		integration_hashes_gen.go
integrations.go		integrations.go
integrations_test.go		integrations_test.go
main.go		main.go
main_test.go		main_test.go
mise.toml		mise.toml
package-lock.json		package-lock.json
package.json		package.json
plans.go		plans.go
plans_test.go		plans_test.go
server.go		server.go
server_agent_test.go		server_agent_test.go
server_test.go		server_test.go
session.go		session.go
session_test.go		session_test.go
share.go		share.go
share_integration_test.go		share_integration_test.go
share_test.go		share_test.go
status.go		status.go
status_test.go		status_test.go
testutil_test.go		testutil_test.go
watch.go		watch.go
watch_test.go		watch_test.go

Folders and files

Latest commit

History

Repository files navigation