About
The Crit skill provides structured code reviews with inline comments for code changes, plans, live pages, or local HTML files. It activates only when users explicitly invoke `/crit` or directly request Crit, not for generic review requests. The tool auto-detects review mode from arguments like files, directories, URLs, or PR numbers without requiring user input about mode selection.
Quick Install
Claude Code
Recommendednpx skills add tomasz-tomczyk/crit -a claude-code/plugin add https://github.com/tomasz-tomczyk/critgit clone https://github.com/tomasz-tomczyk/crit.git ~/.claude/skills/critCopy and paste this command in Claude Code to install this skill
Documentation
Review with Crit
This is the interactive, human-in-the-browser review cycle. Run it only after
the user explicitly invokes /crit or directly asks to use Crit. A generic
request to review code, a plan, a diff, a PR, or a page does not count.
Review and revise code changes, plans, live pages (running dev servers, staging URLs), or local HTML files using crit for inline comment review.
Step 1: Pass arguments to crit
The CLI auto-detects the review mode from its arguments. Do not ask the user which mode to use. Pass arguments through:
crit <arguments> # file, dir, URL, .html — CLI auto-detects mode
crit --pr <num|url> # GitHub PR (range mode)
crit --range <base>..<head> # commit range (range mode)
crit # no args → branch diff
If no arguments, check conversation context:
- A plan file was written earlier in this conversation →
crit <plan-file> - Otherwise → bare
crit(branch diff)
If the user wants to open the review from another device — e.g. a phone over Tailscale:
Keep crit on loopback and reverse-proxy in. Same Step 1 args still apply (file, bare crit, etc.):
crit --public-url "https://<machine>.ts.net" --allow-unauthenticated-network --no-open [args…]
# then: tailscale serve --bg --https=443 http://127.0.0.1:<port>
--public-urlonly changes the URL crit prints — it does not expose the server.--allow-unauthenticated-networkis required with--public-url(even on loopback) and with any non-loopback--host. Crit has no auth: anyone who can reach the URL can read the repo and post comments that may trigger agents. Confirm the user wants that blast radius.- Do not bind
--hostto a Tailscale/LAN IP — proxy withtailscale serve(or an SSH tunnel). Get<port>from crit's startup output, or fix it with-p. Relay the URL crit prints (the public one), not localhost.
Step 2: Launch crit and block until review completes
CRITICAL — you MUST run this step. Do NOT skip it. Do NOT proceed without it.
Run crit in the foreground and block until it exits:
crit <plan-file> # specific file
crit # git mode
If a crit server is already running from earlier in this conversation, crit automatically connects to it. Starting from scratch, it spawns the daemon, opens the browser, and blocks until the user clicks "Finish Review".
crit prints the review URL on startup (e.g. Started crit daemon at http://localhost:<port>). Relay it verbatim:
"Crit is open at http://localhost:<port>. Leave inline comments, then click Finish Review."
Do NOT proceed until crit completes. Do NOT ask the user to type anything. Do NOT read the review file early. Wait for the foreground command to finish — that is how you know the human is done reviewing.
Step 3: Read the review output
When crit completes, read stdout and follow its instructions. Check stderr for approved: true or approved: false.
When a comment has quote, anchor, or drifted:
quote: the specific text the reviewer selected — focus your changes on the quoted text rather than the entire line rangeanchor: use it to locate the current position of the content; line numbers may be stale after editsdrifted: true: original content was removed or heavily rewritten — line numbers are approximate at best
Fallback (mid-round re-entry, plan hooks, or headless workflows): crit comments / crit comments --json. Use crit comments --plan <slug> for plan-mode reviews.
Step 4: Address each review comment
For each unresolved comment:
- Understand what the comment asks for
- If it contains a suggestion block, apply that specific change
- Revise the referenced file (plan or code file from the diff)
- Reply with what you did:
crit comment --reply-to <id> --author 'Hermes' '<what you did>'(reply bodies support markdown) - Do not pass
--resolve. Resolving is the reviewer's call. Only add--resolveif the user explicitly asks.
Editing the plan file triggers Crit's live reload — the user sees changes in the browser immediately.
When replying to multiple comments
Use --json for a single bulk call instead of one invocation per comment:
echo '[
{"reply_to": "c_a1b2c3", "body": "Fixed"},
{"reply_to": "c_d4e5f6", "body": "Refactored as suggested"}
]' | crit comment --json --author 'Hermes'
Step 5: Signal completion and start next round
CRITICAL — you MUST run this step. Do NOT skip it. Do NOT proceed without it.
The finish prompt on stdout includes the command to run again — use it to start a new round.
On subsequent calls, crit automatically signals round-complete first, then blocks until the next "Finish Review" click.
Tell the user: "Changes applied. Review the diff in your browser and click Finish Review when ready."
Do NOT proceed until crit completes. When it does, return to Step 3. If the user finishes with zero comments, the review is approved — stop the loop and proceed.
Sharing
If the user asks for a URL, a shareable link, or to share the review:
crit share <file>
Always relay the full output to the user — copy the URL directly into your response. Don't make them dig through tool output.
To remove a shared review:
crit unpublish [file...]
QR codes
Only use --qr in real terminal environments with monospace rendering. Skip it in mobile apps or web chat UIs — Unicode block characters won't render.
crit share --qr <file>
GitHub Repository
Frequently asked questions
What is the crit skill?
crit is a Claude Skill by tomasz-tomczyk. Skills package instructions and resources that Claude loads on demand, so Claude can perform crit-related tasks without extra prompting.
How do I install crit?
Use the install commands on this page: add crit to Claude Code as a plugin, or clone its repository into your skills directory, then restart Claude so it picks up the skill.
What category does crit belong to?
crit is in the Development category, tagged general.
Is crit free to use?
Yes. crit is listed on AIMCP and free to install.
Related Skills
qmd is a local search and indexing CLI tool that enables developers to index and search through local files using hybrid search combining BM25, vector embeddings, and reranking. It supports both command-line usage and MCP (Model Context Protocol) mode for integration with Claude. The tool uses Ollama for embeddings and stores indexes locally, making it ideal for searching documentation or codebases directly from the terminal.
This skill executes implementation plans by dispatching a fresh subagent for each independent task, with code review between tasks. It enables fast iteration while maintaining quality gates through this review process. Use it when working on mostly independent tasks within the same session to ensure continuous progress with built-in quality checks.
The mcporter skill enables developers to manage and call Model Context Protocol (MCP) servers directly from Claude. It provides commands to list available servers, call their tools with arguments, and handle authentication and daemon lifecycle. Use this skill for integrating and testing MCP server functionality in your development workflow.
This skill deploys and orchestrates Vertex AI ADK agents using A2A protocol, managing AgentCard discovery, task submission, and supporting tools like Code Execution Sandbox and Memory Bank. It enables building multi-agent systems with sequential, parallel, or loop orchestration patterns in Python, Java, or Go. Use it when asked to deploy ADK agents or orchestrate agent workflows on Google Cloud.