Crit: Local-first, single-binary CLI for reviewing agent plans and diffs
Crit is a local-first review tool packaged as a single binary. It opens your file or code diff in a browser with a GitHub-inspired interface, lets you leave comments, then your agent acts on the feedback automatically. Repeat until satisfied — all before hitting GitHub.
Core loop: comment, agent updates, diff refreshes
Drag across a range of lines, leave comments, hit Finish Review. The agent picks up the feedback, edits the file, and Crit reloads with the updated diff. Previous comments stay visible; resolve only when you're satisfied. Works for both plans and code — same UI, beautifully rendered markdown with syntax highlighting for 190+ languages.
Install in one command
$ brew install crit $ go install github.com/tomasz-tomczyk/crit@latest $ nix profile install github:tomasz-tomczyk/crit # Windows: PS> iwr https://github.com/tomasz-tomczyk/crit/releases/latest/download/crit-windows-amd64.exe -OutFile crit.exe
Then run crit or crit plan.md. Pre-built binaries for ARM64, WSL also available.
Integrates with 11 agents
One-command setup for Claude Code, Cursor, Copilot, Codex, OpenCode, Gemini, Qwen, Hermes, Windsurf, Cline, Aider. Example:
$ claude plugin add tomasz-tomczyk/crit $ claude plugin install crit@crit $ crit install cursor $ crit install github-copilot $ crit install codex
See full setup docs for each agent.
Multi-round and concurrent reviews
Iterate over multiple rounds per file. Run several reviews in parallel without stepping on each other — useful when juggling multiple agents.
Optional sharing and self-hosting
Reviews stay local by default. One click generates a public link — no install, no login for viewers. You can self-host the share target (crit-web) for privacy. Without sharing, reviews auto-delete after 30 days of inactivity.
Small quality-of-life features
- Vim keybindings
- Git diffs (split & unified)
- Round-over-round diffs
- Mermaid diagrams
- Table of contents
- Dark & light themes
- Draft autosave
- Insert suggestions
Who it's for
Developers who frequently review AI-generated plans and code diffs and want a dedicated local UI to batch feedback and iterate without leaving their workflow.
📖 Read the full source: HN AI Agents
👀 See Also
Stanford Researchers Release OpenJarvis: A Local-First Framework for On-Device AI Agents
Stanford researchers have released OpenJarvis, a local-first framework for building on-device personal AI agents with tools, memory, and learning capabilities. The project includes GitHub repository and website links for developers to explore.
Developer shares solution for Claude AI ignoring rules beyond 50-count threshold
A developer reports Claude Code started silently dropping rules once their shared rule set exceeded approximately 50 items, particularly during frontend-heavy tasks. They built a hook that scans prompts and loads only 2-3 relevant rules based on keyword matching.
Specsmaxxing: Fighting AI Psychosis with YAML Specs and ACAI
Acai.sh introduces Specsmaxxing: a method to combat AI agents losing context by writing requirements in YAML and using numbered Acceptance Criteria for AI (ACAI) that agents reference in code.
Shipwright: An Open-Source Project Management Tool Built on Claude Code
Shipwright is an open-source project management tool that runs on Claude Code with 44 skills, 7 specialized agents, and 16 workflows. It includes binary quality gates and recovery playbooks, and was used to audit credential registries and evaluate automation platforms before engineering work began.