workflowstacks
local-ai

crit: Streamline Your AI Agent Feedback Loop

crit lets founders quickly iterate with AI agents via a simple CLI, turning feedback into actionable code improvements. Ideal for Go‑based dev teams. 1.2k+ GitHub stars

From the repo · “Review AI coding agents' plans, diffs and running apps in the browser. Local-first, works with any agent.”

1,240 stars+23★ this week104 forksGoGuide quality 8/10 · reviewed Oct 18Updated 10/23/2026100% free · open source
What it does

Crit provides instant feedback for founders and developers using AI agents, particularly useful for automated code review

When to use it
  • •When you need to review code submissions from multiple contributors
  • •When you want to automate the initial review process for code quality and standards
  • •When you need to integrate AI-driven feedback into your development workflow
Ready-to-paste prompt
crit feedback -r https://github.com/tomasz-tomczyk/crit -c my-config.yml
Heads up: Make sure you have Go 1.17 or later installed to compile and run crit
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

⚡ Runs out of the box

A prompt/skill package — nothing to install beyond adding it to your AI tool.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/crit && curl -fsSL https://workflowstacks.com/api/skills/crit/claude-skill -o ~/.claude/skills/crit/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How crit: Streamline Your AI Agent Feedback Loop works
Codeflow
Free to inspect

Crit: Streamline Your AI Agent Feedback Loop is a very large Go project (~138k lines across 571 code files, plus 244 test files). You install it into your AI tool with one command; there is nothing to run yourself. Last commit this month, MIT license, has a test suite.

Size
Very large codebase
~138k lines · 571 code files · days to read — use, don't read
Setup
Install as a skill / plugin
Add it to Claude Code (or your AI tool) with one command — 44 skills inside. Nothing to run yourself.
Runs on
Inside your AI tool
Helper scripts use Go · Node.js
Go 58%JavaScript 22%TypeScript 13%CSS 4%Shell 2%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENTS.md
    The instructions the AI actually follows
  3. 3
    cmd/crit/main.go
    Where the program starts running
  4. 4
    internal/config/cli.go
    Inside internal/ — the main logic begins here
What's in each folder
internal/Core code — the actual logic432 files
web/Frontend / UI460 files
integrations/Sub-packages / plugins90 files
cmd/Command-line entry points34 files
docs/Documentation15 files
scripts/Helper scripts16 files
.claude-plugin/Plugin manifest — what gets installed1 files
.config/Configuration1 files
READMEHas testsDocumentedCI checksMIT licenseUpdated this month
Quick Actions
Details
Creator
tomasz-tomczyk
Language
Go
Category
local-ai
Published
2/16/2026

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/crit.svg)](https://workflowstacks.com/skills/crit?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.

Free n8n template

Review Reply Drafter

Draft personalized, on-brand replies to every customer review — including careful responses to negative ones. You approve before anything is posted.

Outcome guide

Automate replies to your customer reviews

The workflow reads your reviews and drafts a personalized reply for each: warm thanks for happy customers, careful and de-escalating for unhappy ones. Nothing posts automatically — you approve every draft.

MCP config

GitHub MCP config

Search repos, read code, open issues and PRs from Claude.

Ready-to-run pack · one-time $29

Review Watchdog

Catch every bad review the day it lands — with a reply ready.

Includes the tested workflow and a written setup playbook. Needs: Google Places API key (free tier).

See what you get

Related skills

More local-ai tools founders pair with this one.

local-ai★ 132,105
Run Powerful LLMs Locally with llama.cpp – Fast C++ Inference
Empower your product with on‑device LLM inference using llama.cpp’s efficient C++ engine. Ideal for founders who need privacy, speed, and no cloud costs. 130k+ GitHub stars.
local-ai★ 94,806
Stirling-PDF: Edit PDFs Anywhere
Edit PDFs on any device with Stirling-PDF, a tool for startup founders, backed by 80k+ GitHub stars
local-ai★ 38,301
Run AI Locally with llmfit
Find compatible AI models for your hardware with llmfit, a tool for founders, with 29k+ GitHub stars.
local-ai★ 5,701
openmed – On‑device Clinical NLP & HIPAA De‑identification for Health Startups
Run 1,000+ medical models in 12 languages entirely on‑device, keeping patient data in‑house. Ideal for founders building secure, cloud‑free health apps. 5.5k+ GitHub stars
local-ai★ 3,321
openui5: Build Enterprise‑Grade Web Apps that Run Anywhere
OpenUI5 lets founders create responsive, enterprise‑ready web applications that work on any device and browser. Ideal for JavaScript teams seeking a proven open‑source UI framework. 3.3k+ GitHub stars.
local-ai★ 289
jitllm
Java Inference Tornado toolkit: High performance LLM inference & serving for the JVM