Rami Code Review
Reviews every PR for security, bugs, and performance, then fixes the findings through MCP, keeping you in control of what merges.
README
<p align="center"> <img src="https://rami.reviews/static/images/rami_logo_full.png" alt="Rami" width="200"> </p>
Rami Code Review
Works with Claude Code AND Codex. Rami reviews every PR for security, bugs, and performance — then fixes the findings through MCP. You stay in control of what merges.
<p align="center"> <img src="https://rami.reviews/static/images/rami_pr_check.png" alt="Rami PR check" width="720"> </p>
Disputing Findings
Not every finding needs a fix. Push back when you have evidence — Rami evaluates the dispute and either accepts it or asks you to fix:
- False positive — the code is actually correct
- Framework guarantee — the framework handles this case
- Intentional design — this is by design, not a mistake
- Duplicate — the same issue is reported elsewhere
The dispute loop runs in the same session as the review, so accepted disputes drop out and only real issues land in your commits.
Getting Started
1. Install the GitHub App
Install Rami on your repository.
2. Add the marketplace
Claude Code:
/plugin marketplace add rami-code-review/claude-code-marketplace
Codex:
Install the Rami plugin from this repository's Codex marketplace metadata.
3. Install the plugin
Claude Code:
/plugin install rami@rami-code-review
Codex:
Install the rami plugin from the rami-code-review marketplace.
4. Run a review
On a PR branch, run:
/rami:review
Rami fetches the review, walks each finding by priority, and applies fixes (or accepts disputes) until the PR is clean.
Commands
/rami:review
Full review-fix-dispute loop on the current PR branch:
- Fetches review results
- Walks findings by priority (blocking → high → medium → low)
- Fixes each one — or lets you dispute with evidence
- Commits and pushes
- Repeats until clean (up to 5 iterations)
/rami:review-status
Check review status without triggering a new review.
/rami:usage
Check remaining quota and credit balance.
/rami:setup
Guided setup — installs the GitHub App, registers the MCP server, completes OAuth, and verifies the connection. Run this first if Rami isn't connected yet. It can also offer, only if you agree, to add a short removable Rami section to your CLAUDE.md / AGENTS.md.
/rami:doctor
Read-only health check. Reports auth, GitHub App coverage, quota, and whether the plugin is up to date — with the fix for anything that's off.
/rami:upgrade
Updates the plugin to the latest published version and shows what changed.
Troubleshooting
"No PR found for branch" — push the branch and open a pull request.
"Authentication required" — install the Rami GitHub App on the repo.
Review taking too long? — /rami:review-status checks progress without triggering a new review.
Keeping Rami up to date
Rami checks once a day — silently — whether a newer plugin version is published, and nudges you when one is. To update at any time:
/rami:upgrade
Or manually:
claude plugin marketplace update rami-code-review
claude plugin update rami@rami-code-review
Then run /reload-plugins (or start a new session) to activate it.
Links
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.