By guimatheus92
Generic, plugin-based PR review for GitHub and Azure DevOps. Orchestrates parallel reviewer agents in a single session (Copilot CLI or Claude Code), with optional Codex second opinion and stack/business-rule skills.
Reviews PR diffs for architectural drift — layering violations, abstraction leaks, dependency direction, coupling, and module boundaries. Dispatch on every pull request.
Reviews PR diffs for performance regressions — hot-path issues, scale-with-data problems, memory leaks, render storms, and synchronous I/O in request paths. Dispatch on every PR that touches request handlers, render loops, or data processing.
Broad-sweep code-quality reviewer for PR diffs. Flags naming issues, dead code, complexity, DRY violations, missing or misleading comments, type-erasure, and unclear control flow. Dispatch on every pull request.
Generic security reviewer for PR diffs. Hunts for credential leaks, injection vulnerabilities, broken authn/authz, unsafe deserialization, insecure defaults, and missing input validation at trust boundaries. Dispatch when reviewing any pull request.
Reviews PR diffs for silent failures — swallowed errors, missing error propagation, falsy returns that hide bugs, async errors that vanish, and authorization checks that fail open. Dispatch on every PR.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Executables (bin/) — files in this plugin's bin/directory are added to the Bash tool's PATH while the plugin is enabled.
A generic, plugin-based PR review tool for GitHub and Azure DevOps, packaged as a plugin for Copilot CLI or Claude Code. Orchestrates parallel reviewer agents in a single agent session (companion plugins optional) and posts every finding back to the PR as a resolvable inline review comment — never a top-level comment, nothing dropped. When the codex CLI is installed, a Codex second-opinion reviewer runs alongside automatically.
/pr-review https://github.com/org/repo/pull/123
/pr-review https://dev.azure.com/org/proj/_git/repo/pullrequest/456 --dry-run
LLMs are unreliable at gathering metadata, deduplicating findings, and posting comments. A thin Node CLI handles those deterministic tasks; reviewer agents only do the actual reviewing. See architecture for the full execution model.
Inside a copilot session:
/plugin marketplace add guimatheus92/pr-review
/plugin install pr-review@pr-review
Or inside a claude (Claude Code) session:
/plugin marketplace add guimatheus92/pr-review
/plugin install pr-review@pr-review
No npm install needed. The plugin ships a pre-bundled dist/cli.cjs; the slash command finds it via $CLAUDE_PLUGIN_ROOT under Claude Code (falling back to ~/.copilot/installed-plugins/) and runs it with node. The plugin layout (commands/, agents/, skills/) loads in both hosts; the manifest lives in two places on purpose — .claude-plugin/plugin.json (Claude Code's canonical location) and a root plugin.json (which Copilot CLI requires).
Command name per host: Copilot CLI exposes the command as /pr-review. Claude Code namespaces plugin commands as /pr-review:pr-review — and because this plugin also ships reviewer agents, Claude Code does not register a bare /pr-review alias for it (empirically: plugins that ship agents don't get the bare form; it's a host behavior, not configurable in the plugin). To get a bare /pr-review under Claude Code, drop a personal command at ~/.claude/commands/pr-review.md (personal commands have no namespace, so /pr-review resolves):
---
description: Bare alias for the pr-review plugin command.
argument-hint: "<pr-url> [flags]"
allowed-tools: ["Bash"]
---
Run the pr-review CLI in the background and poll it (you are plumbing, not the reviewer):
```bash
CLI=$(find ~/.claude/plugins/cache -name cli.cjs -path '*/pr-review/*/dist/*' -not -path '*/node_modules/*' 2>/dev/null | sort | tail -1)
node "$CLI" review $ARGUMENTS --detach
```
If the output has a `run-id:`, poll `node "$CLI" status <run-id>` (~25s apart) until it prints the summary; otherwise print the output verbatim.
For local development:
git clone https://github.com/guimatheus92/pr-review && cd pr-review
npm install && npm run build
# inside copilot (or claude — same slash commands; claude also accepts `claude plugin marketplace add ./` from the shell):
/plugin marketplace add .
/plugin install pr-review@pr-review
| Provider | Env var | Fallback |
|---|---|---|
| GitHub | GITHUB_TOKEN / GH_TOKEN / COPILOT_GITHUB_TOKEN | gh auth token |
| Azure DevOps | AZURE_DEVOPS_PAT / SYSTEM_ACCESSTOKEN | none |
/pr-review <pr-url> # review with auto-discovered skills; posts line comments (default)
/pr-review <pr-url> --dry-run # preview findings without posting
/pr-review <pr-url> --skip security # skip specific reviewers
/pr-review <pr-url> --context-only # prepare context + skill routing table, don't run reviewers
/pr-review <pr-url> --lang pt-BR # language for finding titles/bodies (default: en)
/pr-review <pr-url> --fail-on high # exit 1 if any high/critical finding survives dedupe
/pr-review <pr-url> --runtime claude # host the session in Claude Code instead of Copilot CLI
/pr-review <pr-url> --no-codex # skip the Codex second-opinion reviewer
Exit codes: 0 clean, 1 findings at/above --fail-on, 2 pipeline error (including an orchestrator run that produced no parseable findings).
On a publish run (the default), every finding lands as a resolvable inline review thread — so each one can be discussed and resolved in place:
npx claudepluginhub guimatheus92/pr-review --plugin pr-reviewGive your agent video input. /video analyzes a URL or local file — transcript, key frames, OCR, timeline — via the mcp-video-analyzer MCP server (auto-registered) or its CLI.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex, antigravity, and grok CLIs when installed) to get diverse perspectives on coding problems
Complete developer toolkit for Claude Code
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.