Code review

lzehrung/codegraph

Skill Claude CodeCodex

Use for repo structure, symbol navigation, dependency analysis, duplicate triage, and PR impact review when plain text search is too shallow.

stefan-jansen/coding-agent-plugins

Plugin Claude Code

Bundles 3 skills, 4 commands, 3 agents · 287 tokens together

Code development and quality assurance - skills: analyze, review, docs; commands: test, fix, git, prepare-review.

jscraik/Agent-Skills

Skill Codex needs its repo

Run structured AI code review as an advisory closeout gate for local diffs, PR branches, or commits when the user asks for autoreview, Codex review, second-model review, or pre-ship validation.

teakzc/backpack-plus

MCP server Claude CodeCodexCursor +2

MCP server "code-review-graph" as configured in teakzc/backpack-plus. Launched with C:\Python313\python.exe -m code_review_graph serve.

gomilesf/convergo

Plugin Gemini CLI

Intent-driven planning, implementation and independent review with bounded repairs.

Drakaniia/skills

Plugin Claude Code

Bundles 5 skills, 1 hook · 340 tokens together

Language-agnostic agent skills for keeping codebases healthy — audit structure, execute refactoring, prevent decay, and enforce clean code design.

JJFromTenex/claude-code-training

Command GitHub Copilot

You are scoring a Build Battle submission. Participants had 45 minutes with Claude Code, the Northwind Payments merchant console, and one ticket: NWP-201, issue virtual cards from the console.

acaprino/daodan

Skill Claude Code

Structural entropy auditor for duplicated domain concepts, competing sources of truth and wrong abstractions. TRIGGER WHEN: spawned by the abstraction-architect audit method (references/audit.md, run by /daodan:check-health) or by the reviews of /daodan:review-changes and /daodan:review-branch; asking who canonically…

paultyng/skill-issue

Skill Claude CodeCodex

Use when the user asks for a deep review, full review, comprehensive review, production readiness assessment, full audit, multi-domain audit, "security and reliability and code review", or "review everything". Also use when the user explicitly requests performance review alongside the comprehensive request (e.g.…

OutlineDriven/odin-reflector

Plugin Claude Code

Bundles 4 hooks

Codex CLI reflector — independent critic, oracle, and metacognition layer.

kunaltulsidasani/claude-reimagined

MCP server Claude CodeCodexCursor +2

Local-first knowledge graph for token-efficient code review through MCP and CLI. Runs locally from the code-review-graph Python package.

jdanigo/hydraia

Plugin Claude Code

Bundles 52 skills, 17 commands, 27 agents, 6 hooks · 4,533 tokens together

A self-contained agentic development harness for Claude Code. One command runs the full feature pipeline: context, think, design + threat model, plan with self-review, sub-agent execution, double code review, and security gates. Bundles every skill and agent it needs.

StringKe/std-agent

Skill Claude CodeCodex

Review the current diff for correctness and regressions.

QBall-Inc/the-bulwark

Plugin Claude Code

Bundles 30 skills, 17 agents, 6 hooks · 1,988 tokens together

Full-lifecycle SDLC guardrailing framework for Claude Code — from product ideation and planning through implementation, code review, and test validation. Enterprise-grade skills and agents for AI-human peer collaboration.

SunflowersLwtech/covate

Plugin Claude Code

Bundles 1 skill, 2 commands, 1 MCP server · 67 tokens together

Covate - Context-aware learning sidebar for AI coding assistants, served as an MCP server.

user-hash/Lifeblood

Skill Codex

Use when an agent should work with Lifeblood's MCP semantic-code tools: analyzing C# or Unity workspaces, querying symbols/dependencies/blast radius/file impact/test impact, checking architectural invariants, validating edits with compilecheck/diagnose, or choosing the right Lifeblood tool instead of grep-style…

beyondeye/aitasks

Skill Claude Code

Shared implementation workflow for task-based skills, with profile-check sites wrapped in Jinja conditionals.

shir-bruchim/agent-runtime-kit

Skill Claude Code

Structured GitHub PR/diff review across correctness, security, tests, and architecture with severity ratings. Use to review a PR or pull request. (Built-in /code-review for a quick working-tree diff; this is the full multi-dimension PR pass.).

juanmhidalgo/claude-plugins

Plugin Claude Code

Bundles 6 skills, 14 commands, 13 agents · 1,475 tokens together

Comprehensive code review workflow: branch reviews, PR triage, false positive dismissal, and fix tracking.

vladolaru/claude-code-plugins

Agent Claude Code

Consumes pre-gathered reconciliation context (all agent findings, source snippets, scope annotations), performs semantic deduplication, scope checking, and fact verification in one pass, then produces clean review findings.

pronskiy/php-src-developer

Plugin Claude Code

Bundles 9 skills, 1 agent · 1,413 tokens together

Claude Code plugin for developing the PHP language core (php-src): bug fixing, idea prototyping, and code review.

aegntic/aegntic-MCP

Command Claude Code

Command "jprompt_ultra_diff_review" from aegntic/aegntic-MCP, covering ultra diff review, task 1: create diff.txt, code review, diff and task 2: git diff and append.

DevvGwardo/brain-mcp

Skill Codex

Audit and harden the brain-mcp repository with Hermes Agent. Use when Codex needs to inspect this repo for reliability, orchestration, or maintainability weak spots; run a read-only Hermes audit; implement one or two bounded fixes locally; validate the result; and then commit and push only the intended changes.

peteretelej/diffchunk

MCP server Claude CodeCodexCursor +2

MCP server for navigating large diff files with intelligent chunking. Runs locally from the diffchunk Python package.