🔓Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked con…
// devtoolstirth8205/⟨Python⟩★ 30,030◷ MIT[ claude ]
Projects tagged #code-review
// code-review (30)
🔓
🔓Open-source & free — Battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments…
// devtoolsalibaba/⟨Go⟩★ 21,079◷ Apache-2.0[ claude ]
🔓🚀 PR Agent: The Original Open-Source PR Reviewer. This project is not the Qodo free tier.
// uncategorizedThe-PR-Agent/⟨Python⟩★ 12,605◷ MIT[ claude ]
🔓Annotate and review coding agent plans and code diffs visually, share with your team, send feedback to agents with one click.
// devtoolsbacknotprop/⟨TypeScript⟩★ 7,891◷ Apache-2.0[ claude ]
🔓🦸 AI 编程超能力 · 中文增强版 — superpowers（116k+ ⭐）完整汉化 + 6 个中国原创 skills，让 Claude Code / Copilot CLI / Hermes Agent / Cursor / Windsurf / Kiro / Gemini CLI 等 16 款 AI…
// devtoolsjnMetaCode/⟨JavaScript⟩★ 7,776◷ MIT[ claude ]
🔓Professional slash commands for Claude Code that provide structured workflows for software development tasks including code review, feature creation, sec…
// devtoolsqdhenry/⟨Shell⟩★ 1,330[ claude ]
🔓Multi-agent autonomous SDLC framework. Spec to deployed app. PRD, GitHub issue, OpenAPI/JSON/YAML, or one-line brief. 5 AI providers, 11 quality gates.
// devtoolsasklokesh/⟨Shell⟩★ 1,046◷ NOASSERTION[ claude ]
🔓
🔓Eleven Claude Code skills ported to OpenCode: code-review, security-review, feature-dev, frontend-design + 7 more. One config line, one plugin.
// devtoolswaybarrios/⟨JavaScript⟩★ 474◷ MIT[ claude ]
🔓Multi-agent orchestration platform for Gemini CLI, Claude Code, Codex, and Qwen Code — 39 specialists, parallel subagents, persistent sessions, and built-in…
// devtoolsjosstei/⟨JavaScript⟩★ 455◷ Apache-2.0[ claude ]
🔓A stack-agnostic Claude Code skill: strict code reviewer, pair programmer, debugger, and mentor (Python/Bash/Apps Script/JS). Security-first, phase-aware eng…
// devtoolsbjgreenberg/⟨Shell⟩★ 146◷ Apache-2.0[ claude ]
🔓Mission control for AI coding agents — run Claude Code, Codex, Antigravity, and more as one supervised team. Every submission audited; every mission reversible.
// devtoolsKilbex/⟨Rust⟩★ 116◷ Apache-2.0[ claude ]
🔓Subagent Verification for Claude AI Code Networks 2026
// devtoolsminetechnic2012-lang/⟨HTML⟩★ 116[ claude ]
🔓Multi-model consensus code review and plan review plugin for Claude Code
// devtoolsAltimateAI/★ 32◷ MIT[ claude ]
🔓Ghost personas review your code before it ships. Find edge cases, race conditions, and business logic bugs before production.
// devtoolsmturac/★ 58◷ MIT[ claude ]
🔓把实现计划派发给另一个 AI 执行，你只负责审——纯 CLI 的协调者/executor 两角色协作工具（opencode / Claude Code / grok / codex，支持远程开发机）
// devtoolsXsxdot/⟨Go⟩★ 10◷ Apache-2.0[ claude ]
🔓SUPERCHARGE AI-assisted development by using Git. Cross-model review gates, evidence-linked closure, verification profiles, model-tier routing, artifact enve…
// devtoolsdevallibus/★ 55◷ MIT[ claude ]
🔓Software engineering discipline grounded in named primary standards (OWASP, ITIL, IETF RFCs, ISO, BABOK, SBAR, and more), shipped as a Claude Code plugin and…
// mcp-serversaethrox/⟨Astro⟩★ 18◷ MIT[ claude ]
🔓Claude Code skill that quizzes you on the code Claude wrote — verify you understood it before shipping.
// skillsarimet/⟨Shell⟩★ 27◷ MIT[ claude ]
🔓Open & nano reimplementation of Sakana Fugu. A repo-native, multi-agent coding loop powered by 9+ LLMs (isolated via Claude Code) and an independent Codex re…
// devtoolsBicaMindLabs/⟨TypeScript⟩★ 24◷ Apache-2.0[ claude ]
🔓Run Claude Code, Codex, Cursor & OpenCode around the clock on a box you own. Steer, review, and merge from any screen — web app or Telegram. Self-hosted, MIT…
// devtoolsUstaLabs/⟨TypeScript⟩★ 21◷ MIT[ claude ]
🔓AI pull-request reviewer: hybrid RAG + a code graph + Claude Code. Whole-repo context, inline GitHub comments grounded on exact code. MCP server + Claude Cod…
// mcp-serversmimfort/⟨Python⟩★ 20◷ MIT[ claude ]
🔓A Claude / AI security review prompt for shipping safe apps. TRAP (True Readiness Audit Prompt) turns Claude Code, Cursor, or Copilot into an adversarial, ev…
// securitybikr/★ 17◷ MIT[ claude ]
🔓Claude Code plugin marketplace — agentic-engineering (spec-driven shape→decide→execute→measure→eval with adversarial review) + github-keeper (audit/elevate R…
// pluginsGiustoPiedimonte/⟨Python⟩★ 13◷ MIT[ claude ]
🔓Proof-of-done for AI coding agents. Local evidence receipts for Codex, Claude Code, Cursor, and GitHub Actions.
// devtoolsAtharvaMaik/⟨Python⟩★ 16◷ MIT[ claude ]
🔓Think first, then code. Where Claude Code and Codex jump straight to writing, this stays review-first: a code reviewer, security scanner, root-cause debugger…
// devtoolsPythoughts-labs/⟨Python⟩★ 14◷ Apache-2.0[ claude ]
🔓Stacked pull requests on plain git + the GitHub CLI. A Claude-native skill that splits a feature into a clean chain of small, dependent PRs — with automatic…
// skillsahmadatallah/⟨TypeScript⟩★ 12◷ MIT[ claude ]
🔓🚦 Senior-QA review skill for Claude Code: runs a regression hunter + a change reviewer in parallel, then gives one read-only SIGN OFF / DO NOT SHIP verdict…
// skillslohani-mohit/⟨Shell⟩★ 11◷ MIT[ claude ]
🔓Multi-agent Claude Code plugin: parallel specialized reviewers (bugs, security, CLAUDE.md compliance, git history, test coverage), confidence scoring, termin…
// devtoolsMANOJ21K/⟨JavaScript⟩★ 2[ claude ]
🔓Claude Code terminals pass a git baton through an adversarial, frozen-invariant review gate. Composable builder / reviewer / planner / researcher roles, rigo…
// devtoolsinferencegod/⟨JavaScript⟩★ 1◷ MIT[ claude ]