GitHub 发布 AI 代码评审开放基准 ReviewBench
GitHub 发布代码评审离线基准 ReviewBench，基于 1.039 亿个 GitHub PR 的分布特征，构建了覆盖 19 种语言、219 个公开 PR 的评测集，并公开数据集、评分规则与 LLM 评审模型配置。
Awaiting translation
Why it matters: GitHub 公开了 AI 代码评审基准的数据集、评分规则与评测入口，读者可据此对比不同评审智能体。
Code review
All topicsReviewing AI-written code and using AI to review code.
13 curated itemsRelated topicsTesting and verificationSpec-driven developmentExpert perspectives
Latest curated items
Items 1–13 · 13 totalGitHub Blog · CopilotSelectedAI score6666
Cursor · ChangelogSelectedAI score6262 Cursor Launches Two Bots: Rollouts and Security Review
Cursor has released two bots, Rollouts and Security Review, both available on Team and Enterprise plans.
Why it matters: The official docs cover the monitoring and security review workflows for both bots, so readers can judge whether they fit into their existing delivery pipeline.
Addy Osmani · BlogSelectedAI score8080 Addy Osmani on engineering methods for bringing AI agents into legacy codebases
Addy Osmani suggests that when introducing AI agents into brownfield codebases, you should first make hidden constraints visible and make cheap changes trustworthy. He recommends dividing code into green, yellow, and red zones: green zones with solid tests let agents move in small, fast steps; yellow zones require writing characterization tests first; and red zones involving sensitive logic like authentication, billing, and permissions must have humans involved step by step. The zones are drawn by hand, and a yellow zone can only be upgraded to green once characterization tests exist and the module owner has reviewed the first batch of changes.
Why it matters: The author turns the constraints of bringing agents into an old codebase into actionable rules—zoning, characterization tests, and migration units—and cites migration data from several companies as reference.
Vibe Code Textbook · ArticlesSelectedAI score8787 审查 coding agent 的 diff：检查清单最先抓到什么
作者给出一份按危害排序的十项 agent diff 检查清单，依次看被删除的测试、被跳过或弱化的断言、宽泛异常捕获、新增依赖、任务范围外文件、CI 配置改动、疑似密钥、遗留标记和净删除超过 40 行的文件。
Awaiting translation
Why it matters: 给出按危害排序的十项 agent diff 检查清单，并附可复用的扫描脚本与行号定位。
Hacker News · Agent SkillsSelectedAI score7878 mattpocock releases AI coding Agent Skills built for real engineering
Author mattpocock has released a set of AI coding Agent Skills he uses day to day. They're aimed at real engineering rather than vibe coding, and the emphasis is on being small, easy to modify, composable, and compatible with any model.
Why it matters: The author breaks years of engineering experience into a set of composable Skills and explains the failure mode each one targets, so readers can judge whether they fit into their own development workflow.
Augment Code · BlogSelectedAI score6262 Augment Code Expands Cosmos: Turning Code Review into an Agentic PR-to-Merge Loop
Augment Code has extended its Cosmos review system from code review to a full PR-to-merge loop, adding four capabilities: Verifier, PR Fixer, Review Dashboard, and cosmos approve. Dedicated Experts handle risk analysis, line-by-line correctness review, design review, runtime verification, and fixes.
Why it matters: Augment has expanded code review into a PR-to-merge loop covering fixes, verification, and approval, giving readers a way to judge how multi-agent division of labor plays out in practice.
OpenAI Developer Blog · CodexSelectedAI score7171 Codex Code Review now supports custom review rules in AGENTS.md
OpenAI has added custom repository rules to Codex Code Review: you can put review guidelines in AGENTS.md, and Codex applies them during review and cites where each one came from in its findings. In OpenAI's own evaluation, the rule-guided version caught 98% of the required custom issues, versus 58.3% for the baseline. The guidance is to start with non-obvious invariants like compatibility requirements and data boundaries, put repo-level rules in the root directory and service-level rules in the corresponding directory, and leave formatting and mechanical checks to CI.
Why it matters: OpenAI lays out the capabilities, the syntax, and the evaluation data for Codex Code Review custom rules, so you can judge how to bake your team's review experience into AGENTS.md.
AI Hero · Skills UpdatesSelectedAI score6565 AI Hero skills repo ships v1.1: adds /wayfinder, renames /to-spec and /to-tickets
AI Hero's skills repo ships v1.1, renaming /to-prd to /to-spec, merging /to-plan and /to-issues into /to-tickets, and adding new Skills like /wayfinder, /research, and /prototype.
Why it matters: The author walks through the full Skill flow from grilling to deployment and gives the migration commands for the renames, the merge, and the new /wayfinder—useful for anyone building an AI development workflow.
Lovable · BlogSelectedAI score8888 花掉 8.5 万美元 token 后，我在 Lovable 扩展智能体编程的经验
Lovable 一名工程师从今年 1 月到 6 月把个人 token 花费从每月约 600 美元推到 5 月的约 2.5 万美元、累计约 8.5 万美元，同时把每周合并 PR 数从 20-30 个提升到 150 个以上。
Awaiting translation
Why it matters: 作者公开了自己每月约 2.5 万美元 token 的智能体开发配置，包括风险分级、多智能体评审和上下文管理，可迁移到其他团队。
AI Hero · Skills UpdatesSelectedAI score6060 AI Hero 新增 /handoff 与 /prototype 两个 Skill 并修复多个已有 Skill
AI Hero 在其 skills 仓库新增 /handoff 和 /prototype 两个 Skill。
Awaiting translation
Why it matters: 作者公开了 /handoff 与 /prototype 两个 Skill 的设计思路，可看到上下文交接与原型验证如何嵌入智能体工作流。
Ryan LopopoloSelectedAI score7474 智能体时代的生产函数变了：实现不再稀缺，验证才是
作者认为，软件组织一直把人的实现时间当作稀缺投入，智能体打破了这个假设，因此策略必须可执行、验证必须随实现规模扩展。他以在大型 TypeScript 代码库开启 ESLint 的 no-await-in-loop 规则为例，发现 600 处违规，过去这需要昂贵的迁移，现在一个 PR 就能完成修复并补齐测试覆盖。
Awaiting translation
Why it matters: 作者以开启 ESLint 规则、迁移 600 处违规的亲身实践，说明智能体时代实现成本下降后，约束与验证为何成为新的稀缺环节。
OpenAI Developer Blog · CodexSelectedAI score8787 OpenAI 如何用 Skills 加速 Agents SDK 仓库维护
OpenAI 用 Codex 配合仓库内的 Skills、AGENTS.md 和 GitHub Actions 维护 Agents SDK 仓库，把验证、发布准备、示例集成测试和 PR 评审变成可重复流程。
Awaiting translation
Why it matters: OpenAI 官方公开了用 Skills、AGENTS.md 和 GitHub Action 维护 Agents SDK 仓库的完整配置，可迁移到其他开源项目。
Jesse VincentSelectedAI score7171 How I Used a Coding Agent in September 2025: A Dual-Session Workflow with Claude Code
The author walks through their full workflow with Claude Code: first isolating tasks with git worktree, then using a brainstorming prompt to make Claude ask only one question at a time and confirm the design in stages, and finally using a planning prompt to break the plan into small tasks and write them into docs/plans/.
Why it matters: The author splits Claude Code into two sessions—an architect and an implementer—and shares reusable prompts plus a git worktree approach for isolating tasks.