本是为了白嫖5刀开的第一个月Go订阅，但没注意到OpenCodeGo会自动续费，于是连着几天发退款申请了，前几次次申请被官方拒绝说退款，后面接着炮轰官方，说自己只是个大学生 ，给孩子退款吧哈哈哈哈，没想到还真成了！ 1 个帖子 - 1 位参与者 阅读完整话题
VibeCoding经验总结 全局 开发工具 codex app,claude code,opencode 工具 CodeGraph 索引项目文件，减少token消耗，加快对项目的加载速度 everything claude code 一套可复用的工程工作流组件库，把常用的 agents（子代理）、skills（工作流技能）、slash commands（斜杠命令）、rules（规则约束）、hooks（事件钩子自动化）、以及 MCP server 配置示例集中在一起，提供一套可直接复用的工程化工作流。 superpower 是一套给 AI 编程助手（如 Claude Code、Cursor 等）用的技能框架 ，把资深工程师的开发经验固化为可组合的技能模块，强制 AI 遵循标准化开发流程，从"盲目写代码"变成"有规划、重质量、可追溯"的专业开发伙伴。 git 善用git防止失控 前端 getdesign 把主流网站的设计方案总结成了md,开发是让ai参考这个md，样式永远不失控，审美在线 OpenDesign（不好用，不如stitch好用） 前端原型设计工具，本地部署，支持codex claude等 Stitch 用google的stitch设计界面，现在这个还是免费的，设计出来后可以直接通过mcp 根codex或者claude 链接 然后实现 开发思路 1 先通过stitch完成界面的设计 2 下载界面，然ai解析界面然后分析需求形成prd文档 3 根据prd文档形成需求文档，功能文档，技术文档 4 根据这些文档开始开发 5 过程中多形成项目skills，可以节约token 最好所有操作都文档先行，不要一上来就写代码，最好所有操作都文档先行，不要一上来就写代码，最好所有操作都文档先行，不要一上来就写代码 中间测试，开发过程 以上插件都会帮你自动规划 3 个帖子 - 2 位参与者 阅读完整话题
我现在设想是codegraph配合todo tree可视化调度。同样热门上那个类comfyui的工作流节点有点用不明白。 但是现在卡在怎么让ai强制使用codegraph的mcp，已经在codex的全局agent和项目agent都声明，任何增删改查的行为都必须通过codegraph的mcp，还试了钩子发挥tool如果没codegraph进行retry(虽然不知道用着对不对)。但是有时候ai大人真的鸟都不鸟我。 7 个帖子 - 7 位参与者 阅读完整话题
有什么方法，可以每天都检测更新吗？ 发现 codegraph 比 gitnexus 更好用些，只是体感，更省 token
有什么方法，可以每天都检测更新吗？ 发现 codegraph 比 gitnexus 更好用些，只是体感，更省 token
有什么方法，可以每天都检测更新吗？ 发现 codegraph 比 gitnexus 更好用些，只是体感，更省 token
有什么方法，可以每天都检测更新吗？ 发现 codegraph 比 gitnexus 更好用些，只是体感，更省 token
有什么方法，可以每天都检测更新吗？ 发现 codegraph 比 gitnexus 更好用些，只是体感，更省 token
有什么方法，可以每天都检测更新吗？ 发现 codegraph 比 gitnexus 更好用些，只是体感，更省 token
CodeGraph CodeGraph这个MCP会提前把代码库构建成知识图谱，佬友们有用过的吗？他相对于ace或者fast-context会有更好的效果吗？ 2 个帖子 - 2 位参与者 阅读完整话题
使用 Github:Codeg （开启多智能体协同的情况下）在 claude code 进行开发，在一个会话里使用 skill 和不使用 skill 的区别效果： 使用 skill 后任务完成会由 codex 自动 review ，有问题直接修复，解决了我以前手动来回倒腾的问题。这是 skill 内容（如果使用其它子智能体 review 的话，可以把 skill 里面的 codex 替换一下），可以直接在 skills 管理里面添加，欢迎大佬们使用反馈，或者创作分享： name: sub-agent-review-loop description: Use when any task could modify code, tests, config, schemas, migrations, deps, build/deploy scripts, artifacts, or behavior before completion Sub-Agent Review Loop Overview Use Codex as an independent reviewer after work that can modify artifacts or behavior. Loop until the latest result is production-ready. Core principle: Work is not complete until Codex approves the latest fixed version as production-ready. Required Loop Finish the implementation and run the relevant local checks. Call Codeg MCP delegate_to_agent with agent_type: "codex" , absolute working_dir , and a self-contained task containing the request, changed files or diff/SHAs, checks run, and constraints. Require this quality bar: production-ready; do not approve while in-scope correctness, security, reliability, data, API, UX, performance, test, or maintainability issues remain. Use receiving-code-review : verify claims, fix valid feedback, and push back with evidence on invalid or out-of-scope feedback. Run the relevant checks again after fixes. Send the updated result back to Codex for re-review. Repeat until Codex approves the latest version with no unresolved valid in-scope issues. Do not use an ordinary in-session Task/general-purpose reviewer as a substitute. If delegate_to_agent is missing, Codeg MCP is not injected/enabled, the call fails, or the Codex child session fails, tell the human and leave the task incomplete or blocked. Do not self-review instead. Codeg MCP Call { "agent_type": "codex", "working_dir": "<absolute current working directory>", "task": "<complete review prompt; child cannot see this conversation>" } Codex Review Prompt Review these completed changes as Codex. Quality bar: production-ready. Do not approve while in-scope correctness, security, reliability, data, API, UX, performance, test, or maintainability issues remain. User request: <request> Changes to review: <diff, changed files, or BASE_SHA..HEAD_SHA> Verification already run: <commands and results> Return: - Verdict: APPROVED or CHANGES_REQUESTED - Critical / Important / Minor issues - Required verification For re-review, add: Re-review the latest state after fixes against the same production-ready quality bar. Do not approve unless the current version is ready to ship. Quick Reference Situation Required action Artifact/behavior-changing task is done Call delegate_to_agent before final response Codex finds valid issues Fix, verify, send back to Codex Feedback seems wrong Verify, push back with evidence Minor issues remain Fix valid ones unless they expand scope or risk Codex approves latest version Final response may be sent after checks pass Red Flags Rationalizations: "The change is tiny." "The user is waiting." "Tests already passed." "I reviewed my own diff." "Codex only found nits." "I fixed the issue, so another review is unnecessary." "I used a generic reviewer subagent instead of Codeg MCP." Common Mistakes Mistake Fix Reviewing the original diff after fixes Ask Codex to review the latest state Blindly applying feedback Verify with codebase evidence first Stopping after fixes Re-dispatch Codex after changes Treating tests as a replacement for review Run tests and Codex review Using an in-session reviewer Use Codeg MCP delegate_to_agent Completion Gate Final response is allowed only after implementation and accepted fixes are done, relevant checks pass or limitations are stated, Codex approves the latest version, and no known valid production-readiness issue remains in scope.
使用 Github:Codeg （开启多智能体协同的情况下）在 claude code 进行开发，在一个会话里使用 skill 和不使用 skill 的区别效果： 使用 skill 后任务完成会由 codex 自动 review ，有问题直接修复，解决了我以前手动来回倒腾的问题。这是 skill 内容（如果使用其它子智能体 review 的话，可以把 skill 里面的 codex 替换一下），可以直接在 skills 管理里面添加，欢迎大佬们使用反馈，或者创作分享： name: sub-agent-review-loop description: Use when any task could modify code, tests, config, schemas, migrations, deps, build/deploy scripts, artifacts, or behavior before completion Sub-Agent Review Loop Overview Use Codex as an independent reviewer after work that can modify artifacts or behavior. Loop until the latest result is production-ready. Core principle: Work is not complete until Codex approves the latest fixed version as production-ready. Required Loop Finish the implementation and run the relevant local checks. Call Codeg MCP delegate_to_agent with agent_type: "codex" , absolute working_dir , and a self-contained task containing the request, changed files or diff/SHAs, checks run, and constraints. Require this quality bar: production-ready; do not approve while in-scope correctness, security, reliability, data, API, UX, performance, test, or maintainability issues remain. Use receiving-code-review : verify claims, fix valid feedback, and push back with evidence on invalid or out-of-scope feedback. Run the relevant checks again after fixes. Send the updated result back to Codex for re-review. Repeat until Codex approves the latest version with no unresolved valid in-scope issues. Do not use an ordinary in-session Task/general-purpose reviewer as a substitute. If delegate_to_agent is missing, Codeg MCP is not injected/enabled, the call fails, or the Codex child session fails, tell the human and leave the task incomplete or blocked. Do not self-review instead. Codeg MCP Call { "agent_type": "codex", "working_dir": "<absolute current working directory>", "task": "<complete review prompt; child cannot see this conversation>" } Codex Review Prompt Review these completed changes as Codex. Quality bar: production-ready. Do not approve while in-scope correctness, security, reliability, data, API, UX, performance, test, or maintainability issues remain. User request: <request> Changes to review: <diff, changed files, or BASE_SHA..HEAD_SHA> Verification already run: <commands and results> Return: - Verdict: APPROVED or CHANGES_REQUESTED - Critical / Important / Minor issues - Required verification For re-review, add: Re-review the latest state after fixes against the same production-ready quality bar. Do not approve unless the current version is ready to ship. Quick Reference Situation Required action Artifact/behavior-changing task is done Call delegate_to_agent before final response Codex finds valid issues Fix, verify, send back to Codex Feedback seems wrong Verify, push back with evidence Minor issues remain Fix valid ones unless they expand scope or risk Codex approves latest version Final response may be sent after checks pass Red Flags Rationalizations: "The change is tiny." "The user is waiting." "Tests already passed." "I reviewed my own diff." "Codex only found nits." "I fixed the issue, so another review is unnecessary." "I used a generic reviewer subagent instead of Codeg MCP." Common Mistakes Mistake Fix Reviewing the original diff after fixes Ask Codex to review the latest state Blindly applying feedback Verify with codebase evidence first Stopping after fixes Re-dispatch Codex after changes Treating tests as a replacement for review Run tests and Codex review Using an in-session reviewer Use Codeg MCP delegate_to_agent Completion Gate Final response is allowed only after implementation and accepted fixes are done, relevant checks pass or limitations are stated, Codex approves the latest version, and no known valid production-readiness issue remains in scope.
codegraph 和 fast_context 是同样的功能吗？小白求教 2 个帖子 - 2 位参与者 阅读完整话题
针对这个工具编写了一片完整的博客： CodeGraph：让 AI 编程工具真正读懂大型代码库 最近发现一个挺有意思的工具：CodeGraph 。它没有花里胡哨的力图界面，但是它足够精确和快，而且有文件自动监听更新。 它特别适合配合 Cursor 、Claude Code 这种 AI Coding 工具一起用。 很多时候 AI 写代码慢，其实不是因为“不会写”，而是它一直在那疯狂搜索项目、分析调用链、到处 grep 😂 尤其大项目里特别明显： 反复读文件 找不到真实入口 改错地方 上下文越吃越大 CodeGraph 做的事情，本质上就是提前帮 AI 把整个项目的代码关系整理好。 比如： 谁调用了谁 类型之间怎么关联 模块依赖关系 哪些文件真正相关 这样 Cursor / Claude Code 在分析代码时，就不用像无头苍蝇一样到处探索了。 我实际用下来最大的感受就是： AI “理解项目”的速度明显快很多。 尤其是大型 monorepo ，效果会更明显。 感觉“代码图谱 + AI” 这个方向，后面会越来越重要。
使用 Github:Codeg （开启多智能体协同的情况下）在 claude code 进行开发，在一个会话里使用 skill 和不使用 skill 的区别效果： 使用 skill 后任务完成会由 codex 自动 review ，有问题直接修复，解决了我以前手动来回倒腾的问题。这是 skill 内容（如果使用其它子智能体 review 的话，可以把 skill 里面的 codex 替换一下），可以直接在 skills 管理里面添加，欢迎大佬们使用反馈，或者创作分享： name: sub-agent-review-loop description: Use when any task could modify code, tests, config, schemas, migrations, deps, build/deploy scripts, artifacts, or behavior before completion Sub-Agent Review Loop Overview Use Codex as an independent reviewer after work that can modify artifacts or behavior. Loop until the latest result is production-ready. Core principle: Work is not complete until Codex approves the latest fixed version as production-ready. Required Loop Finish the implementation and run the relevant local checks. Call Codeg MCP delegate_to_agent with agent_type: "codex" , absolute working_dir , and a self-contained task containing the request, changed files or diff/SHAs, checks run, and constraints. Require this quality bar: production-ready; do not approve while in-scope correctness, security, reliability, data, API, UX, performance, test, or maintainability issues remain. Use receiving-code-review : verify claims, fix valid feedback, and push back with evidence on invalid or out-of-scope feedback. Run the relevant checks again after fixes. Send the updated result back to Codex for re-review. Repeat until Codex approves the latest version with no unresolved valid in-scope issues. Do not use an ordinary in-session Task/general-purpose reviewer as a substitute. If delegate_to_agent is missing, Codeg MCP is not injected/enabled, the call fails, or the Codex child session fails, tell the human and leave the task incomplete or blocked. Do not self-review instead. Codeg MCP Call { "agent_type": "codex", "working_dir": "<absolute current working directory>", "task": "<complete review prompt; child cannot see this conversation>" } Codex Review Prompt Review these completed changes as Codex. Quality bar: production-ready. Do not approve while in-scope correctness, security, reliability, data, API, UX, performance, test, or maintainability issues remain. User request: <request> Changes to review: <diff, changed files, or BASE_SHA..HEAD_SHA> Verification already run: <commands and results> Return: - Verdict: APPROVED or CHANGES_REQUESTED - Critical / Important / Minor issues - Required verification For re-review, add: Re-review the latest state after fixes against the same production-ready quality bar. Do not approve unless the current version is ready to ship. Quick Reference Situation Required action Artifact/behavior-changing task is done Call delegate_to_agent before final response Codex finds valid issues Fix, verify, send back to Codex Feedback seems wrong Verify, push back with evidence Minor issues remain Fix valid ones unless they expand scope or risk Codex approves latest version Final response may be sent after checks pass Red Flags Rationalizations: "The change is tiny." "The user is waiting." "Tests already passed." "I reviewed my own diff." "Codex only found nits." "I fixed the issue, so another review is unnecessary." "I used a generic reviewer subagent instead of Codeg MCP." Common Mistakes Mistake Fix Reviewing the original diff after fixes Ask Codex to review the latest state Blindly applying feedback Verify with codebase evidence first Stopping after fixes Re-dispatch Codex after changes Treating tests as a replacement for review Run tests and Codex review Using an in-session reviewer Use Codeg MCP delegate_to_agent Completion Gate Final response is allowed only after implementation and accepted fixes are done, relevant checks pass or limitations are stated, Codex approves the latest version, and no known valid production-readiness issue remains in scope.
使用 Codeg （开启多智能体协同的情况下）在claude code进行开发，在一个会话里使用skill和不使用skill的区别效果： 使用skill后任务完成会由codex自动review，有问题直接修复，解决了我以前手动来回倒腾的问题。这是skill内容（如果使用其它子智能体review的话，可以把skill里面的codex替换一下），可以直接在skills管理里面添加： --- name: sub-agent-review-loop description: Use when any task could modify code, tests, config, schemas, migrations, deps, build/deploy scripts, artifacts, or behavior before completion --- # Sub-Agent Review Loop ## Overview Use Codex as an independent reviewer after work that can modify artifacts or behavior. Loop until the latest result is production-ready. **Core principle:** Work is not complete until Codex approves the latest fixed version as production-ready. ## Required Loop 1. Finish the implementation and run the relevant local checks. 2. Call Codeg MCP `delegate_to_agent` with `agent_type: "codex"`, absolute `working_dir`, and a self-contained `task` containing the request, changed files or diff/SHAs, checks run, and constraints. 3. Require this quality bar: **production-ready; do not approve while in-scope correctness, security, reliability, data, API, UX, performance, test, or maintainability issues remain.** 4. Use `receiving-code-review`: verify claims, fix valid feedback, and push back with evidence on invalid or out-of-scope feedback. 5. Run the relevant checks again after fixes. 6. Send the updated result back to Codex for re-review. 7. Repeat until Codex approves the latest version with no unresolved valid in-scope issues. Do not use an ordinary in-session Task/general-purpose reviewer as a substitute. If `delegate_to_agent` is missing, Codeg MCP is not injected/enabled, the call fails, or the Codex child session fails, tell the human and leave the task incomplete or blocked. Do not self-review instead. ## Codeg MCP Call ```json { "agent_type": "codex", "working_dir": "<absolute current working directory>", "task": "<complete review prompt; child cannot see this conversation>" } ``` ## Codex Review Prompt ```markdown Review these completed changes as Codex. Quality bar: production-ready. Do not approve while in-scope correctness, security, reliability, data, API, UX, performance, test, or maintainability issues remain. User request: <request> Changes to review: <diff, changed files, or BASE_SHA..HEAD_SHA> Verification already run: <commands and results> Return: - Verdict: APPROVED or CHANGES_REQUESTED - Critical / Important / Minor issues - Required verification ``` For re-review, add: ```markdown Re-review the latest state after fixes against the same production-ready quality bar. Do not approve unless the current version is ready to ship. ``` ## Quick Reference | Situation | Required action | | --- | --- | | Artifact/behavior-changing task is done | Call `delegate_to_agent` before final response | | Codex finds valid issues | Fix, verify, send back to Codex | | Feedback seems wrong | Verify, push back with evidence | | Minor issues remain | Fix valid ones unless they expand scope or risk | | Codex approves latest version | Final response may be sent after checks pass | ## Red Flags Rationalizations: - "The change is tiny." - "The user is waiting." - "Tests already passed." - "I reviewed my own diff." - "Codex only found nits." - "I fixed the issue, so another review is unnecessary." - "I used a generic reviewer subagent instead of Codeg MCP." ## Common Mistakes | Mistake | Fix | | --- | --- | | Reviewing the original diff after fixes | Ask Codex to review the latest state | | Blindly applying feedback | Verify with codebase evidence first | | Stopping after fixes | Re-dispatch Codex after changes | | Treating tests as a replacement for review | Run tests and Codex review | | Using an in-session reviewer | Use Codeg MCP `delegate_to_agent` | ## Completion Gate Final response is allowed only after implementation and accepted fixes are done, relevant checks pass or limitations are stated, Codex approves the latest version, and no known valid production-readiness issue remains in scope. 欢迎佬们使用反馈，或者创作分享 。 1 个帖子 - 1 位参与者 阅读完整话题
如图，这个项目最近在github上还挺火的，有佬亲身体验过吗 3 个帖子 - 3 位参与者 阅读完整话题
邀请大佬们体验一下，多智能体协作的爽感。 可以在任意主智能体里发起对话，然后其它 N 个子智能体协作（支持 claude code 、codex 、gemini 、opencode 等）。 比如我经常有这样的场景，使用 claude code 开发，然后 codex 来 review （自我感觉 codex 大局观强，claude code 的编码能力强），然后把 codex 的 review 发给 claude code ，claude code 基本都回复的情况属实，然后接着干活，每次都需要重复的手动操作一遍。 我捣腾多了之后就一直想着实现多智能体协作，在 claude code 把需求开发完了之后 codex 自动 review 代码，然后 claude code 评估，接着处理，在一个会话里自动把流程跑完。 现在多智能体协作已支持，诚邀大佬们体验一波，另外可以使用这个特性，结合一些 skills 或工具，可以碰撞一些意想不到的火花。 开源地址： https://github.com/xintaofei/codeg
邀请大佬们体验一下，多智能体协作的爽感。 可以在任意主智能体里发起对话，然后其它 N 个子智能体协作（支持 claude code 、codex 、gemini 、opencode 等）。 比如我经常有这样的场景，使用 claude code 开发，然后 codex 来 review （自我感觉 codex 大局观强，claude code 的编码能力强），然后把 codex 的 review 发给 claude code ，claude code 基本都回复的情况属实，然后接着干活，每次都需要重复的手动操作一遍。 我捣腾多了之后就一直想着实现多智能体协作，在 claude code 把需求开发完了之后 codex 自动 review 代码，然后 claude code 评估，接着处理，在一个会话里自动把流程跑完。 现在多智能体协作已支持，诚邀大佬们体验一波，另外可以使用这个特性，结合一些 skills 或工具，可以碰撞一些意想不到的火花。 开源地址： https://github.com/xintaofei/codeg
邀请大佬们体验一下，多智能体协作的爽感。 可以在任意主智能体里发起对话，然后其它 N 个子智能体协作（支持 claude code 、codex 、gemini 、opencode 等）。 比如我经常有这样的场景，使用 claude code 开发，然后 codex 来 review （自我感觉 codex 大局观强，claude code 的编码能力强），然后把 codex 的 review 发给 claude code ，claude code 基本都回复的情况属实，然后接着干活，每次都需要重复的手动操作一遍。 我捣腾多了之后就一直想着实现多智能体协作，在 claude code 把需求开发完了之后 codex 自动 review 代码，然后 claude code 评估，接着处理，在一个会话里自动把流程跑完。 现在多智能体协作已支持，诚邀大佬们体验一波，另外可以使用这个特性，结合一些 skills 或工具，可以碰撞一些意想不到的火花。 开源地址： https://github.com/xintaofei/codeg