惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

月光博客
月光博客
罗磊的独立博客
The GitHub Blog
The GitHub Blog
V
V2EX
Last Week in AI
Last Week in AI
博客园 - 聂微东
MyScale Blog
MyScale Blog
美团技术团队
L
LangChain Blog
博客园 - Franky
腾讯CDC
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
博客园_首页
S
SegmentFault 最新的问题
爱范儿
爱范儿
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
Stack Overflow Blog
Stack Overflow Blog
量子位
小众软件
小众软件
宝玉的分享
宝玉的分享
J
Java Code Geeks
Google DeepMind News
Google DeepMind News
D
Docker
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报

Claude Code

听说 Claude Code 可能要通过视频监控程序员,防止程序员离开电脑前了 大家用 claude code 是订阅还是买 apikey 来使用啊 claude -p 现在到底走什么额度啊 无法使用 claude remote-control Java 开发同行你们是通过哪种方式调用 Claude 进行 AI 编程的 如何简单地在 Claude Code 里对不同的 workflow 设置不同的 DS 模型温度 用 Claude Code Vibe Coding 从 0 到 1 开发过程 想请教一下大家,如何稳定使用 claude code,稳定使用的成本是多少呢? claude code 有好用的 windows 平台上的图形界面吗? Claude Code + DS V4 Flash,CC 搞鬼了? claude code 突然日文跟我对话 请教一下各位, claude code 怎么像 codex 那样 branch in a new chat? 最近做了一款终端软件,配合插件可以管理 clalude code 启动模型和查看 claude code 调用详情,大家可是体验拍砖 A\这是疯了? Claude Code 崩了 claude code 这类工具这么实现全自动化完成需求? 求证: Claude Code 的响应速度是不是普遍比 Cursor(opus)、Codex 慢? Claude Code 周限额临时提升 50% claude 这次更新是不是意味着 max 号池中转基本完蛋了 有没有友友知道大量的 claude 的 api 从哪里搞啊? Claude Code(Opus4.7 模型)支持快速模式 中转站有开源版本吗? vscode 远程 root 用户开发无法开启 auto 模式的解决 大家平时 claude 等配置三方接口用 200K 还是 1M? 求稳定 Claude Code 车队 V2EX › 登录 claude code mac 桌面端感觉很好用啊,为啥还是很多人只用 cli? Claude Code 最近总是在修复代码缩进 请教 Windows Claude code cli 要如何更新? CLaude code 会话你们是怎么删除?
分享一个 Codeg 多智能体协同下的 skill 案例,在一个会话里...
molicloud · 2026-05-27 · via Claude Code

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: claude code

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

  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

{
  "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.