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

IT之家
IT之家
Recent Announcements
Recent Announcements
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
The GitHub Blog
The GitHub Blog
MyScale Blog
MyScale Blog
爱范儿
爱范儿
GbyAI
GbyAI
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
美团技术团队
Y
Y Combinator Blog
博客园 - 叶小钗
Apple Machine Learning Research
Apple Machine Learning Research
Martin Fowler
Martin Fowler
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
罗磊的独立博客
M
MIT News - Artificial intelligence
博客园 - Franky
V
Visual Studio Blog
I
InfoQ
V
V2EX
Hugging Face - Blog
Hugging Face - Blog
腾讯CDC
博客园 - 司徒正美
L
LangChain Blog

V2EX - 技术

Local-first 软件收录站 从 X 上搬运来的白嫖 GPT Plus 教程 阿里云百炼 Coding Plan Pro 套餐 新增当日 token 限制 大家的 Claude 弹了 kyc 嘛 现在 Google 的 Gemini 和 AI 模式降智的厉害啊 用的 TAG 家的 T, ip 跳变是否影响使用 claude 同一 apple 账户能给不同 claude 账号充值么 做了个 Go 的 MCP Server 框架,一行代码把 Gin API 接入 AI 请教各位,想回归技术,如何系统学习 Agent? OpenAI GPT-IMAGE-2 提示词合集 你是说, claude opus4.6 写代码的能力不如 gpt5.4? 关于智谱 Max 套餐要不要升级续费呢? App → CLI → App ? Github 账号被 404 了,现在没法恢复,求各位大佬指点 cursor 的次数套餐以后应该都用不了新模型了 openrouter 使用国外模型 买了咸鱼低价 Gemini pro,账号差点被盗。突然发现国内诈骗成本为零 Gemini 手机版客户端登陆总是在此国家/地区无法使用 gemini 感觉 gpt 这些低价渠道要爆了 claude code 和 codex 在 vibe coding 还有质的区别吗? 阿里 Coding Plan 一天三变, Lite 版本到期不能续费了 RAG 难以让人满意啊 2026 年了,这个世界还存在互联网精神🥹 两个账号阵亡,尼区 Claude Pro 订阅 分享下最近低价 GPT Codex 的来源(源头) OpenAI 发布 Codex 重大更新:支持自动操作电脑与长期任务自动化 使用 claude 从 0 开始开发一个校友会系统可行吗 同一个 appleid 可以给不同 chatGPT 账号订阅 plus 吗? 自动驾驶项目开发建议 终于, 降智几天之后, opus4.7 出来了
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 V2EX - 技术

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.