Token导航 LogoToken导航TokenDH.com
研究检索external-servicegithub未标认证来源可访问许可证需确认审计提醒

codex-think-aboutCodex think about 搜索

Agent Skill

codex-think-about 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

662

周安装

8

GitHub Stars

59

下载量

65
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:codex-think-about(Codex think about 搜索)
来源仓库:https://github.com/lploc94/codex_skill
仓库路径:skills/codex-think-about
安装命令:
npx skills add https://github.com/lploc94/codex_skill --skill codex-think-about
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/lploc94/codex_skill --skill codex-think-about

简介

codex-think-about 用于同行推理而非代码审查,支持多级思考深度调节。

  • Claude 与 Codex 作为平等分析伙伴参与辩论循环。
  • 需先选择 effort level(high/xhigh),再构建事实导向问题。
  • 输出包含 round-1 prompt 模板与参考材料路径说明。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

Codex Think About

Purpose

Use this skill for peer reasoning, not code review. Claude and Codex are equal analytical peers; Claude orchestrates the debate loop and final synthesis.

Prerequisites

  • A clear question or decision topic from the user.
  • codex CLI installed and authenticated.
  • codex-review skill pack is installed (npx github:lploc94/codex_skill).

Runner

RUNNER="{{RUNNER_PATH}}"

Workflow

  1. Ask user to choose reasoning effort level: low, medium, high, or xhigh (default: high). Gather factual context only (no premature opinion). Set EFFORT.
  2. Build round-1 prompt from references/prompts.md.
  3. Start Codex + Claude Independent Analysis (parallel): a. Start Codex thread: node "$RUNNER" start --working-dir "$PWD" --effort "$EFFORT" --sandbox danger-full-access. b. Claude Independent Analysis (IMMEDIATELY, before polling): Analyze the question independently using own knowledge and optionally MCP tools. Follow the structured format in references/claude-analysis-template.md. Complete this BEFORE reading any Codex output. See references/workflow.md Step 2.5 for detailed instructions. c. INFORMATION BARRIER: Do NOT read $STATE_DIR/review.md or interpret Codex's conclusions until Step 5. Poll activity telemetry (file reads, URLs, topics) is allowed for progress reporting.
  4. Poll Codex with adaptive intervals (Round 1: 90s/60s/30s/15s..., Round 2+: 45s/30s/15s...). After each poll, report specific activities from poll output. See references/workflow.md for parsing guide. NEVER report generic "Codex is running".
  5. Cross-Analysis: After Codex completes, compare Claude's independent analysis with Codex output. Identify genuine agreements, genuine disagreements, and unique perspectives from each side. See references/workflow.md Step 4.
  6. Resume via --thread-id and loop until consensus, stalemate, or hard cap (5 rounds).
  7. Present user-facing synthesis with agreements, disagreements, cited sources, and confidence.

Effort Level Guide

LevelDepthBest for
lowSurface checkQuick sanity check
mediumStandard reviewMost day-to-day work
highDeep analysisImportant features
xhighExhaustiveCritical/security-sensitive

Required References

  • Execution loop: references/workflow.md
  • Prompt templates: references/prompts.md
  • Output contract: references/output-format.md
  • Claude analysis format: references/claude-analysis-template.md

Rules

  • Keep roles as peers; no reviewer/implementer framing.
  • Codex must NOT modify, create, or delete ANY project files. danger-full-access sandbox is used SOLELY for web search. Prompt contains strict guardrails.
  • Codex MUST cite sources (URL) for factual claims from web.
  • Separate researched facts (with sources) from opinions.
  • Detect stalemate when arguments repeat with no new evidence.
  • End with clear recommendations, source list, and open questions.
  • Information barrier: Claude MUST complete its independent analysis (Step 3b) before reading Codex output. This prevents anchoring bias.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

33.68%
按下载量换算22

Claude

33.62%
按下载量换算22

Cursor

18.87%
按下载量换算12

Gemini CLI

9.55%
按下载量换算6

安全审计

Gen Agent Trust Hub

可疑

Socket

可疑

Snyk

可疑

权限和风险

external-service

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills