Token导航 LogoToken导航TokenDH.com
研究检索只读github未标认证来源可访问许可证需确认审计通过

codex-impl-reviewCodex impl 审查

Agent Skill

codex-impl-review 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

396

周安装

17

GitHub Stars

59

下载量

139
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-impl-review(Codex impl 审查)
来源仓库:https://github.com/lploc94/codex_skill
仓库路径:skills/codex-impl-review
安装命令:
npx skills add https://github.com/lploc94/codex_skill --skill codex-impl-review
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-impl-review

简介

codex-impl-review 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。

  • 它对未提交的更改或分支差异执行对抗性审查,在合并前识别潜在风险。
  • 支持工作树模式与分支模式,可调整审查强度等级从 low 到 xhigh。
  • 安装命令为 npx skills add https://github.com/lploc94/codex_skill --skill codex-impl-review,需 staged changes 或 commit history。
  • 使用前建议核实 RUNNER_PATH 变量设置正确及 codex-review 技能包已部署。

SKILL.md

Codex Implementation Review

Purpose

Use this skill to run adversarial review on uncommitted changes before commit, or on branch changes before merge.

Prerequisites

  • Working-tree mode (default): working tree has staged or unstaged changes.
  • Branch mode: current branch differs from base branch (has commits not in base).
  • codex CLI is installed and authenticated.
  • codex-review skill pack is installed (npx github:lploc94/codex_skill).

Runner

RUNNER="{{RUNNER_PATH}}"

Workflow

  1. Ask user to choose review effort level: low, medium, high, or xhigh (default: high). Ask review mode: working-tree (default) or branch. If branch mode, ask for base branch name and validate (see workflow.md for base branch discovery). Set EFFORT and MODE.
  2. Run pre-flight checks (see references/workflow.md §1.5).
  3. Build prompt from references/prompts.md (Working Tree or Branch Review Prompt), following the Placeholder Injection Guide.
  4. Start round 1 with node "$RUNNER" start --working-dir "$PWD" --effort "$EFFORT".
  5. Poll with adaptive intervals (Round 1: 60s/60s/30s/15s..., Round 2+: 30s/15s...). After each poll, report specific activities from poll output (e.g. which files Codex is reading, what topic it is analyzing). See references/workflow.md for parsing guide. NEVER report generic "Codex is running" — always extract concrete details.
  6. Parse issue list with references/output-format.md.
  7. Fix valid issues in code; rebut invalid findings with evidence.
  8. Resume debate via --thread-id until APPROVE, stalemate, or hard cap (5 rounds).
  9. Return final review summary, residual risks, and recommended next steps.

Effort Level Guide

LevelDepthBest forTypical time
lowSurface checkQuick sanity check~2-3 min
mediumStandard reviewMost day-to-day work~5-8 min
highDeep analysisImportant features~10-15 min
xhighExhaustiveCritical/security-sensitive~20-30 min

Required References

  • Detailed execution: references/workflow.md
  • Prompt templates: references/prompts.md
  • Output contract: references/output-format.md

Rules

  • If invoked during Claude Code plan mode, exit plan mode first — this skill requires code editing.
  • Codex reviews only; it does not edit files.
  • Preserve functional intent unless fix requires behavior change.
  • Every accepted issue must map to a concrete code diff.
  • If stalemate persists, present both sides and defer to user.

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

34.28%
按下载量换算48

Claude

29.46%
按下载量换算41

Cursor

17.28%
按下载量换算24

Gemini CLI

9.92%
按下载量换算14

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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。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