Vet代码审查工具：AI驱动，实时检查Git差异与对话历史，提升代码质量

vet by atilladeniz/kubeli

1 周安装量

308 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/atilladeniz/kubeli --skill vet

开发自动化代码质量

🇨🇳中文介绍

Vet

在完成任何逻辑单元代码变更后立即运行 Vet。不要批量处理变更，不要等待被要求运行 Vet，确保你是积极主动的。

Vet 会审查 git 差异和对话历史记录，以发现代码变更和对话历史记录中的问题。当结合对话历史记录频繁运行时，它最为有效，这有助于它捕捉请求内容与实际实现之间的误解。尽管如此，vet 并不能替代运行测试。

安装

使用 pip、pipx 或 uv 安装 vet：

# 使用 pip
pip install verify-everything

# 使用 pipx
pipx install verify-everything

# 使用 uv
uv tool install verify-everything

# 验证安装：
vet --help

运行 Vet

标准用法

运行 vet 前，请确定正确的 Python 二进制文件：

$(command -v python3 || command -v python)

使用任何可解析的命令（优先使用 python3）。下面的示例使用 python3，如果你的系统提供的是 python，请替换。

OpenCode：

vet "goal" --history-loader "python3 ~/.agents/skills/vet/scripts/export_opencode_session.py --session-id <ses_ID>"

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

相关 Skills

FlyClaw：零登录航班聚合查询工具，Python实现多源航班信息与价格搜索

4,000,000 周安装

find-skills 技能搜索工具 - Vercel Labs 开源智能体技能包管理器

812,900 周安装

Vercel React 最佳实践指南 | 58条Next.js性能优化规则与代码重构

269,400 周安装

Vercel Web界面规范检查工具 - 自动检测代码是否符合Web设计指南

218,000 周安装

vet "goal" --history-loader "python3 ~/.codex/skills/vet/scripts/export_codex_session.py --session-file <path-to-session.jsonl>"

vet "goal" --history-loader "python3 ~/.claude/skills/vet/scripts/export_claude_code_session.py --session-file <path-to-session.jsonl>"

无对话历史记录

你只应搜索来自你当前使用的编码工具的会话。如果用户要求你使用不同的工具，他们很可能指的是 vet 的代理模式，而不是会话。

OpenCode： --session-id 参数需要一个 ses_... 会话 ID。要查找当前会话 ID：

运行：opencode session list --format json 以列出包含 ID 和标题的最近会话。
通过匹配标题或时间戳从列表中识别当前会话。
- 重要：验证找到的会话与当前对话匹配。如果标题不明确，请比较时间戳或检查多个候选会话。
将会话 ID 作为 --session-id 参数传递。

Codex： 会话文件存储在 ~/.codex/sessions/YYYY/MM/DD/ 中。要查找正确的会话文件：

在当前对话中找到最独特的句子/问题/字符串。
运行：grep -rl "UNIQUE_MESSAGE" ~/.codex/sessions/ 以查找匹配的会话文件。
- 重要：验证找到的对话与当前对话匹配，并且它不是另一个包含相同搜索字符串的对话。
将匹配到的文件路径作为 --session-file 参数传递。

Claude Code： 会话文件存储在 ~/.claude/projects/<encoded-path>/ 中。编码路径将 / 替换为 -（例如，/home/user/myproject 变为 -home-user-myproject）。要查找正确的会话文件：

在当前对话中找到最独特的句子/问题/字符串。
运行：grep -rl "UNIQUE_MESSAGE" ~/.claude/projects/ 以查找匹配的会话文件。
- 重要：验证找到的对话与当前对话匹配，并且它不是另一个包含相同搜索字符串的对话。
将匹配到的文件路径作为 --session-file 参数传递。

注意：标准用法部分的示例假设用户在用户级别安装了 vet 技能，而不是在项目级别。在尝试运行 vet 之前，请检查它是否安装在项目级别，项目级别的安装应优先于用户级别。如果安装在项目级别，请确保 history-loader 选项指向正确的位置。

Vet 会分析自基础提交以来的完整 git 差异。这可能包括同一仓库中其他代理或会话所做的更改。如果 vet 报告的问题与你在此次会话中未做的更改相关，请忽略它们，假设它们属于其他代理或用户。

--base-commit REF：用于差异比较的 Git 引用（默认：HEAD）
--model MODEL：要使用的 LLM（默认：claude-opus-4-6）
--list-models：列出 vet 支持的所有模型
- 运行 vet --help 并查看 vet 仓库的 readme 以获取有关定义自定义 OpenAI 兼容模型的详细信息。
--update-models：从远程注册表获取最新的社区模型定义并缓存在本地。有关何时运行此命令，请参见下面的"更新模型注册表"。
--confidence-threshold N：最小置信度 0.0-1.0（默认：0.8）
--output-format FORMAT：输出格式为 text、json 或 github
--quiet：抑制状态消息和'未发现问题。'
--agentic：此模式通过本地安装的 Claude Code 或 Codex CLI 路由分析，而不是直接调用 API。如果 vet 因缺少 API 密钥而失败，请尝试此模式。这速度较慢，因此不是默认设置，但它通常能更精确地识别问题。--model 参数会转发给工具，但 vet 不进行验证，因为 vet 不知道每个工具支持哪些模型。
--agent-harness：此选项有两个选择：codex 和 claude。Claude Code 是默认值。
--help：显示完整的选项列表

随着代理工具和 LLM API 的变化，vet CLI、技能文件和导出脚本可能会过时。

如果发生这种情况，请尝试更新它们。运行 which vet 以确定 vet 是如何安装的，并相应地进行更新。对于技能文件，请检查磁盘上存在哪些技能目录，并使用 https://github.com/imbue-ai/vet/tree/main/skills/vet 上的最新版本更新它们。

更新模型注册表

运行 vet --update-models 以从远程注册表获取最新的社区模型定义，而无需升级 vet 本身。这会在本地缓存模型定义，使它们出现在 --list-models 中，并可与 --model 一起使用。

在以下情况下应运行 vet --update-models：

Vet 报告未知或无法识别的模型错误时。
vet --list-models 未显示你或用户期望可用的模型时。
用户明确要求你更新模型注册表时。

更多信息可在 vet 仓库中找到：

🇺🇸English

Vet

Run vet immediately after ANY logical unit of code changes. Do not batch changes, do not wait to be asked to run vet, make sure you are proactive.

Vet reviews git diffs and conversation history to find issues in code changes and conversation history. It is most effective when run frequently with conversation history, which helps it catch misunderstandings between what was requested and what was implemented. Despite this, vet is not a replacement for running tests.

Installation

Install vet using pip, pipx, or uv:

# Using pip
pip install verify-everything

# Using pipx
pipx install verify-everything

# Using uv
uv tool install verify-everything

# Verify installation:
vet --help

Running Vet

Standard Usage

Before running vet, determine the correct Python binary:

$(command -v python3 || command -v python)

Use whichever resolves (prefer python3). The examples below use python3, substitute python if that is what your system provides.

OpenCode:

vet "goal" --history-loader "python3 ~/.agents/skills/vet/scripts/export_opencode_session.py --session-id <ses_ID>"

Codex:

vet "goal" --history-loader "python3 ~/.codex/skills/vet/scripts/export_codex_session.py --session-file <path-to-session.jsonl>"

Claude Code:

vet "goal" --history-loader "python3 ~/.claude/skills/vet/scripts/export_claude_code_session.py --session-file <path-to-session.jsonl>"

Without Conversation History

vet "goal"

Finding Your Session

You should only search for sessions from your coding harness. If a user requests you use a different harness, they are likely referring to vet's agentic mode, not the session.

OpenCode: The --session-id argument requires a ses_... session ID. To find the current session ID:

Run: opencode session list --format json to list recent sessions with their IDs and titles.
Identify the current session from the list by matching the title or timestamp.
- IMPORTANT: Verify the session you found matches the current conversation. If the title is ambiguous, compare timestamps or check multiple candidates.
Pass the session ID as --session-id.

Codex: Session files are stored in ~/.codex/sessions/YYYY/MM/DD/. To find the correct session file:

Find the most unique sentence / question / string in the current conversation.
Run: grep -rl "UNIQUE_MESSAGE" ~/.codex/sessions/ to find the matching session file.
- IMPORTANT: Verify the conversation you found matches the current conversation and that it is not another conversation with the same search string.
Pass the matched file path as --session-file.

Claude Code: Session files are stored in ~/.claude/projects/<encoded-path>/. The encoded path replaces / with - (e.g. /home/user/myproject becomes -home-user-myproject). To find the correct session file:

Find the most unique sentence / question / string in the current conversation.
Run: grep -rl "UNIQUE_MESSAGE" ~/.claude/projects/ to find the matching session file.
- IMPORTANT: Verify the conversation you found matches the current conversation and that it is not another conversation with the same search string.
Pass the matched file path as --session-file.

NOTE: The examples in the standard usage section assume the user installed the vet skill at the user level, not the project level. Prior to trying to run vet, check if it was installed at the project level which should take precedence over the user level. If it is installed at the project level, ensure the history-loader option points to the correct location.

Interpreting Results

Vet analyzes the full git diff from the base commit. This may include changes from other agents or sessions working in the same repository. If vet reports issues that relate to changes you did not make in this session, disregard them, assuming they belong to another agent or the user.

Common Options

--base-commit REF: Git ref for diff base (default: HEAD)
--model MODEL: LLM to use (default: claude-opus-4-6)
--list-models: list all models that are supported by vet
- Run vet --help and look at the vet repo's readme for details about defining custom OpenAI-compatible models.
--update-models: fetch the latest community model definitions from the remote registry and cache them locally. See "Updating the Model Registry" below for when to run this.
--confidence-threshold N: Minimum confidence 0.0-1.0 (default: 0.8)
--output-format FORMAT: Output as text, json, or

Updating

The vet CLI, skill files, and export scripts can become outdated as agent harnesses and LLM APIs change.

If this happens, try updating them. Run which vet to determine how vet was installed and update accordingly. For the skill files, check which skill directories exist on disk and update them with the latest versions from https://github.com/imbue-ai/vet/tree/main/skills/vet.

Updating the Model Registry

Run vet --update-models to fetch the latest community model definitions from the remote registry without upgrading vet itself. This caches model definitions locally so they appear in --list-models and can be used with --model.

You should run vet --update-models when:

Vet reports an unknown or unrecognized model error.
vet --list-models does not show a model you or the user expects to be available.
The user explicitly asks you to update the model registry.

Additional Information

Additional information can be found in the vet repo:

https://github.com/imbue-ai/vet

Weekly Installs

Repository

atilladeniz/kubeli

GitHub Stars

308

First Seen

1 day ago

Security Audits

Gen Agent Trust HubPass SocketFail SnykWarn

Installed on

zencoder1

amp1

cline1

openclaw1

opencode1

cursor1

agent-browser 浏览器自动化工具 - Vercel Labs 命令行网页操作与测试

147,400 周安装

--quiet: Suppress status messages and 'No issues found.'

--agentic: Mode that routes analysis through the locally installed Claude Code or Codex CLI instead of calling the API directly. Try this if vet fails due to missing API keys. This is slower so it is not the default, but it often results in higher precision issue identification. --model is forwarded to the harness but not validated by vet, as vet doesn't know which models each harness supports.

--agent-harness: The two options for this are codex and claude. Claude Code is the default.

--help: Show comprehensive list of options