ralphmode

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Ralphmode

Ralphmode is a cross-platform permission profile for long-running

ralph

jeo

workflows. It reduces approval friction, but it is not "allow everything everywhere." The core rule is simple: widen automation only inside a bounded project or disposable sandbox, and keep secrets plus destructive commands explicitly blocked.

Ralphmode是适用于长时间运行的

ralph

或

jeo

工作流的跨平台权限配置文件。它降低了审批阻力，但并非“允许所有位置的所有操作”。核心规则很简单：仅在有边界的项目或一次性沙箱内扩大自动化范围，同时明确阻断机密信息和破坏性命令。

When to use this skill

何时使用该技能

You want
```
ralph
```
to iterate without repeated approval popups.
You are setting up the same repo for Claude Code, Codex CLI, and Gemini CLI.
You need a shared safety model: repo-only writes, no secrets reads, no destructive shell by default.
You want a stronger separation between day-to-day automation and true YOLO mode.

你希望
```
ralph
```
可以迭代运行，无需重复弹出审批窗口
你正在为Claude Code、Codex CLI和Gemini CLI配置同一个代码仓库
你需要一套共享的安全模型：默认仅支持仓库内写入、禁止读取机密、禁止运行破坏性shell命令
你希望在日常自动化和完全无限制模式（YOLO mode）之间实现更强的隔离

Instructions

使用说明

Step 1: Define the automation boundary first

步骤1：先定义自动化边界

Before changing any permission mode:

Pick one project root and keep automation scoped there.
List files and commands that must stay blocked:
```
.env*
```
,
```
secrets/**
```
, production credentials,
```
rm -rf
```
,
```
sudo
```
, unchecked
```
curl | sh
```
.
Decide whether this is a normal repo or a disposable sandbox.

If the answer is "disposable sandbox," you may use the platform's highest-autonomy mode. If not, use the repo-scoped preset instead.

在修改任何权限模式之前：

选定一个项目根目录，将自动化的作用范围限定在该目录内
列出必须阻断的文件和命令：
```
.env*
```
、
```
secrets/**
```
、生产环境凭证、
```
rm -rf
```
、
```
sudo
```
、未校验的
```
curl | sh
```
确定当前是普通代码仓库还是一次性沙箱

如果是“一次性沙箱”，你可以使用平台的最高自治模式；否则请使用仓库范围的预设配置。

Step 2: Choose one preset per platform

步骤2：为每个平台选择一个预设

Use only the section that matches the current tool:

Claude Code: everyday preset first,
```
bypassPermissions
```
only for isolated sandboxes.
Codex CLI: use the current official approval and sandbox model first; treat older
```
permissions.allow
```
and
```
permissions.deny
```
snippets as compatibility-only.
Gemini CLI: trust only the project root; there is no true global YOLO mode.

Detailed templates live in references/permission-profiles.md.

仅使用与当前工具匹配的部分：

Claude Code：优先使用日常预设，仅当使用隔离沙箱时才开启
```
bypassPermissions
```
Codex CLI：优先使用当前官方的审批和沙箱模型，将旧的
```
permissions.allow
```
和
```
permissions.deny
```
代码片段仅作为兼容方案使用
Gemini CLI：仅信任项目根目录，不存在真正的全局无限制模式

详细模板位于references/permission-profiles.md。

Step 3: Apply the profile locally, not globally, unless the workspace is disposable

步骤3：本地应用配置文件而非全局应用，除非工作区是一次性的

Prefer project-local configuration over user-global defaults.

Claude Code: start with project
```
.claude/settings.json
```
.
Codex CLI: start with project config and repo instructions or rules files.
Gemini CLI: trust the current folder, not
```
~/
```
or broad parent directories.

If you must use a user-global default, pair it with a stricter denylist and a sandbox boundary.

优先使用项目本地配置而非用户全局默认配置：

Claude Code：从项目的
```
.claude/settings.json
```
开始配置
Codex CLI：从项目配置、仓库说明或规则文件开始配置
Gemini CLI：仅信任当前文件夹，不要信任
```
~/
```
或范围宽泛的父目录

如果你必须使用用户全局默认配置，请搭配更严格的拒绝列表和沙箱边界使用。

Step 4: Run Ralph with an explicit verification loop

步骤4：运行Ralph时搭配显式的验证循环

After permissions are configured:

Confirm the task and acceptance criteria.
Run
```
ralph
```
or the
```
jeo
```
plan-execute-verify loop.
Verify outputs before claiming completion.
If the automation profile was temporary, revert it after the run.

Recommended execution contract:

text

boundary check -> permission profile -> ralph run -> verify -> cleanup or revert

权限配置完成后：

确认任务和验收标准
运行
```
ralph
```
或
```
jeo
```
的计划-执行-验证循环
验证输出后再确认任务完成
如果自动化配置是临时的，运行完成后将其恢复

推荐的执行约定：

text

boundary check -> permission profile -> ralph run -> verify -> cleanup or revert

Step 5: Keep "skip" and "safe" separate

步骤5：将“跳过审批”和“安全”分开

Treat these as different modes:

Repo automation: minimal prompts inside a bounded workspace.
Sandbox YOLO: promptless execution in a disposable environment only.

Do not collapse them into one shared team default.

将以下模式视为不同的模式：

仓库自动化：在有边界的工作区内仅弹出最少提示
沙箱无限制模式：仅在一次性环境中实现无提示执行

不要将它们合并为一个共享的团队默认配置。

Examples

示例

Example 1: Claude Code sandbox run

示例1：Claude Code沙箱运行

Use the Claude sandbox preset from references/permission-profiles.md, then run Ralph only inside that isolated repo:

bash

/ralph "fix all failing tests" --max-iterations=10

使用references/permission-profiles.md中的Claude沙箱预设，然后仅在该隔离仓库内运行Ralph：

bash

/ralph "fix all failing tests" --max-iterations=10

Example 2: Codex CLI repo-scoped Ralph run

示例2：Codex CLI仓库范围的Ralph运行

Apply the Codex repo preset from references/permission-profiles.md, then run the task. The current official model uses config file settings, not CLI flag overrides:

toml

approval_policy = "never"
sandbox_mode = "workspace-write"

Place this in

~/.codex/config.toml

(or a project-local override) and restart Codex before running Ralph.

应用references/permission-profiles.md中的Codex仓库预设，然后运行任务。当前官方模型使用配置文件设置，而非CLI标志覆盖：

toml

approval_policy = "never"
sandbox_mode = "workspace-write"

将该配置放在

~/.codex/config.toml

（或项目本地覆盖配置）中，重启Codex后再运行Ralph。

Example 3: Gemini CLI trust-only setup

示例3：Gemini CLI仅信任设置

Trust the current project folder, keep explicit file selection, then run the Ralph workflow for that repo only.

信任当前项目文件夹，保留显式文件选择，然后仅为该仓库运行Ralph工作流。

Best practices

最佳实践

Default to the least-permissive preset that still lets Ralph finish end-to-end.
Keep secret denylists and destructive command denylists even when approvals are reduced.
Use full bypass only in disposable environments with a clear project boundary.
Record which preset was applied so teammates can reproduce or revert it.
Re-check platform docs when upgrading CLI versions because permission models change faster than skill content.

默认选择可支持Ralph端到端完成任务的最低权限预设
即使减少了审批，也要保留机密拒绝列表和破坏性命令拒绝列表
仅在具有明确项目边界的一次性环境中使用完全绕过权限的配置
记录所应用的预设，以便团队成员可以复现或恢复配置
升级CLI版本时重新查阅平台文档，因为权限模型的更新速度快于本技能内容的更新速度

References

参考资料

What are Agent Skills?
Agent Skills Specification
Permission Profiles
Claude Code permissions
Codex configuration and rules
ChatGPT Codex sandbox and approval modes
Gemini CLI trusted folders

什么是Agent Skills?
Agent Skills Specification
权限配置文件
Claude Code permissions
Codex configuration and rules
ChatGPT Codex sandbox and approval modes
Gemini CLI trusted folders