提示词中文站 prompts.chat 中文镜像
首页 全部提示词 Agent Skill

更新 Agent 权限

Update Agent Permissions

文本 @grantcarthew 1,571 字符 在 prompts.chat 查看 译文有问题？

中文译文

任务：更新 Agent 权限

请分析我们的整个对话，并识别出所有使用过的具体命令。

为 Claude Code 和 Gemini CLI 两者更新权限。

参考文件

  • Claude：~/.claude/settings.json
  • Gemini 策略：~/.gemini/policies/tool-permissions.toml
  • Gemini 设置：~/.gemini/settings.json
  • Gemini 受信任文件夹：~/.gemini/trustedFolders.json

指令

  1. 审计：将识别出的命令与两个配置文件中当前允许的命令进行对比。
  2. 筛选：只包含提供资源只读访问权限的命令。
  3. 限制：明确排除任何能够修改、删除或销毁数据的命令。
  4. 更新：只将缺失的只读命令添加到两个配置文件中。
  5. 约束：不要使用通配符。每条命令必须单独列出，以实现细粒度安全控制。

将命令列表按两个类别展示给我：只读（Read-Only）和写入（Write）。

我们这里主要关注的是属于以下类别的只读命令：Read、Get、Describe、View 或类似类别。

一旦我批准了该列表，就更新两个配置文件。

Claude 格式

文件：~/.claude/settings.json

Claude 使用一个 JSON 权限对象，包含 allow、deny 和 ask 数组。

允许格式：Bash(command subcommand:*)

将新命令按字母顺序插入 allow 数组内。

Gemini 格式

文件：~/.gemini/policies/tool-permissions.toml

Gemini 使用一个 TOML 策略引擎，规则位于不同的优先级层级。

规则类型与优先级：

  • decision = "deny" 位于 priority = 200，用于破坏性操作
  • decision = "ask_user" 位于 priority = 150，用于需要确认的写入操作
  • decision = "allow" 位于 priority = 100，用于只读操作

对于 allow 规则，使用 commandPrefix（提供词边界匹配）。 对于 deny 和 ask 规则，使用 commandRegex（捕获标志变体）。

新的只读命令应按类别添加到相应的现有 [[rule]] 块中，如果没有合适的类别，则添加到一个新块中。

示例 allow 规则：

[[rule]]
toolName = "run_shell_command"
commandPrefix = ["command subcommand1", "command subcommand2"]
decision = "allow"
priority = 100

Gemini 目录

如果访问了工作区之外的任何新目录，请将它们添加到：

  • ~/.gemini/settings.json 中的 context.includeDirectories
  • ~/.gemini/trustedFolders.json，值为 "TRUST_FOLDER"

例外情况

不要建议添加以下命令：

  • git branch：使用 -D 标志将删除分支
  • git pull：以防触发合并操作
  • git checkout：切换分支可能会中断工作
  • ajira issue create：为防止过度创建新问题
  • find：-delete 和 -exec 标志具有破坏性（请改用 fd）

English original

Task: Update Agent Permissions

Please analyse our entire conversation and identify all specific commands used.

Update permissions for both Claude Code and Gemini CLI.

Reference Files

  • Claude: ~/.claude/settings.json
  • Gemini policy: ~/.gemini/policies/tool-permissions.toml
  • Gemini settings: ~/.gemini/settings.json
  • Gemini trusted folders: ~/.gemini/trustedFolders.json

Instructions

  1. Audit: Compare the identified commands against the current allowed commands in both config files.
  2. Filter: Only include commands that provide read-only access to resources.
  3. Restrict: Explicitly exclude any commands capable of modifying, deleting, or destroying data.
  4. Update: Add only the missing read-only commands to both config files.
  5. Constraint: Do not use wildcards. Each command must be listed individually for granular security.

Show me the list of commands under two categories: Read-Only, and Write

We are mostly interested in the read-only commands here that fall under the categories: Read, Get, Describe, View, or similar.

Once I have approved the list, update both config files.

Claude Format

File: ~/.claude/settings.json

Claude uses a JSON permissions object with allow, deny, and ask arrays.

Allow format: Bash(command subcommand:*)

Insert new commands in alphabetical order within the allow array.

Gemini Format

File: ~/.gemini/policies/tool-permissions.toml

Gemini uses a TOML policy engine with rules at different priority levels.

Rule types and priorities:

  • decision = "deny" at priority = 200 for destructive operations
  • decision = "ask_user" at priority = 150 for write operations needing confirmation
  • decision = "allow" at priority = 100 for read-only operations

For allow rules, use commandPrefix (provides word-boundary matching). For deny and ask rules, use commandRegex (catches flag variants).

New read-only commands should be added to the appropriate existing [[rule]] block by category, or a new block if no category fits.

Example allow rule:

[[rule]]
toolName = "run_shell_command"
commandPrefix = ["command subcommand1", "command subcommand2"]
decision = "allow"
priority = 100

Gemini Directories

If any new directories outside the workspace were accessed, add them to:

  • context.includeDirectories in ~/.gemini/settings.json
  • ~/.gemini/trustedFolders.json with value "TRUST_FOLDER"

Exceptions

Do not suggest adding the following commands:

  • git branch: The -D flag will delete branches
  • git pull: Incase a merge is actioned
  • git checkout: Changing branches can interrupt work
  • ajira issue create: To prevent excessive creation of new issues
  • find: The -delete and -exec flags are destructive (use fd instead)

同类提示词

更多「Agent Skill」→