How do I install the Qwen Code Permission skill?

Run npx skillmds@latest add cnife/qwen-code-permission in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Qwen Code Permission safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Qwen Code Permission?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Qwen Code Permission free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Qwen Code Permission?

cnife (@cnife) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Qwen Code Permission by cnife — Agent Skill

Name: Qwen Code Permission
Author: cnife

Qwen Code Permission

Automate adding permission rules to Qwen Code's settings.json. Use whenever the user wants to allow, deny, or require confirmation for a command in Qwen Code. Trigger on phrases like "把 X 加到允许列表"、"添加到允许"、"允许 Bash(X)"、"deny 某命令"、"permission rule"、"auto-approve this command"、"skip confirmation for"、"always allow" — even if the user doesn't explicitly mention Qwen Code's settings.json. Also use when working with Qwen Code permission configuration or troubleshooting auto-approval rules.

cnife 9ca57c2 2 files · 5.1 KB Updated Sep 17, 2026

File contents

Qwen Code Permission Manager

Manage Qwen Code's permissions.allow / permissions.ask / permissions.deny in settings.json.

Workflow

Identify the rule string from user request (e.g., "Bash(. ~/.x-cmd.root/X)")
Determine the action: allow (default) / ask / deny

Run the bundled script (find it at scripts/add_permission.py relative to this skill):

uv run --script <skill-path>/scripts/add_permission.py "Bash(. ~/.x-cmd.root/X)" --action allow

Confirm the change was written
Remind user: 配置更改需要重启 Qwen Code（/exit 后重新运行）才能生效

Rule Reference

Tool name aliases

Alias	Canonical tool
`Bash` / `Shell`	`run_shell_command`
`Read` / `ReadFile`	`read_file`
`Edit` / `EditFile`	`edit`
`Write` / `WriteFile`	`write_file`
`Grep` / `SearchFiles`	`grep_search`
`Glob` / `FindFiles`	`glob`
`ListFiles`	`list_directory`
`WebFetch`	`web_fetch`
`Agent`	`task`
`Skill`	`skill`

Meta-categories

Rule name	Tools covered
`Read`	`read_file` + `grep_search` + `glob` + `list_directory`
`Edit`	`edit` + `write_file`

Read(/path/**) matches all four read tools. To restrict only file reading, use ReadFile(/path/**) or read_file(/path/**).

Path pattern prefixes

Prefix	Meaning	Example
`//`	Absolute path from filesystem root	`//etc/passwd`
`~/`	Relative to home directory	`~/Documents/*.pdf`
`/`	Relative to project root	`/src/*/.ts`
`./`	Relative to current working directory	`./secrets/**`
(none)	Same as `./`	`secrets/**`

Rule examples

Rule	Meaning
`"Bash"`	All shell commands
`"Bash(git *)"`	Commands starting with `git` (word boundary)
`"Bash(npm run *)"`	Any `npm run` script
`"WebFetch(api.example.com)"`	That domain and all subdomains
`"mcp__puppeteer"`	All tools from the puppeteer MCP server

Configuration

Qwen Code reads ~/.qwen/settings.json (user) or .qwen/settings.json (project). The permissions section:

{
  "permissions": {
    "allow": ["Bash(git *)"],
    "ask": ["Bash(git push *)"],
    "deny": ["Bash(rm -rf *)"]
  }
}

Decision priority: deny > ask > allow > default. First matching rule wins. allow rules merge across all scopes (user + project + system).

---name: qwen-code-permissiondescription: Automate adding permission rules to Qwen Code's settings.json. Use whenever the user wants to allow, deny, or require confirmation for a command in Qwen Code. Trigger on phrases like "把 X 加到允许列表"、"添加到允许"、"允许 Bash(X)"、"deny 某命令"、"permission rule"、"auto-approve this command"、"skip confirmation for"、"always allow" — even if the user doesn't explicitly mention Qwen Code's settings.json. Also use when working with Qwen Code permission configuration or troubleshooting auto-approval rules.---# Qwen Code Permission ManagerManage Qwen Code's `permissions.allow` / `permissions.ask` / `permissions.deny` in `settings.json`.## Workflow1. Identify the rule string from user request (e.g., `"Bash(. ~/.x-cmd.root/X)"`)2. Determine the action: `allow` (default) / `ask` / `deny`3. Run the bundled script (find it at `scripts/add_permission.py` relative to this skill): ```bash uv run --script <skill-path>/scripts/add_permission.py "Bash(. ~/.x-cmd.root/X)" --action allow ```4. Confirm the change was written5. Remind user: **配置更改需要重启 Qwen Code（`/exit` 后重新运行）才能生效**## Rule Reference### Tool name aliases| Alias | Canonical tool ||-------|---------------|| `Bash` / `Shell` | `run_shell_command` || `Read` / `ReadFile` | `read_file` || `Edit` / `EditFile` | `edit` || `Write` / `WriteFile` | `write_file` || `Grep` / `SearchFiles` | `grep_search` || `Glob` / `FindFiles` | `glob` || `ListFiles` | `list_directory` || `WebFetch` | `web_fetch` || `Agent` | `task` || `Skill` | `skill` |### Meta-categories| Rule name | Tools covered ||-----------|--------------|| `Read` | `read_file` + `grep_search` + `glob` + `list_directory` || `Edit` | `edit` + `write_file` |> `Read(/path/**)` matches all four read tools. To restrict only file reading, use `ReadFile(/path/**)` or `read_file(/path/**)`.### Path pattern prefixes| Prefix | Meaning | Example ||--------|---------|---------|| `//` | Absolute path from filesystem root | `//etc/passwd` || `~/` | Relative to home directory | `~/Documents/*.pdf` || `/` | Relative to project root | `/src/**/*.ts` || `./` | Relative to current working directory | `./secrets/**` || (none) | Same as `./` | `secrets/**` |### Rule examples| Rule | Meaning ||------|---------|| `"Bash"` | All shell commands || `"Bash(git *)"` | Commands starting with `git` (word boundary) || `"Bash(npm run *)"` | Any `npm run` script || `"WebFetch(api.example.com)"` | That domain and all subdomains || `"mcp__puppeteer"` | All tools from the puppeteer MCP server |## ConfigurationQwen Code reads `~/.qwen/settings.json` (user) or `.qwen/settings.json` (project).The `permissions` section:```json{ "permissions": { "allow": ["Bash(git *)"], "ask": ["Bash(git push *)"], "deny": ["Bash(rm -rf *)"] }}```**Decision priority:** `deny` > `ask` > `allow` > default. First matching rule wins.`allow` rules merge across all scopes (user + project + system).

Frequently asked questions