Agent skill

Permission Manager

by aAAaqwq in aAAaqwq/AGI-Super-Team

管理Claude Code的全局工具权限配置,自动将MCP命令或其他工具添加到allowedTools中,避免每次使用时都需要手动批准。工作流程:确认用户需要添加的命令 - 确认添加级别(默认全局~/.claude.json) - 执行添加 - 验证并提醒重启。

MITAuto-check passedTesting & QA

Install Permission Manager

skills CLI
$ npx skills add aAAaqwq/AGI-Super-Team --skill permission-manager -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install aAAaqwq/AGI-Super-Team permission-manager --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/aAAaqwq/AGI-Super-Team.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/permission-manager .claude/skills/permission-manager && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
permission-manager
GitHub stars
105
Used in
1 other repo
Token cost
~1.3k tokens
SKILL.md length
125 words
Files
1
Skills in repo
167
Repo updated
First seen
Licence
MIT

At a glance

管理Claude Code的全局工具权限配置,自动将MCP命令或其他工具添加到allowedTools中,避免每次使用时都需要手动批准。工作流程:确认用户需要添加的命令 - 确认添加级别(默认全局~/.claude.json) - 执行添加 - 验证并提醒重启。

  • Works in 5 steps: 确认用户需求 → 确认配置级别 → 执行权限添加 → …
  • Tasks that involve Browser testing
  • SKILL.md covers 工作流程, 常见预设工具集, 注意事项 and 可用工具
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Permission Manager is an agent skill from aAAaqwq/AGI-Super-Team. 管理Claude Code的全局工具权限配置,自动将MCP命令或其他工具添加到allowedTools中,避免每次使用时都需要手动批准。工作流程:确认用户需要添加的命令 - 确认添加级别(默认全局~/.claude.json) - 执行添加 - 验证并提醒重启。

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Testing & QA, covering Browser testing. It works with Model Context Protocol, Figma, Playwright and GitHub. The repository describes itself as: An installable, cross-framework AI organization: C-suite agents, expert subagents, curated skills, independent review, and one-command setup across 18 AI client/runtime adapters. The licence is MIT.

When your agent uses it

  • Tasks that involve Browser testing

Example prompts

  • “/permission-manager”

Requirements

  • Node.js

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. 确认用户需求
  2. 确认配置级别
  3. 执行权限添加
  4. 验证与确认
  5. 可选:同时启用MCP服务器

What it can do on your machine

Read from SKILL.md and the folder at commit 331ecd3. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are javascript).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Permission Manager loads about 1.3k tokens when it runs. Until then it costs about 38 tokens; SKILL.md has 125 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~38
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from aAAaqwq/AGI-Super-Team at commit 331ecd3, republished under its MIT licence (© aAAaqwq). 125 words, ~1,327 tokens.

Download SKILL.mdSave it as .claude/skills/permission-manager/SKILL.md (or your agent's skills folder).
name
permission-manager
description
管理Claude Code的全局工具权限配置,自动将MCP命令或其他工具添加到allowedTools中,避免每次使用时都需要手动批准。工作流程:确认用户需要添加的命令 -> 确认添加级别(默认全局~/.claude.json) -> 执行添加 -> 验证并提醒重启。
author
Daniel Li

Claude Code 权限管理助手

  • Author: Daniel Li
  • Copyright © Daniel Li. All rights reserved.

你是Claude Code的权限管理助手,帮助用户配置全局工具自动执行权限。

工作流程

1. 确认用户需求

询问用户需要添加哪些工具的自动执行权限:

常见工具分类:

分类工具示例
Playwright/浏览器自动化mcp__chrome-devtools__*, mcp__plugin_playwright_playwright__*
Figma MCPmcp__figma__*
GitHubmcp__github__*
飞书mcp__feishu__*
Notionmcp__notionApi__*
SkillsSkill

询问方式:

  • "你想添加哪些工具的自动执行权限?"
  • "可以选择预设分类(Playwright/Figma/GitHub等)或指定具体工具名"
2. 确认配置级别

确认添加位置(默认为用户级别全局配置):

级别配置文件路径说明
全局(推荐)~/.claude.json所有项目生效
项目级{项目}/.claude.json仅当前项目生效

配置路径规则:

  • Windows: %USERPROFILE%\.claude.json → C:/Users/{用户名}/.claude.json
  • macOS/Linux: ~/.claude.json → /home/{用户名}/.claude.json
3. 执行权限添加

使用 Node.js 脚本方式修改配置(比 Edit 工具更可靠):

执行步骤:

  1. 创建临时脚本文件 update_permissions.js
  2. 读取现有配置
  3. 添加/合并 allowedTools 数组
  4. 保存并覆盖原配置
  5. 验证修改结果

脚本模板:

javascript
const fs = require('fs');
const configPath = 'C:/Users/Administrator/.claude.json'; // 根据系统调整
const data = JSON.parse(fs.readFileSync(configPath, 'utf8'));

// 新增的工具列表
const newTools = [
  '工具名1',
  '工具名2',
  // ...
];

// 合并现有工具(去重)
const existingTools = data.allowedTools || [];
data.allowedTools = [...new Set([...existingTools, ...newTools])];

// 保存
fs.writeFileSync(configPath, JSON.stringify(data, null, 2));
console.log('✅ 已添加 ' + newTools.length + ' 个工具权限');
4. 验证与确认

修改完成后执行验证:

javascript
const data = JSON.parse(fs.readFileSync(configPath, 'utf8'));
console.log('当前 allowedTools 总数:', data.allowedTools.length);

输出确认信息:

✅ 权限配置完成!

添加级别: 全局 (~/.claude.json)
新增工具: X 个
工具总数: Y 个

已添加的工具列表:
- 工具1
- 工具2
- ...

⚠️ 请重启 Claude Code 以使配置生效!
5. 可选:同时启用MCP服务器

如果添加的工具属于某个被禁用的MCP服务器,从 disabledMcpServers 中移除:

javascript
Object.keys(data.projects).forEach(projectKey => {
  const project = data.projects[projectKey];
  if (project.disabledMcpServers) {
    project.disabledMcpServers = project.disabledMcpServers.filter(
      s => s !== '要启用的服务器名'
    );
  }
});

常见预设工具集

Playwright 完整套(29个)
javascript
const playwrightTools = [
  'Skill',
  'mcp__chrome-devtools__click',
  'mcp__chrome-devtools__close_page',
  'mcp__chrome-devtools__drag',
  'mcp__chrome-devtools__emulate',
  'mcp__chrome-devtools__evaluate_script',
  'mcp__chrome-devtools__fill',
  'mcp__chrome-devtools__fill_form',
  'mcp__chrome-devtools__get_console_message',
  'mcp__chrome-devtools__get_network_request',
  'mcp__chrome-devtools__handle_dialog',
  'mcp__chrome-devtools__hover',
  'mcp__chrome-devtools__list_console_messages',
  'mcp__chrome-devtools__list_network_requests',
  'mcp__chrome-devtools__list_pages',
  'mcp__chrome-devtools__navigate_page',
  'mcp__chrome-devtools__new_page',
  'mcp__chrome-devtools__performance_analyze_insight',
  'mcp__chrome-devtools__performance_start_trace',
  'mcp__chrome-devtools__performance_stop_trace',
  'mcp__chrome-devtools__press_key',
  'mcp__chrome-devtools__resize_page',
  'mcp__chrome-devtools__select_page',
  'mcp__chrome-devtools__take_screenshot',
  'mcp__chrome-devtools__take_snapshot',
  'mcp__chrome-devtools__upload_file',
  'mcp__chrome-devtools__wait_for',
  'mcp__plugin_playwright_playwright__browser_navigate',
  'mcp__plugin_playwright_playwright__browser_snapshot'
];
Figma MCP 完整套(11个)
javascript
const figmaTools = [
  'mcp__figma__get_design_context',
  'mcp__figma__get_variable_defs',
  'mcp__figma__get_code_connect_map',
  'mcp__figma__add_code_connect_map',
  'mcp__figma__get_screenshot',
  'mcp__figma__create_design_system_rules',
  'mcp__figma__get_metadata',
  'mcp__figma__get_figjam',
  'mcp__figma__whoami',
  'mcp__figma__get_strategy_for_mapping',
  'mcp__figma__send_get_strategy_response'
];
GitHub 完整套
javascript
const githubTools = [
  'mcp__github__add_issue_comment',
  'mcp__github__create_branch',
  'mcp__github__create_issue',
  'mcp__github__create_or_update_file',
  'mcp__github__create_pull_request',
  'mcp__github__create_pull_request_review',
  'mcp__github__create_repository',
  'mcp__github__fork_repository',
  'mcp__github__get_file_contents',
  'mcp__github__get_issue',
  'mcp__github__get_pull_request',
  'mcp__github__get_pull_request_comments',
  'mcp__github__get_pull_request_files',
  'mcp__github__get_pull_request_reviews',
  'mcp__github__get_pull_request_status',
  'mcp__github__list_commits',
  'mcp__github__list_issues',
  'mcp__github__list_pull_requests',
  'mcp__github__merge_pull_request',
  'mcp__github__push_files',
  'mcp__github__search_code',
  'mcp__github__search_issues',
  'mcp__github__search_repositories',
  'mcp__github__search_users',
  'mcp__github__update_issue'
];

注意事项

  1. 配置文件备份:修改前建议备份现有配置
  2. JSON格式正确性:使用 Node.js 处理确保格式正确
  3. 路径适配:Windows/macOS/Linux 路径格式不同
  4. 权限问题:确保有写入 ~/.claude.json 的权限
  5. 重启生效:修改后必须重启 Claude Code

可用工具

  • 读取配置:Read 工具
  • 执行脚本:Bash 工具运行 node 命令
  • 验证结果:Bash 工具运行 node 验证命令

© aAAaqwq, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/permission-manager of aAAaqwq/AGI-Super-Team.

Open the folder on GitHubat commit 331ecd3

Used in 1 other repository

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in aAAaqwq/AGI-Super-Team, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Permission Manager next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Permission Manager compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Permission Manager this skillaAAaqwq/AGI-Super-Team1051 repos~1.3kAutomated safety check: PassMIT
Record E2E Giflablup/backend.ai-webui133—~907Automated safety check: NotesLGPL-3.0
Igniteui Wc Figma To AppIgniteUI/igniteui-webcomponents170—~7.2kAutomated safety check: PassMIT
Testing Course Samplesmicrosoft/ai-agents-for-beginners77k—~1.1kAutomated safety check: NotesMIT
Testing Course Samplesmicrosoft/ai-agents-for-beginners77k—~1kAutomated safety check: NotesMIT
Testing Course Samplesmicrosoft/ai-agents-for-beginners77k—~1.3kAutomated safety check: NotesMIT

Similar skills

  • Record E2E Gif

    lablup/backend.ai-webui

    Record Playwright e2e tests as one GIF per test case (video → ffmpeg palette GIF) and return a markdown table for a PR description.

    133 GitHub stars~907 tokensUpdated today
    Testing & QAAuto-check: notes
  • Igniteui Wc Figma To App

    IgniteUI/igniteui-webcomponents

    Builds Ignite UI Web Components views from Figma designs, supporting Indigo.Design kits, third-party kits (Material 3, Fluent 2, shadcn/ui, Untitled UI, in-house), and plain frames.

    170 GitHub stars~7.2k tokensUpdated today
    Frontend & DesignAuto-check passed
  • Testing Course Samples

    microsoft/ai-agents-for-beginners

    Official

    A skill your agent uses when asked to validate, test, smoke-test, or run the course's notebook and code samples against a live Microsoft Foundry / Azure OpenAI configuration.

    77k GitHub stars~1.1k tokensUpdated 20 days ago
    Testing & QAAuto-check: notes
  • Testing Course Samples

    microsoft/ai-agents-for-beginners

    Official

    השתמש כאשר מתבקשים לבדוק תוקף, לבצע בדיקת פונקציונליות בסיסית, או להריץ את המחברת ודוגמאות הקוד של הקורס נגד תצורת Microsoft Foundry / Azure OpenAI חיה.

    77k GitHub stars~1k tokensUpdated 20 days ago
    Testing & QAAuto-check: notes
  • Testing Course Samples

    microsoft/ai-agents-for-beginners

    Official

    Koristite kada se zatraži validacija, testiranje, smoke-test ili pokretanje bilježnica i primjera koda tečaja protiv aktivne Microsoft Foundry / Azure OpenAI konfiguracije.

    77k GitHub stars~1.3k tokensUpdated 20 days ago
    Testing & QAAuto-check: notes
  • Testing Course Samples

    microsoft/ai-agents-for-beginners

    Official

    Gunakan apabila diminta untuk mengesahkan, menguji, melakukan ujian asap, atau menjalankan buku nota dan contoh kod kursus terhadap konfigurasi Microsoft Foundry / Azure OpenAI secara langsung.

    77k GitHub stars~1.3k tokensUpdated 20 days ago
    Testing & QAAuto-check: notes

More from aAAaqwq/AGI-Super-Team

All 167 skills in this repo
  • Content Creator

    aAAaqwq/AGI-Super-Team

    Create SEO-optimized marketing content with consistent brand voice.

    105 GitHub starsUsed in 3 repos~1.9k tokens
    Auto-check passed
  • Financial Calculator

    aAAaqwq/AGI-Super-Team

    Advanced financial calculator with future value tables, present value, discount calculations, markup pricing, and compound interest.

    105 GitHub starsUsed in 1 repo~1.5k tokens
    Auto-check passed
  • Bankr Signals

    aAAaqwq/AGI-Super-Team

    Transaction-verified trading signals on Base blockchain. An agent skill from aAAaqwq/AGI-Super-Team.

    105 GitHub starsUsed in 2 repos~3.3k tokens
    Auto-check passed
  • Erc 8004

    aAAaqwq/AGI-Super-Team

    Register AI agents on Ethereum mainnet using ERC-8004 (Trustless Agents).

    105 GitHub starsUsed in 2 repos~1.2k tokens
    Auto-check passed
  • Frontend Design Ultimate

    aAAaqwq/AGI-Super-Team

    Create distinctive, production-grade static sites with React, Tailwind CSS, and shadcn/ui — no mockups needed.

    105 GitHub starsUsed in 2 repos~2.7k tokens
    Auto-check passed
  • Zsxq Smart Publish

    aAAaqwq/AGI-Super-Team

    Publish and manage content on 知识星球 (zsxq.com). An agent skill from aAAaqwq/AGI-Super-Team.

    105 GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed

Questions about Permission Manager

What does Permission Manager do?

管理Claude Code的全局工具权限配置,自动将MCP命令或其他工具添加到allowedTools中,避免每次使用时都需要手动批准。工作流程:确认用户需要添加的命令 - 确认添加级别(默认全局~/.claude.json) - 执行添加 - 验证并提醒重启。. Permission Manager is an agent skill from aAAaqwq/AGI-Super-Team.

When should I use Permission Manager?

Permission Manager fits situations like: tasks that involve Browser testing.

How do I install Permission Manager in Claude Code?

Run `npx skills add aAAaqwq/AGI-Super-Team --skill permission-manager -a claude-code`. Or copy the skill folder (skills/permission-manager in aAAaqwq/AGI-Super-Team) into .claude/skills/permission-manager in your project. Claude Code loads it when a task matches its description.

How do I install Permission Manager in Codex?

Run `npx skills add aAAaqwq/AGI-Super-Team --skill permission-manager -a codex`. Or copy the skill folder (skills/permission-manager in aAAaqwq/AGI-Super-Team) into .agents/skills/permission-manager in your project. Codex loads it when a task matches its description.

Can I use Permission Manager in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add aAAaqwq/AGI-Super-Team --skill permission-manager -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/permission-manager, .gemini/skills/permission-manager, .github/skills/permission-manager and .opencode/skills/permission-manager in your project.

What does Permission Manager need to run?

SKILL.md names no scripts, command-line tools or credentials: Permission Manager is instructions for the agent only. Our summary lists: Node.js.

Does Permission Manager access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Permission Manager safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Permission Manager use?

Permission Manager is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Permission Manager use?

About 1.3k tokens (SKILL.md is roughly 5.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Permission Manager?

Skills that share tags, products or a category with Permission Manager: Record E2E Gif (lablup/backend.ai-webui, 133 stars), Igniteui Wc Figma To App (IgniteUI/igniteui-webcomponents, 170 stars), Testing Course Samples (microsoft/ai-agents-for-beginners, 77k stars) and Testing Course Samples (microsoft/ai-agents-for-beginners, 77k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Permission Manager?

aAAaqwq (a GitHub user) maintains it in aAAaqwq/AGI-Super-Team, which has 105 GitHub stars. The repository holds 167 skills in this directory. The repository was last updated on October 8, 2026.

Source: aAAaqwq/AGI-Super-Team on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.