跳到主要内容
知仓学习社ZHICANG

permission-manager

Manage opencode permissions: review always-allow lists, suggest safe read-only commands, configure permission patterns

不碰外部(只输出文字)无严重或高危命中sickn33/agentic-awesome-skills

它会碰到什么

扫了多少2 个文本文件,3 KB
它会碰到什么不碰外部(只输出文字)
命中总数0 处
命中统计严重 0 · 高 0 · 中 0 · 低 0

这一栏是扫描器报的事实,不是结论。命中多不等于有毒(安全工具、规则库、示例脚本本来就会包含危险写法),命中少也不等于干净。它和你手上的凭据、文件、网络有什么关系,需要你自己看。

技能内容

What I do

  • Review and summarize currently always-allowed commands
  • Suggest safe read-only commands for auto-approval
  • Add or remove commands from the allow list in opencode.json
  • Configure skill-level permissions (allow/deny/ask) with wildcard patterns
  • Audit permission configs for security and usability

When to Use

Use this when optimizing opencode's permission settings, reviewing allowed commands, or configuring skill access controls.

Workflow Steps

  1. Read current config: Load ~/.config/opencode/opencode.json or project-level opencode.json
  2. Summarize permissions: Identify currently allowed commands and skill permissions
  3. Suggest additions: Propose safe read-only commands for auto-allow (see recommended list below)
  4. Apply changes: Edit the config to add/remove permission entries
  5. Validate: Ensure JSON is valid after changes

Complements opencode's built-in allow/deny/ask permissions by auditing current config and recommending adjustments through conversation.

Key Rules

  • Never allow commands that modify files, commit, push, or change system state
  • Prefer exact command entries such as git status --short, git diff --stat, and ls -la
  • Avoid trailing wildcards such as git status* unless the expanded command family has been manually reviewed as read-only
  • Confirm with user before modifying permission config
  • Distinguish between bash command permissions and skill permissions
  • Keep config organized: group related commands together

Limitations

  • This skill is scoped to opencode permission configuration and should not modify other agent hosts' permission stores.
  • Treat all write-capable command permissions as high-risk; review them manually even when a pattern looks narrow.

How to trigger me

Use the Task tool with the permission-manager subagent type:

/permissions

Or in natural language, ask opencode to "manage opencode permissions" or "review allowed commands".

想直接用这个技能?

本站把开放许可(MIT / Apache 等)的技能按仓库打包整理到网盘,点一下转存到你自己的网盘,不用一个个从 GitHub 拉。许可未声明的技能只给原始仓库链接,不打包。

同名技能的其他版本

有 3 个不同仓库或目录里都有叫 permission-manager 的技能。它们内容并不相同,别混用: