Skip to content
Back to skills

Allow Agent Commands

ASecurity

Add or change allowed commands in AI agent permission configs (OpenCode, Claude Code)

  • 666 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added February 8, 2026
toolsbashgit

Works with

  • claude code

Security analysis

A100/100

Scanned February 12, 2026

npx -y skills add majiayu000/claude-skill-registry --skill allow-agent-commands --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Allow Agent Commands?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Allow Agent Commands
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/majiayu000-allow-agent-commands/badge)](https://www.skillsdirectory.com/skills/majiayu000-allow-agent-commands)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: allow-agent-commands
description: Add or change allowed commands in AI agent permission configs (OpenCode, Claude Code)
---

# Adding/Changing Allowed Commands

## When to use this skill

Use this skill when:

- A command needs to be added to the allow list for AI agents
- Permission settings need to be modified for existing commands
- Setting up a new AI tool that requires command permissions

## How it works

Commands must be explicitly allowed in the permission configs before agents
can run them. This skill covers adding entries to both OpenCode and Claude
Code configuration files.

**IMPORTANT**: The config files are stowed into `~` via GNU Stow symlinks.
Always edit them directly from within the ai-config repository, NOT from `~`.
The paths below are relative to the ai-config repository root.

## OpenCode Configuration

File: `.config/opencode/opencode.json` under `permission.bash`

Format:
```json
"uname *": "allow",
```

Pattern: `"command argpatterns": "action"` where `*` matches any args

**Important**: Insert new entries in alphabetical order by command name.
When adding a new command, find the correct position to maintain sorting.
**Do NOT reorder existing entries.**

## Claude Code Configuration

File: `.claude/settings.json` under `permissions.allow`

Format:
```json
"Bash(uname:*)",
```

**Important**: Insert new entries in alphabetical order. Commands are sorted
by the command name (the part after `Bash(` and before `:`).
**Do NOT reorder existing entries.**

## General Pattern for New AI Tools

When adding new AI tools:

1. Find their config file (usually in `~/.config/` or project root)
2. Look for `permissions`, `allowedCommands`, or similar sections
3. Add the command with glob patterns for arguments
4. **Insert new entries in alphabetical order by command name**
5. **Do NOT reorder existing entries.**

## After Adding Commands

After adding the new command entries to both config files:

1. Check if there are any other staged changes with `git status`
2. If there are NO other staged changes, stage ONLY the new hunks in the two
   config files using the `git-stager` subagent (be careful not to stage
   unrelated changes)
3. Invoke the `git-committer` subagent to commit the changes

## Examples

Adding `rg` (ripgrep) to both configs:

**OpenCode** (insert after `rev *`, before `rpm -q*`):
```json
"rg *": "allow",
```

**Claude Code** (insert after `Bash(rg:*)`, before `Bash(rpm -q:*)`):
```json
"Bash(rg:*)",
```

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.