Subagents Explore Only
Turns every subagent into a read-only explorer. A SubagentStart hook injects an instruction into each subagent's context (built-in, custom and plugin agents alike) before its first prompt: investigate with read-only tools, never edit, create or delete files, never run state-changing commands, and report findings back so the main agent makes every change. The main conversation is not affected. This is an instruction, not enforcement: install the security subagent-read-only-guard hook alongside it to block writes from subagents.
npx claude-code-templates@latest --skill ••••••••••••••••••••Interactive Terminal Locked
Unlock this skill to run and inspect the interactive installation sequence.
{
"description": "Turns every subagent into a read-only explorer. A SubagentStart hook injects an instruction into each subagent's context (built-in, custom and plugin agents alike) before its first prompt: investigate with read-only tools, never edit, create or delete files, never run state-changing commands, and report findings back so the main agent makes every change. The main conversation is not affected. This is an instruction, not enforcement: install the security/subagent-read-only-guard hook alongside it to block writes from subagents.",
"hooks": {
"SubagentStart": [
{
"hooks": [
{
"type": "command",
"command": "printf '%s\\n' '{\"hookSpecificOutput\":{\"hookEventName\":\"SubagentStart\",\"additionalContext\":\"You are running as an exploration-only subagent. Your job is to investigate and report, not to change anything. Use only read-only actions: read files, search with Grep and Glob, list directories, inspect git history and diffs, and read web pages with WebFetch or WebSearch. Do not create, edit, move or delete files. Do not run commands that change state, such as package installs, builds that write output, git commit, git push, git checkout, migrations, or requests that write to external services. If the task seems to require a change, do not make it: describe the exact change (file, location and proposed content) in your final report so the main agent can apply it.\"}}'"
}
]
}
]
}
}
How to Use & Getting Started
# Step 1: Initialize skill agent setup
npx skills add Subagents Explore Only --install-production
python -m pip install -r requirements.txt
codex plugin install Subagents Explore Only@latest
export API_KEY=secret_token_key_here
Installation Runbook & Walkthrough Locked
Unlock this skill to reveal complete step-by-step setup guides, terminal commands, configuration recipes, repository links, and interactive installation video walkthroughs.
Unlock full access to Subagents Explore Only
Get instant access to complete setup guides, repository source code, and integration assets.
More in setting
View all setting skills →Context Monitor
Real-time Claude Code context usage monitor with visual progress bars, color-coded alerts, session analytics (cost, duration, lines changed), and auto-compact warnings. Tracks conversation context consumption and provides visual feedback to prevent session interruptions.
Performance Optimization
Optimize Claude Code performance by adjusting token limits and disabling non-essential features. Reduces API costs and improves response times for development workflows focused on code quality over conversational features.
Development Utils
Enhanced development environment configuration with useful utilities and debugging features. Includes built-in ripgrep usage, terminal title updates, and directory maintenance for improved developer experience.