What it does
The subagents-explore-only hook runs at SubagentStart and adds an instruction to each subagent's context before its first prompt. This covers built-in, custom and plugin agents. The instruction tells subagents to investigate with read-only tools, never edit, create or delete files, never run state-changing commands, and report their findings so the main agent makes every change. The main conversation is not affected.
It suits workflows where subagents should gather information about a codebase or project without altering it, leaving all modifications to the main agent.
It is set up as a hook that injects text into subagent context. Because it only adds an instruction, it depends on the subagent following it.
Limitations and requirements
The hook provides an instruction, not enforcement, so subagents are not technically prevented from writing files or running commands. The publisher recommends installing the security/subagent-read-only-guard hook alongside it to block writes from subagents.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
Sources
- AI Templates (aitmpl) first seen 13 Nov 2026 · last seen 18 Nov 2026 · its page on the source · figures reported by the source: aitmpl downloads 137
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.
As shown on www.aitmpl.com when we last read it