Skip to content
Agent Orchestration
Hook

Hooks

What rlm-claude-code runs automatically, and when. A hook is a command Claude Code fires at a fixed moment, without you asking for it.

From plugin
rlm-claude-code
1062 skills1 agent8 commands6 hooks
Install
> /plugin marketplace add rand/rlm-claude-code
> /plugin install rlm-claude-code@rlm-claude-code

Ships with rlm-claude-code. Installing the plugin gets these hooks.

What fires, and when

SessionStart

Fires once when a session begins, and again after a context compaction. It is where a plugin sets up its environment, or restores state the compaction dropped.

  • Matches.*"${CLAUDE_PLUGIN_ROOT}/scripts/hook-dispatch.sh" session-init

UserPromptSubmit

Fires before Claude sees each prompt you send. A plugin can use it to inject context, so the same instruction reaches the model every turn instead of only at session start.

  • Matches.*"${CLAUDE_PLUGIN_ROOT}/scripts/hook-dispatch.sh" complexity-check

PreToolUse

PostToolUse

PreCompact

  • Matches.*

Stop

  • Matches.*"${CLAUDE_PLUGIN_ROOT}/scripts/hook-dispatch.sh" trajectory-save
Read hooks/hooks.json
Ships withrlm-claude-code

Transform Claude Code into a Recursive Language Model (RLM) agent with intelligent orchestration, unbounded context handling, persistent memory, and REPL-based decomposition.

Get the whole plugin