Agent Memory
Hook
Hooks
What auto-memory runs automatically, and when. A hook is a command Claude Code fires at a fixed moment, without you asking for it.
Install
$ npx -y skills add severity1/claude-code-auto-memory --agent claude-codeShips with auto-memory. Installing the plugin gets these hooks.
What fires, and when
PreToolUse
- Matches
Bashpython3 "${CLAUDE_PLUGIN_ROOT}/scripts/trigger.py" || python "${CLAUDE_PLUGIN_ROOT}/scripts/trigger.py"
PostToolUse
- Matches
Edit|Write|Bashpython3 "${CLAUDE_PLUGIN_ROOT}/scripts/post-tool-use.py" || python "${CLAUDE_PLUGIN_ROOT}/scripts/post-tool-use.py"
Stop
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/trigger.py" || python "${CLAUDE_PLUGIN_ROOT}/scripts/trigger.py"
SubagentStop
- Matches
^(auto-memory:)?memory-updater$python3 "${CLAUDE_PLUGIN_ROOT}/scripts/trigger.py" || python "${CLAUDE_PLUGIN_ROOT}/scripts/trigger.py"
Ships withauto-memory
Your CLAUDE.md, always in sync. Minimal tokens. Zero config. Just works. A Claude Code plugin that watches what Claude Code edits, deletes, and moves - then quietly updates your project memory in the background. No manual maintenance needed.
Get the whole plugin

