What it does. Use this when the user asks to search memory, "did we already solve this?", "how did we do X last time?", or wants work from previous sessions.
mem-search
Layered workflow. Do not dump full observations until IDs are filtered, and do not reach for raw tool bodies until the summaries came up short.
search(query)
— index with IDstimeline(anchor=ID)
— nearby contextget_observations(ids=[...])
— full details for those IDs onlyget_tool_uses(ids=[...])
— the ORIGINAL tool_input
/ tool_response
for specific tool calls. Last resort: these are unsummarized and can run to thousands of tokens each.
Stamp
platformSource
as
cursor
or
grok-bot
on writes for this host. When reading, do not drop the other host
Install
npx skills add thedotmack/claude-mem --skill mem-search
Or copy the skill folder manually:
git clone https://github.com/thedotmack/claude-mem.git
cp -r claude-mem/claude-mem-cursor/skills/mem-search/ ~/.claude/skills/mem-search
Source: thedotmack/claude-mem — 102,229 stars, Apache-2.0, verified 2026-10-22.
