Skip to main content
affpapa.org
RU EN
skill Claude Code CX Codex Cursor GitHub Copilot

mem-search — Claude Code skill: what it does, how to install

Searches memory for solutions and context from previous coding sessions when you need to recall past work.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add thedotmack/claude-mem --skill mem-search -a claude-code
Open on GitHub

What mem-search does

The skill runs a layered search workflow across claude-mem records. Instead of dumping raw data immediately, it first calls search(query) to find relevant IDs, checks nearby context with timeline(anchor=ID), and loads complete records via get_observations(ids=[...]) only for selected items.

Raw tool calls via get_tool_uses(ids=[...]) remain a last resort. Unprocessed tool_input and tool_response entries consume thousands of tokens each, so the skill fetches them only when summaries fall short. On write operations, it records platformSource as cursor or grok-bot, while reads keep entries from both hosts. If the MCP server is missing, run npx claude-mem install --ide before using it.

Install this if your agent handles recurring tasks and needs access to past session history without blowing prompt token limits.

What it helps with

  • retrieve solutions to problems solved in earlier sessions
  • inspect nearby context using timeline around a specific ID
  • fetch raw tool_input and tool_response payloads when summaries are insufficient

Example prompts for the agent

  • Did we already solve this database timeout issue last time?
  • Search memory for how we configured the build script previously

How to install mem-search

1Skills CLI (Vercel)

npx skills add thedotmack/claude-mem --skill mem-search -a claude-code

2Manually: put the files in place

~/.claude/skills/mem-search/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/mem-search/

From the same set15

The whole set →
smart-explore thedotmack Uses tree-sitter to map code structure and find symbols. Useful when you need to explore a codebase without loading every full file. Claude Code CX Codex Cursor +1 7,300installs make-plan thedotmack Turns a feature request into a phased plan built on real documentation instead of guesses. Useful right before you run do. Claude Code CX Codex Cursor +1 7,200installs do thedotmack The skill runs an implementation plan in phases through subagents. Use it when a plan needs execution with checks after each phase. Claude Code CX Codex Cursor +1 7,000installs knowledge-agent thedotmack Builds focused knowledge corpora from claude-mem observations and lets you query them in an AI session. Useful for reviewing past work by topic or project. Claude Code CX Codex Cursor +1 5,700installs learn-codebase thedotmack Instructs the agent to read every source file in full before starting work. Built for onboarding on unfamiliar repositories. Claude Code CX Codex Cursor +1 5,300installs how-it-works thedotmack Explains how claude-mem works behind the scenes. It covers tool observation logging, local file storage, and memory injection timing. Claude Code CX Codex Cursor +1 5,100installs pathfinder thedotmack This skill maps feature flows, finds duplicated concerns, and proposes a unified architecture. Use it to inspect a codebase before a refactor. Claude Code CX Codex Cursor +1 5,100installs wowerpoint thedotmack Turns a single text document into a kawaii NotebookLM slide deck via CLI. Helpful when you need to render an architecture doc or report into clear, shareable slides. Claude Code CX Codex Cursor +1 4,400installs

Similar

baoyu-post-to-x JimLiu Publishes text, images, video and long-form articles to X through a real Chrome browser. Useful when you want a post out of your agent instead of a manual tab. Claude Code CX Codex Cursor +1 28,900installs events coreyhaines31 Plans and manages webinars, conferences, and meetups focused on pipeline and qualified meetings rather than badge scans. Claude Code CX Codex Cursor +1 22,300installs nature-response Yuan1z0825 A skill that drafts, audits and revises responses to peer review, revision cover letters and marked manuscripts. Claude Code CX Codex Cursor +1 15,100installs baoyu-translate JimLiu Translates articles, files and URLs in three modes: quick, normal and refined. The refined mode adds a review and polish pass before publication. Claude Code CX Codex Cursor +1 25,600installs prd official github Turns a feature idea into a structured PRD with user stories, technical requirements, and risks. Use it when planning a software feature or an AI-powered one. GitHub Copilot 24,035installs imsg openclaw Connects AI coding agents to the imsg CLI to read chat history, send iMessage and SMS texts, and manage reactions or polls. Claude Code CX Codex Cursor +1 3,400installs find-skills vercel-labs Discovers and installs agent skills from skills.sh directly inside your coding assistant. Handy when you need domain-specific workflows for a project. Claude Code CX Codex Cursor +1 4,000,000installs grill-me Matt Pocock grill-me interviews you about a plan or design to expose gaps and sharpen decisions. Use it before implementation starts. Claude Code 1,424,476installs

Questions about mem-search

How do I install mem-search in Claude Code?

Run npx skills add thedotmack/claude-mem --skill mem-search -a claude-code in your terminal.

What does mem-search do?

It queries previous session memory in stages, filtering records by ID before loading detailed observations or raw tool calls.

What is required if the MCP server is missing?

Run the setup command npx claude-mem install --ide for your host before using the skill.

Source text

SKILL.md · Apache-2.0 
---
name: mem-search
description: >-
  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.

1. `search(query)` — index with IDs
2. `timeline(anchor=ID)` — nearby context
3. `get_observations(ids=[...])` — full details for those IDs only
4. `get_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 unless asked.

If MCP is missing, run the install skill first (`npx claude-mem install --ide <host>`).

© thedotmack · Apache-2.0 · thedotmack/claude-mem

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor