Skip to content
cccskills
FreePublished on GitHubEnglish overview

mem-search

Search persistent Claude-Mem records on cmem.ai for context from earlier sessions across agents. Narrow keyword searches to relevant observations, then explain past work, decisions, and dates in plain language.

OriginalShow the original description

This skill should be used when the user asks to "search memory", "what do you remember about X", "check claude-mem", "mem search", "find past observations", "what did we do last session", or wants prior-session context about a project, decision, file, or task. Searches the user's Claude-Mem (cmem.ai) memory.

thedotmack/claude-mem
AI rating90/ 100See how to install

Good for

  • Recalling what happened in the previous session
  • Finding the reasoning behind a project decision
  • Retrieving past records about a file or error
  • Reviewing saved work across different agents

Overview

What it does

mem-search searches past Claude-Mem work records stored on cmem.ai and extracts the context you need. These timestamped records summarize earlier sessions from Claude Code, Cowork, Codex, and other agents. It starts with broad keywords to find titles and summaries, then narrows the search using distinctive terms from those results. It explains relevant information in plain language and provides record dates and times when you ask when something happened.

When it helps

Use it to check where the previous session left off or recall why a project decision was made. You can also look for related records using a file name or an error message.

Example requests

  • “Search memory and tell me what we did in the previous session.”
  • “Check what decisions we previously made about this file.”

Notes

The bundled CLI runs on Node.js and uses the cmem.ai API key configured in the plugin. If no key is configured, setup is required. Search terms are sent to cmem.ai, so do not include secrets. Date and type filters may be ignored; the search approach therefore prioritizes narrowing by keywords.

This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.

Objective evaluation

AI rated this skill on four points using only the contents of its SKILL.md. Stars and popularity are not taken into account.

Clear instructionsIs it clear when to use it and what it does?
AGoodIt explicitly searches cmem.ai when asked about previous sessions or decisions.
Concrete stepsAre steps, inputs, outputs, and examples spelled out?
AGoodIt provides a search command, broad-to-narrow search steps, and a status diagnostic example.
SafetyAre sending data, deleting files, and running commands disclosed?
AGoodIt discloses that queries are sent to cmem.ai and explicitly prohibits including secrets.
Easy setupDoes it need few tools or API keys, and are they documented?
BPartly lackingIt requires Node.js and a cmem.ai API key but gives no concrete key configuration procedure.

The total counts each point as A = 25, B = 15, C = 5. Rated by AI (OpenAI Codex) as of Oct 21, 2026. Treat it as a guide and read the original before installing.

Disagree? Request a re-evaluation

Tell us which point is wrong and why. No login needed. We will check it against the SKILL.md, redo the evaluation, and show the result here.

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

Files included (1)

  • SKILL.md2.0 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Claude-Mem Search (Cowork)

Search the user's persistent Claude-Mem memory on cmem.ai. Memory contains timestamped observations synthesized from past sessions across all their agents (Claude Code, Cowork, Codex, and others).

How to search

Run the bundled CLI (no dependencies, uses the plugin's configured API key):

node "${CLAUDE_PLUGIN_ROOT}/scripts/cmem-hook.mjs" search "your query" --limit 20

Progressive search method

Follow claude-mem's Index → Timeline → Transcript discipline — cheap passes first, expensive detail only for confirmed hits:

  1. Index pass — run 1–3 broad keyword searches (project names, file names, error strings, feature names). Skim titles/summaries only.
  2. Narrow pass — re-search with the most specific terms found in step 1 (IDs, exact phrases) and a smaller --limit.
  3. Answer — synthesize from the observations returned. Quote timestamps when the user asks "when".

Do not dump raw search output at the user; extract the relevant observations and answer in plain language.

Diagnostics

If searches return nothing or error:

node "${CLAUDE_PLUGIN_ROOT}/scripts/cmem-hook.mjs" status

Report the status output plainly: a MISSING api key means the plugin needs the user's cmem.ai key added to its configuration; a 404 on /api/hooks/context just means the newer Pro endpoint isn't deployed — search still works via /api/mcp.

Notes

  • Some filters (date ranges, type) may be silently ignored by the cloud API until MCP parity ships — prefer keyword narrowing over filter flags.
  • Never write secrets into search queries; queries are sent to cmem.ai.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Agent Cost Report

FreeSummaryAI rating 90

Turn agent activity and transcript token counts into a cost report organized around completed outcomes. Separate estimates from measured spending, examine waste and rework, and export readable HTML with supporting JSON, CSV, and evidence.

  • Reviewing weekly agent spending and completed work
  • Comparing costs per completed outcome
  • Investigating the cost of loops and rework
thedotmack/claude-mem102.3KUpdated Oct 22, 2026

babysit

FreeSummaryAI rating 80

Monitor a pull request through reviews and automated checks, verify reported issues against the code, and make focused fixes. Repeat testing and review checks until actionable comments and unresolved threads are cleared and the request is ready to merge.

  • Monitoring a pull request while automated checks run
  • Verifying and fixing review comments
  • Checking unresolved threads before a merge
thedotmack/claude-mem102.3KUpdated Oct 22, 2026

build-and-release

FreeSummaryAI rating 60

Delegate a coding task to a subagent that runs build, merges the ready pull request, and continues from the updated main branch into release, connecting implementation and release work in one automated sequence.

  • Delegating a coding task through release
  • Connecting a ready PR merge to release work
  • Running build and release in sequence
thedotmack/claude-mem102.3KUpdated Oct 22, 2026

ccs-align

FreeSummaryAI rating 90

Check a local claude-mem worker, refresh viewer-specific caches of important observations, and exclude or restore records without deleting history. Inspect rules across shared, project, and agent layers, then append conflicts to a report.

  • Checking worker health and refreshing important observations
  • Excluding cached records while preserving source history
  • Restoring previously excluded observations to a cache
thedotmack/claude-mem102.3KUpdated Oct 22, 2026

childhood

FreeSummaryAI rating 90

Monitor a shipped release by checking published packages, live services, installed plugins, and late CI results or user reports. Verify regressions, prepare authorized fixes, and report release health with evidence and any remaining verification gaps.

  • Checking package contents after publication
  • Verifying changed user flows in production
  • Confirming installed plugins use the shipped version
thedotmack/claude-mem102.3KUpdated Oct 22, 2026

claude-mem-install

FreeSummaryAI rating 90

Set up claude-mem in Cursor with a local or remote worker, the process that runs its work. Follow configuration steps for remote inference through cmem.ai or a local observer using the host's login.

  • Installing claude-mem with a local worker in Cursor
  • Connecting Cursor to a remote claude-mem worker
  • Configuring host-login or cmem.ai inference
thedotmack/claude-mem102.3KUpdated Oct 22, 2026

See all skills by thedotmack

Report a problem with this skill