Mmcp.market

claude-mem-install skill

by thedotmack·thedotmack/claude-mem·95k stars·Apache-2.0

Use this when setting up claude-mem on Grok Bot: local worker plus CMEM Pro observer (default), optional host-login observer, or remote cmem.ai. No Cursor required.

A100/100content scan

Is the claude-mem-install skill safe?

Clean: nothing in its files matched our rules. We read 1 file in the folder on 2026-09-28.

No findings.

Install the claude-mem-install skill

A skill is a folder. Copy it into your agent's skills folder and the agent loads it when the task matches its description. 

git clone --depth 1 https://github.com/thedotmack/claude-mem.git /tmp/claude-mem
mkdir -p ~/.claude/skills
cp -r /tmp/claude-mem/claude-mem-grok-bot/skills/install ~/.claude/skills/claude-mem-install
available in every project

In the Claude apps, zip the folder and upload it from the Skills settings. The folder on GitHub

The instructions your agent would load

SKILL.md as published, without the frontmatter. Read it on GitHub

Install claude-mem on Grok Bot

Independent of Cursor. Grok Bot has no session-start / file-read / tool-use hooks.

Local worker + CMEM Pro observer (default)

npx claude-mem install --ide grok-bot

Do not pass --provider host unless you want the loopback shim. With no --provider, this is the CMEM Pro path:

  • Worker on 127.0.0.1: (default 37700 + uid%100). Do not restart if healthy.
  • Transcript watcher per Grok Bot agent (platformSource=grok-bot)
  • Observer via CMEM Pro: CLAUDEMEMPROVIDER=openrouter, CLAUDEMEMOPENROUTERBASEURL=https://cmem.ai/api/inference/v1, CLAUDEMEMOPENROUTERMODEL=cmem-observer, API key from installer OAuth (cmpro memory key)
  • Interactive installer pre-selects CMEM Pro
  • MCP sessionstartcontext at the start of a real task
  • Live INDEX into agents//memory/log/zz-claude-mem-inject.md (disable with CLAUDEMEMGROKBOTINJECT_ENABLED=false)

No xAI key. No Claude CLI.

Optional: local host-login observer

Explicit opt-in only. Not the user default.

npx claude-mem install --ide grok-bot --provider host

Loopback OpenAI-compatible shim on a free loopback port (not the worker port). Idle replies are ; finished units are one . This Grok login fulfills inbox jobs (skill host-observer).

Remote worker / remote observer

Set plugin variable CLAUDEMEMMCP_TOKEN and use MCP claude-mem-remote.

npx claude-mem install --ide grok-bot --runtime server --server-url https://cmem.ai

More skills from thedotmack/claude-mem

  • AAgent Cost ReportBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json.
  • AAgent Cost ReportBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json.
  • AAgent Cost ReportBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json.
  • AAgent Cost ReportBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json.
  • AAgent Cost ReportBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json.
  • AbabysitWatch a pull request or review cycle until it is ready to merge. Use when asked to babysit, monitor, or keep checking PR comments, reviews, and CI until all actionable issues are resolved.
  • Accs-alignRun the CCS Align seat's hourly breathing cycle — prove the local claude-mem worker is healthy, pull needle observations through search → timeline → get_observations, land them in a seat-owned middle cache via atomic grab → append → filter exclude-marks → replace, manage exclude marks, and walk house → project → seat rules to detect conflicts (SHADOW_HOUSE, DENY_ALLOW, DRIFT, CLOCK_HEADER) with an append-only rules-report.md. Use when asked to run CCS Align, breathe the alignment seat, refresh the middle cache, exclude or restore an observation, walk rules, check rules conflicts, or check the Worker Watch board.
  • Aclaude-mem-installUse this when setting up claude-mem on Cursor: local or remote worker, local host-login observer or remote cmem.ai inference.
  • Acloud-syncSet up or check claude-mem cloud sync with cmem.ai Pro. Use when the user says "set up cloud sync", "sync my memories", "cmem pro", "cloud backup", "sync status", or wants their memory database backed up or synced to their cmem.ai account.
  • Adesign-isAudit a design against Dieter Rams' ten "Good design is..." principles, then hand off a /make-plan prompt for one of three outcomes — new design, refine design, or redesign. Use when the user says "audit this design", "design review", "check this UI against Rams", "is this UI good", "critique this design", "design audit", or asks for a critique that should lead to a plan.
  • Ado
  • AdoExecute a phased implementation plan using subagents. Use when asked to execute, run, or carry out a plan — especially one created by make-plan.

All agent skills → · MCP servers