Is the Claude-Mem skill free?

Yes. The skill itself is free from thedotmack/claude-mem. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Claude-Mem SkillProof Score?

7.2/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 4/5.

How do I install Claude-Mem?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Claude-Mem with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Claude-Mem

Cross-session memory search via a token-efficient search→timeline→fetch workflow

by thedotmack · thedotmack/claude-mem

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 7.2/10
Tested: Jul 20, 2026
Environment: Claude Code 2.x (agent harness)

⚠ This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (SKILL.md not found in repo tree). The test below is what we measured on Jul 20, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.

Fetched plugin.json (v13.11.0), README, and mem-search/SKILL.md raw. SKILL.md has valid frontmatter (name+description), references no missing relative files, and cleanly documents a search→timeline→get_observations token-saving workflow — but it invokes MCP tools that only exist after `npx claude-mem install` stands up a Bun worker + SQLite + Chroma and populates a memory DB, so copying the skill alone is inert and OUTPUT is NOT measured (not a measured loss). Grep of SKILL.md found no exfil/secrets/base64; flagged only that the README ships a `curl | bash` OpenClaw installer and cloud-sync to cmem.ai, neither of which I ran. TRIGGER phrasings — SHOULD: "Did we already fix this auth bug in a previous session?", "How did we set up the worker last time?", "Search our memory for what we shipped last week"; should NOT: "Remember to add error handling here" (instruction, not recall), "What did I just say a moment ago?" (current conversation, which the description explicitly excludes).

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 4/5
Triggers reliably 5/5
Output vs. baseline 5/10
Docs & honesty 4/5

What Claude-Mem does

Claude-Mem is a persistent memory-compression system for Claude Code; its mem-search skill queries a cross-session memory database using a 3-layer search/timeline/get_observations workflow to save tokens. It triggers when you ask "did we already solve this?", "how did we do X last time?", or need work recalled from previous sessions. The skill itself is a clean prompt, but it drives MCP tools that only exist after installing the worker service and populating the database.

How to install Claude-Mem

Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.

Commands — how to trigger Claude-Mem

/claude-mem Cross-session memory search via a token-efficient search→timeline→fetch workflow

It also activates on plain-language prompts like these:

Set up Claude-Mem so my agent remembers past sessions
Capture this session's work and inject it into future ones
Compress my session history so context carries over

Frequently asked questions

Is the Claude-Mem skill free?: Yes. The skill itself is free from thedotmack/claude-mem. SkillProof publishes the install command and an independent test verdict at no cost.
Does Claude-Mem work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 20, 2026. Verdict: Works with setup. Fetched plugin.json (v13.11.0), README, and mem-search/SKILL.md raw. SKILL.md has valid frontmatter (name+description), references no missing relative files, and cleanly documents a search→timeline→get_observations token-saving workflow — but it invokes MCP tools that only exist after `npx claude-mem install` stands up a Bun worker + SQLite + Chroma and populates a memory DB, so copying the skill alone is inert and OUTPUT is NOT measured (not a measured loss). Grep of SKILL.md found no exfil/secrets/base64; flagged only that the README ships a `curl | bash` OpenClaw installer and cloud-sync to cmem.ai, neither of which I ran. TRIGGER phrasings — SHOULD: "Did we already fix this auth bug in a previous session?", "How did we set up the worker last time?", "Search our memory for what we shipped last week"; should NOT: "Remember to add error handling here" (instruction, not recall), "What did I just say a moment ago?" (current conversation, which the description explicitly excludes).
What is the Claude-Mem SkillProof Score?: 7.2/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 4/5.
How do I install Claude-Mem?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Claude-Mem with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.