Claude-Mem, now presented as Grok Mem, records an agent's work, compresses it with AI, and brings relevant notes into later sessions so the agent can remember decisions and next steps. It is intended for persistent context across agent conversations and supports multiple coding-agent environments. The catalogue add-ons provide the workflows and integrations used to operate this memory system.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add thedotmack/claude-mem --skill how-it-worksgit clone --depth 1 https://github.com/thedotmack/claude-memWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/thedotmack/claude-mem/how-it-works)<a href="https://agentmods.dev/skills/thedotmack/claude-mem/how-it-works"><img src="https://agentmods.dev/badge/skills/thedotmack/claude-mem/how-it-works/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/thedotmack/claude-mem/how-it-works"><img src="https://agentmods.dev/badge/skills/thedotmack/claude-mem/how-it-works.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 22 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00047 | $0.00264 |
| Opus 5 | $0.00023 | $0.00132 |
| Sonnet 5 | $0.00009 | $0.00053 |
| Haiku 4.5 | $0.00005 | $0.00026 |
Grade A, and why
how-it-works scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
How claude-mem works
What it does
Every Read, Edit, and Bash that Claude makes turns into a compressed observation. Observations get summarized at session end. Relevant ones get auto-injected into future prompts so the next session starts with context from the last one — no re-explaining the codebase, no re-discovering decisions.
When it kicks in
Memory injection starts on your second session in a project.
The first session in a fresh project seeds memory; subsequent sessions receive auto-injected context for relevant past work. Run /learn-codebase if you want to front-load the entire repo into memory in a single pass (~5 minutes, optional).
Where data lives
Everything stays in ~/.claude-mem on this machine.
Nothing leaves your machine except calls to whichever AI provider you configured for compression (Claude / OpenRouter / Gemini). The SQLite database, vector index, logs, and settings all live under that directory and are removed cleanly on npx claude-mem uninstall.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 23 lines · 47 tokens per session scan A 9214da98b56a
how-it-works is a skill published in the GitHub repository thedotmack/claude-mem (93,603 stars, last pushed today), licensed Apache-2.0. It adds 47 tokens to every session and 264 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
hivemind-memory
Global team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when recalling information.
hivemind-memory
Global team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when recalling information.
hivemind
Global team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when recalling information.
dejavu-rules
A conversation-based manager for rules stored in CLAUDE.md, a project file that tells the coding assistant how to work. It can add, edit, remove, and review those rules.
dejavu
Review and manage learned antipattern rules. Use when Claude should review its past mistakes, apply learned rules to CLAUDE.md, or check rule effectiveness. Triggers on "/dejavu", "review rules", "what did you learn".
dejavu-report
Generate a weekly report of detected patterns and rule effectiveness. Use when user asks "dejavu report", "what did you learn this week", "dejavu weekly".