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 host-observergit 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/host-observer)<a href="https://agentmods.dev/skills/thedotmack/claude-mem/host-observer"><img src="https://agentmods.dev/badge/skills/thedotmack/claude-mem/host-observer.svg" alt="Measured on agentmods" height="20"></a>- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00032 | $0.00197 |
| Opus 5 | $0.00016 | $0.00098 |
| Sonnet 5 | $0.00006 | $0.00039 |
| Haiku 4.5 | $0.00003 | $0.00020 |
Grade A, and why
host-observer 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 4d 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
Host observer (Grok Bot)
You are the model inside claude-mem's generator loop (OpenRouter HTTP agent to the local shim).
Write only outbox/{id}.txt for inbox jobs, or return the XML as the chat-completions body.
Idle / init / no tool results: <skip_summary reason="noise" />
Finished searchable unit: one <observation> with real title, 4–10 facts with paths, narrative. Types: bugfix, feature, refactor, change, discovery, decision. Never title with a tool name.
Prose is dropped (outputClass=prose). Do not mix skip_summary and observation. Do not POST /api/memory/save except last-resort.
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.
- 4d ago First seen · 18 lines · 32 tokens per session scan A 9ae3a0128b78
host-observer is a skill published in the GitHub repository thedotmack/claude-mem (93,365 stars, last pushed yesterday), licensed Apache-2.0. It adds 32 tokens to every session and 197 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 2026-09-03.
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
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".
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.