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 agentmods add skills/udjin-labs/mnemostack/claude-codenpx skills add udjin-labs/mnemostack --skill claude-codegit clone --depth 1 https://github.com/udjin-labs/mnemostackWrote 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/udjin-labs/mnemostack/claude-code)<a href="https://agentmods.dev/skills/udjin-labs/mnemostack/claude-code"><img src="https://agentmods.dev/badge/skills/udjin-labs/mnemostack/claude-code.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00000 | $0.00612 |
| Opus 5 | $0.00000 | $0.00306 |
| Sonnet 5 | $0.00000 | $0.00122 |
| Haiku 4.5 | $0.00000 | $0.00061 |
Grade A, and why
claude-code 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.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Desktop / Claude Code
Wire mnemostack into Claude Desktop (and by extension Claude Code, which reads the same MCP config) as an MCP server.
Install
-
Make sure the binary and a working backend are ready:
pip install 'mnemostack[mcp]' mnemostack health --provider gemini -
Locate the Claude Desktop MCP config:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json - Linux (unofficial/Claude Code):
~/.config/claude/claude_desktop_config.json
- macOS:
-
Merge this entry into the
mcpServersblock (create the file if needed):{ "mcpServers": { "mnemostack": { "command": "mnemostack", "args": [ "mcp-serve", "--provider", "gemini", "--collection", "my-memory" ], "env": { "GEMINI_API_KEY": "your-key-here" } } } }Swap
--provider geminiforollamaoropenaiif that's whathealthvalidated. For graph tools, add--memgraph-uri bolt://localhost:7687. -
Restart Claude Desktop (fully quit, not just close the window).
Verify
In a new chat, ask Claude:
List the MCP tools you have available from mnemostack.
You should see health, search, answer, and feedback (plus graph_query
and graph_add_triple if a Memgraph URI was passed). Then:
Use mnemostack to search for "VPN failover" with tier 1.
The reply should cite sources and not leak any snippets (tier 1 = list only).
Uninstall
Remove the mnemostack entry from mcpServers in the config file and restart
Claude Desktop. No other state lives on the host side — the vector store and
the memgraph are owned by the mnemostack process, not by the integration.
Troubleshooting
- Tools don't appear: check Claude Desktop's MCP logs
(
~/Library/Logs/Claude/mcp*.logon macOS). A common cause ismnemostacknot being on PATH for the GUI app — use an absolute path incommand. fastmcp not installed: the[mcp]extra is missing:pip install 'mnemostack[mcp]'.healthsays DOWN: the MCP server will start but every tool call will fail until Qdrant/embedding provider is reachable.
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 · 74 lines · 0 tokens per session scan A ede32b744e73
claude-code is a skill published in the GitHub repository udjin-labs/mnemostack (7 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 612 tokens. 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 2026-08-31.
Other skills, from other repositories
coding-patterns
Surfaces relevant coding patterns and conventions when writing new code.
memory-retrieval
Automatically retrieve relevant memories when user asks about past decisions, conventions, or patterns.
outcome-feedback
Prompts for outcome feedback after solutions that used memory context.
install-openviking-memory
Install and configure the OpenViking long-term memory plugin for OpenClaw via natural conversation. Once installed, the plugin automatically captures facts from chats and recalls relevant context before each reply (auto-capture + auto-recall, cross-session). Covers prerequisites, install through OpenClaw's plugin…
openclaw-plugin
This plugin is a thin adapter between OpenClaw and LycheeMem. It does not replace memory-core, does not claim plugins.slots.memory, and does not duplicate LycheeMem algorithms.
lycheemem
Forceful operating rules for using LycheeMem as the primary structured long-term memory path inside OpenClaw.