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 Lexus2016/turbo_quant_memory --skill turbo-quant-memorygit clone --depth 1 https://github.com/Lexus2016/turbo_quant_memoryWrote 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/lexus2016/turbo_quant_memory/turbo-quant-memory)<a href="https://agentmods.dev/skills/lexus2016/turbo_quant_memory/turbo-quant-memory"><img src="https://agentmods.dev/badge/skills/lexus2016/turbo_quant_memory/turbo-quant-memory/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/lexus2016/turbo_quant_memory/turbo-quant-memory"><img src="https://agentmods.dev/badge/skills/lexus2016/turbo_quant_memory/turbo-quant-memory.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00067 | $0.02694 |
| Opus 5.5 | $0.00027 | $0.01078 |
| Sonnet 5.5 | $0.00013 | $0.00539 |
| Haiku 4.5 | $0.00007 | $0.00269 |
Grade A, and why
turbo-quant-memory 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 yesterday.
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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Turbo Quant Memory (tqmemory)
Local-first MCP memory server for AI coding agents: compact retrieval, knowledge graph, secrets vault. You are the agent — this skill tells you how to detect, install, and operate it.
1. Detect
Check whether tqmemory is already available:
- MCP tools present? If you can call
health/server_info, tqmemory is installed and registered. Callhealth():migrations_pending: true→ surface themigrations_hintfield verbatim to the user. Do NOT runmigrate --applyyourself — active MCP clients must close first.
- CLI present but not registered? Run
turbo-memory-mcp --versionin a shell. If it answers, the tool is installed and only MCP registration in the current client may be missing (see §2.3). - Neither? Go to §2.
2. Install & Deploy
2.1 Install the CLI
uv tool install turbo-quant-memory
# or pinned: uv tool install 'turbo-quant-memory==0.33.0'
2.2 Install this skill
turbo-memory-mcp skill install
Copies the canonical SKILL.md into all detected agent skill directories (~/.agents/skills/ always, plus detected client dirs). Idempotent — re-run after every uv tool upgrade to upgrade older copies.
2.3 Register the MCP server in the client
# Codex
codex mcp add tqmemory -- turbo-memory-mcp serve
# Gemini CLI
gemini mcp add tqmemory turbo-memory-mcp serve
# Claude Code (project scope)
claude mcp add --scope project tqmemory -- turbo-memory-mcp serve
Any other client (Cursor, OpenCode, Antigravity, Kimi Code) takes the same server under its own config format — merge {"tqmemory": {"command": "turbo-memory-mcp", "args": ["serve"]}} into its MCP server map. Hermes runs a systemd gateway: add the same entry under mcp_servers: in ~/.hermes/config.yaml, then systemctl --user restart hermes-gateway. Per-client details: https://github.com/Lexus2016/turbo_quant_memory/blob/main/CLIENT_INTEGRATIONS.md. Restart the client afterwards.
Claude Code, optional: offer (do not silently add; it edits the user's settings) a SessionStart hook with "matcher": "compact" and {"type": "mcp_tool", "server": "tqmemory", "tool": "recent_context", "input": {"format": "hook", "limit": 5}}. It re-injects recent notes after every compaction. Use format: "hook": an mcp_tool hook's plain text never reaches the model, only its JSON additionalContext does. The full snippet is in CLIENT_INTEGRATIONS.md.
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.
- yesterday Changed · +1 lines db815c36a1ea
- 3d ago Changed · +1 lines 73ac60aea75b
- 4d ago Changed · +11 lines 9397af2f4296
- 16d ago Changed · +15 lines 20c8c392396e
- 1mo ago Changed 9262301a8ead
- 1mo ago Changed 747fdb16f28f
- 1mo ago First seen · 107 lines · 67 tokens per session scan A 3a80a46560ea
turbo-quant-memory is a skill published in the GitHub repository Lexus2016/turbo_quant_memory (9 stars, last pushed yesterday), licensed MIT. It adds 67 tokens to every session and 2,694 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
docmancer
Work from the same local memory as every other coding agent on this machine. Recall prior decisions, preferences, instructions, and project conventions that Claude Code, Codex, Cursor, and other agents wrote here, with cited sources, fully local. Also searches a separate local technical-documentation index.
memoryguard
Local-first MCP memory backend and governance console for coding agents. Auto-organize, quarantine, supersede, and rollback shared memories across multiple agents.
memory
Persist and retrieve agent memory across sessions — recall via the three-stage protocol (structure route → semantic search → navigation fallback), read via memoryload, see the wiki structure via memorybrowse, write well-placed pages via memorywrite (including section-level append/rewrite), maintain via memorycurate.…
memory-dream
Curate the workspace memory wiki as its appointed orchestrator. Trigger on a Cloud-scheduled Dream task or a user's direct curation request. Inspect candidates for orphan leaves, near-duplicates, stale pages, remote conflicts and oversized hubs; browse the graph, cluster leaves into INDEX/hub/leaf structure, maintain…
memory-import
Bulk-import an external knowledge base into Prismer memory via the three-layer import pipeline (07 §3.1). Use when the user asks to import/migrate documents, a knowledge base, or notes into workspace memory. Layer 1 lands raw documents (zero LLM, instantly searchable); Layer 2 is YOUR distillation work — you read the…
prismer-obsidian
Read, search, create, and edit notes in the Obsidian vault.