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 internetyev/cross-agent-memory-kit --skill mcp-memory-querygit clone --depth 1 https://github.com/internetyev/cross-agent-memory-kitWrote 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/internetyev/cross-agent-memory-kit/mcp-memory-query)<a href="https://agentmods.dev/skills/internetyev/cross-agent-memory-kit/mcp-memory-query"><img src="https://agentmods.dev/badge/skills/internetyev/cross-agent-memory-kit/mcp-memory-query/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/internetyev/cross-agent-memory-kit/mcp-memory-query"><img src="https://agentmods.dev/badge/skills/internetyev/cross-agent-memory-kit/mcp-memory-query.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 | $0.00121 | $0.02333 |
| Opus 5.5 | $0.00048 | $0.00933 |
| Sonnet 5.5 | $0.00024 | $0.00467 |
| Haiku 4.5 | $0.00012 | $0.00233 |
Grade A, and why
mcp-memory-query 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 1mo 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Memory Query
Retrieve and present information from the mcp-memory-service. The service stores facts, decisions, conventions, session learnings, and mistake patterns across conversations.
Shared cross-device memory (hybrid Cloudflare backend)
When the hybrid backend is configured, this memory is a single shared store
across all of the user's devices, not a per-machine database. The MCP server
keeps a fast local SQLite cache on each device, and Cloudflare (D1 + Vectorize)
is the shared source of truth. Implications when answering:
(If the server runs the local-only sqlite_vec backend instead, ignore this
section - the store is just the single local database.)
- Eventually consistent. A memory stored on another device appears here after the next background sync (seconds to minutes), not instantly. If a lookup returns nothing for something the user expects, say it may have been written on another device and not synced yet - do not assert "nothing was ever stored".
- Writes are global. Anything stored via this skill is visible on every device after sync. Confirm with: "Stored - it'll sync to your other devices shortly."
- Offline-safe. If Cloudflare is unreachable, reads/writes still hit the local cache and sync up later; results may be slightly behind the shared store.
- The backend is configured in the
memoryMCP serverenvin~/.claude.json(MCP_MEMORY_STORAGE_BACKEND=hybrid+CLOUDFLARE_*). The skill never needs to set this; it only queries via themcp__memory__*tools.
Available tools
| Tool | When to use |
|---|---|
mcp__memory__memory_search |
Primary retrieval - semantic, exact, or hybrid search |
mcp__memory__memory_list |
Browse all memories or filter by tag/type |
mcp__memory__mistake_note_search |
Look up known error patterns before starting a task |
mcp__memory__memory_stats |
Show service health / cache stats |
mcp__memory__memory_health |
Check database health |
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.
- 1mo ago First seen · 221 lines · 121 tokens per session scan A d192a7115687
mcp-memory-query is a skill published in the GitHub repository internetyev/cross-agent-memory-kit (9 stars, last pushed 4mo ago), licensed MIT. It adds 121 tokens to every session and 2,333 once invoked, about $0.0005 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
karpathy-llm-wiki
Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.
lean-ctx
Use LeanCTX Context Gateway tools to select task-relevant code context, apply supported controls, reuse local knowledge and inspect recorded evidence. Use when lean-ctx MCP tools (ctx) are available or file, search or command output needs a focused view.
lean-ctx
Use LeanCTX Context Gateway tools to select task-relevant code context, apply supported controls, reuse local knowledge and inspect recorded evidence. Use when lean-ctx MCP tools (ctx) are available or file, search or command output needs a focused view.
kmd-ingest
The write protocol for a markdown knowledge base (Obsidian-compatible, the LLM-wiki pattern) — personal or shared. Use for EVERY write into the KB — distilling a new or scraped source, promoting a finished artifact/report/lesson into the KB, filing a durable learning, insight, or query answer, or correcting/updating…
pn-continual-learning
Incrementally extract recurring user corrections and durable workspace facts from transcript changes, then update AGENTS.md with plain bullet points only. Use when the user asks to mine previous chats, maintain AGENTS.md memory, or build a self-learning preference loop.
deep-research
Use when asked to research deeply, compare options or vendors, fact-check a claim, investigate an unfamiliar topic, prepare a report or briefing, build a knowledge base or reference doc, or trace a claim to its primary source.