mcp-memory-query

mcp-memory-query is a skill for Claude Code, Codex from internetyev/cross-agent-memory-kit. It costs 121 tokens per session (2,333 once invoked), scanned A, original, MIT.

A memory lookup tool for finding stored facts, decisions, notes, and lessons from earlier coding-agent sessions. Depending on setup, the memory may be shared across devices or kept in one local database.

In plain words
What is it for?
Use it to check what was previously decided, recall project conventions, answer questions about stored knowledge, or retrieve notes from earlier sessions.
Why use it?
It avoids relying on the current conversation to recall past choices and conventions. It also makes clear when information from another device may not have synced yet.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/internetyev/cross-agent-memory-kit/mcp-memory-query
Any agent
npx skills add internetyev/cross-agent-memory-kit --skill mcp-memory-query
Clone the repo
git clone --depth 1 https://github.com/internetyev/cross-agent-memory-kit

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for mcp-memory-query

README.md
[![agentmods](https://agentmods.dev/badge/skills/internetyev/cross-agent-memory-kit/mcp-memory-query.svg)](https://agentmods.dev/skills/internetyev/cross-agent-memory-kit/mcp-memory-query)
Your own site
<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="Measured on agentmods" height="20"></a>
Per session 121 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,333 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00121 $0.02333
Opus 5 $0.00060 $0.01167
Sonnet 5 $0.00024 $0.00467
Haiku 4.5 $0.00012 $0.00233

Measured 3d ago against content hash d192a7115687, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d 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.

skills/mcp-memory-query/SKILL.md · 221 lines

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 memory MCP server env in ~/.claude.json (MCP_MEMORY_STORAGE_BACKEND=hybrid + CLOUDFLARE_*). The skill never needs to set this; it only queries via the mcp__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

Read the full file on GitHub · 221 lines

Changes

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.

  1. 3d ago First seen · 221 lines · 121 tokens per session scan A d192a7115687

Subscribe to this mod's changes

mcp-memory-query is a skill published in the GitHub repository internetyev/cross-agent-memory-kit (9 stars, last pushed 2mo ago), licensed MIT. It adds 121 tokens to every session and 2,333 once invoked, about $0.0006 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 2026-08-31.

Related

Other skills, from other repositories

pnpm

Fast, disk-efficient package manager for this pnpm + Turborepo monorepo. pnpm owns the dependency graph, lockfile, and supply-chain policy; Turborepo owns task orchestration (build, lint, dev, --affected).

louisbrulenaudet/monorepo-template · 96 tokens

ui-ux-design-best-practices

UI/UX polish, component design, animation decisions, and Tailwind v4 patterns for making interfaces feel right. Use when reviewing, writing, or refactoring UI code involving animations, transitions, CSS transforms, gestures, Tailwind utility classes, or interactive component behavior. Triggers on tasks involving…

louisbrulenaudet/monorepo-template · 96 tokens

front-vitest

Depth for Vitest tests of front- React 19 SPAs when DOM, RTL, TanStack Query hooks, or TanStack Router route-tree tests are needed. USE WHEN: adding jsdom or testing-library, writing tsx render or renderHook tests, testing createMemoryHistory plus RouterProvider, Suspense UI, or React 19 act fixtures. DO NOT USE WHEN…

louisbrulenaudet/monorepo-template · 102 tokens

skills-update

USE WHEN: updating locked agent skills from skills-lock.json, refreshing upstream skill content, or running npx skills update for project skills. DO NOT USE WHEN: adding new skills (use npx skills add with explicit approval), running bare npx skills update without skill names, or updating project-local skills that are…

louisbrulenaudet/monorepo-template · 72 tokens

review-code-quality

Lint, style, maintainability review. USE WHEN: user runs /review-code-quality or explicitly asks for this review. DO NOT USE WHEN: implementing features or fixing bugs unless the user asked for a review.

louisbrulenaudet/monorepo-template · 46 tokens

review-security

Security-focused review. USE WHEN: user runs /review-security or explicitly asks for this review. DO NOT USE WHEN: implementing features or fixing bugs unless the user asked for a review.

louisbrulenaudet/monorepo-template · 40 tokens