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 instructions/yuvalsuede/memory-mcp/claude-mdgit clone --depth 1 https://github.com/yuvalsuede/memory-mcpWrote 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/instructions/yuvalsuede/memory-mcp/claude-md)<a href="https://agentmods.dev/instructions/yuvalsuede/memory-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/yuvalsuede/memory-mcp/claude-md.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 | $0.00866 | $0.00866 |
| Opus 5 | $0.00433 | $0.00433 |
| Sonnet 5 | $0.00173 | $0.00173 |
| Haiku 4.5 | $0.00087 | $0.00087 |
Grade A, and why
memory-mcp CLAUDE.md 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 5d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
memory-mcp
Last updated: 2026-01-27 | 28 active memories, 28 total
Architecture
- Memory system needs two modes: instant session recovery and mid-session deep context recall for large projects [memory-design, context-management]
- Two-tier memory system with CLAUDE.md (top 150 lines) and
.memory/state.json(unlimited storage) for project contex... [memory, architecture] - Renamed npm package from
memory-mcptoclaude-memory-mcp[packaging, branding] - Official MCP registry publisher requires manual cloning and building from GitHub source repository, not a standard np... [deployment, mcp-registry]
Key Decisions
- Project memory must be scalable beyond typical 2-5K token context window limits [scaling, context-management]
- Created a CLI tool for memory-mcp with commands like setup, init, status, search, ask, consolidate, and key management [cli, tooling]
- Memory extractor modified to handle new transcript format with nested message content and tool interactions within as... [memory-mcp, architecture]
- Corrected Anthropic Claude model ID from
claude-haiku-4-20250414toclaude-3-5-haiku-20241022[llm, configuration] - Prepared documentation including README.md, ARCHITECTURE.md, LICENSE, CHANGELOG.md for project release [documentation, release-prep]
- Renamed npm package from
claude-memory-mcptoclaude-code-memoryafter verifying availability and selecting the m... [npm, packaging] - Resolved MCP SDK compatibility by switching back to zod v4 after initially attempting zod v3 [dependency, typescript]
- Proposed version bump to 1.0.1 to distribute clean build with zod v4 to npm users [versioning, npm]
- Bumped package version to 1.0.2 to support MCP registry validation requirements [versioning, deployment]
- Identified two separate publish workflows: one for Smithery using
npx @smithery/cli deployand another for official... [deployment, registry]
Gotchas & Pitfalls
- Transcript parsing originally failed due to mismatched entry types: expected 'human/user' but actual format uses 'use... [memory-mcp, parsing]
- MCP server communication fails due to zod version incompatibility between zod v3 and v4, causing JSON parsing errors ... [dependency, typescript]
- Zod v3 causes infinite type recursion with MCP SDK's
server.tool(), requiring a downgrade to zod v4 [typescript, dependency, sdk] - Smithery CLI deploy fails for stdio-based local servers, which cannot be published through their current web UI desig... [deployment, registry]
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.
- 5d ago First seen · 44 lines · 866 tokens per session scan A 52716eb90686
memory-mcp CLAUDE.md is an instructions file published in the GitHub repository yuvalsuede/memory-mcp (98 stars, last pushed 7mo ago), licensed MIT. It adds 866 tokens to every session, about $0.0043 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 2026-08-30.
Other instructions, from other repositories
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
cognirepo CLAUDE.md
Claude Code instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).
wayland-core copilot-instructions.md
Copilot instructions for FerroxLabs/wayland-core, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.
mcp-structured-memory CLAUDE.md
Claude Code instructions for nmeierpolys/mcp-structured-memory, a project described as: Structured Memory MCP Server.
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
RNR-Enhanced-Cognee AGENTS.md
AGENTS.md instructions for vincentspereira/RNR-Enhanced-Cognee, covering rnr enhanced cognee implementation for codex, critical requirements, 1. ascii-only output (no unicode encoding), 2. dynamic categories (no hardcoded categories) and 3. standard memory mcp interface.