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.
/plugin marketplace add memseekai/memseeknpx agentmods add plugins/memseekai/memseek/claude-codegit clone --depth 1 https://github.com/memseekai/memseekGrade A, and why
memseek-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.
What it actually says
{
"name": "memseek-memory",
"version": "0.2.0",
"description": "Durable, provenance-aware project memory for Claude Code.",
"author": {
"name": "Memseek"
},
"homepage": "https://github.com/memseekai/memseek",
"repository": "https://github.com/memseekai/memseek",
"userConfig": {
"MEMSEEK_URL": {
"type": "string",
"title": "Memseek service URL",
"description": "Base URL supplied by your Memseek administrator, without a trailing slash (for example, https://memory.example.com).",
"required": true,
"default": "http://127.0.0.1:8000"
},
"MEMSEEK_API_KEY": {
"type": "string",
"title": "Memseek workspace key",
"description": "Workspace key supplied by your Memseek administrator. Claude Code stores this as a sensitive value.",
"sensitive": true,
"required": true
},
"MEMSEEK_CAPTURE_MODE": {
"type": "string",
"title": "Conversation capture",
"description": "Controls new writes, not recall. conversation saves exact user and assistant chat messages automatically; explicit saves only when you ask Claude to remember; off tells Claude to make no new writes. Existing memory remains readable in every mode.",
"required": true,
"default": "conversation"
}
},
"keywords": [
"memory",
"context",
"mcp",
"claude-code"
]
}
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 First seen · 40 lines scan A 7c184e6567ad
memseek-memory is a plugin published in the GitHub repository memseekai/memseek (7 stars, last pushed 7d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
claude-code
Persistent semantic memory for Claude Code — user preferences, project context, prior decisions, and codebase facts that survive across sessions.
atomicmemory
Plugin marketplace listing 1 plugin: claude-code.
iai-pme
The personal memory engine for AI coding assistants — local, encrypted, verbatim.
iai-memory
Persistent local memory for your assistant: every turn captured verbatim, relevant memory injected at session start and before each turn, and fifteen memory tools over MCP. Requires the iai-pme package (pip install iai-pme).
emulo
Emulo: mine your local AI coding session logs into a personal profile your agent loads before every task.
emulo
Mine real AI coding sessions into a bounded, evidence-backed personal layer.