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 mem0ai/mem0npx agentmods add plugins/mem0ai/mem0/claude-code-plugingit clone --depth 1 https://github.com/mem0ai/mem0Grade A, and why
mem0 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 today.
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": "mem0",
"version": "0.3.0",
"description": "Cross-session memory and token savings for coding agents.",
"author": {
"name": "Mem0"
},
"homepage": "https://docs.mem0.ai/integrations/claude-code",
"repository": "https://github.com/mem0ai/mem0",
"license": "Apache-2.0",
"keywords": ["memory", "coding-agents", "continual-learning", "token-efficiency"],
"userConfig": {
"api_key": {
"type": "string",
"title": "Mem0 API Key",
"description": "Mem0 Platform API key used to create and search memories.",
"sensitive": true,
"required": true
},
"user_id": {
"type": "string",
"title": "Memory user ID",
"description": "Optional stable ID shared across machines. When omitted, Mem0 uses your local account name, matching the earlier Mem0 Claude Code plugin.",
"required": false
},
"top_k": {
"type": "number",
"title": "Manual search results",
"description": "Maximum number of memories returned when Claude runs another search after the automatic first search.",
"default": 3,
"min": 1,
"max": 20,
"required": false
},
"max_context_chars": {
"type": "number",
"title": "Maximum retrieved context",
"description": "Maximum number of memory characters returned for one search.",
"default": 4000,
"min": 1000,
"max": 10000,
"required": false
},
"search_scope": {
"type": "string",
"title": "Default search scope",
"description": "How wide every search runs by default. 'repo' is the whole repository's shared memory plus your own preferences, 'dir' narrows the shared memory to the directory you are working in, and 'mine' is your preferences alone.",
"default": "repo",
"required": false
}
}
}
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.
- today First seen · 53 lines scan A d3569732bf7c
mem0 is a plugin published in the GitHub repository mem0ai/mem0 (64,535 stars, last pushed yesterday), 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 2026-09-02.
Other plugins, from other repositories
mathtype-for-word
Create and validate native MathType equations in Word and PowerPoint, including Word-native equation numbers and references.
multai
MultAI — Submit research prompts to 7 AI platforms simultaneously (Claude.ai, ChatGPT, Copilot, Perplexity, Grok, DeepSeek, Gemini), synthesize results, maintain capability comparison matrices, and produce landscape reports — all from Claude Code.
claude-ltm
Long-term memory for Claude Code — persist project decisions across sessions.
eterdis-strategy-skills marketplace
Plugin marketplace listing 11 plugins: eterdis-strategy-diagnostic, eterdis-strategy-map, eterdis-vrio, eterdis-environmental-radar, eterdis-market-position.
eterdis-environmental-radar
Continuous PESTEL environmental scanning across six categories. Three modes: full scan, monthly review, alert triggers.
eterdis-market-position
Competitive positioning diagnostic — figure out where you actually stand and whether that position is defensible.