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 plugins/alibaizhanov/mengram/marketplace/plugin marketplace add alibaizhanov/mengramgit clone --depth 1 https://github.com/alibaizhanov/mengramGrade A, and why
mengram 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": "mengram",
"owner": {
"name": "Ali Baizhanov",
"email": "[email protected]",
"url": "https://mengram.io"
},
"plugins": [
{
"name": "mengram",
"version": "0.1.4",
"description": "Persistent memory for Claude Code that survives /clear, machine switches, and team handoffs. Hosted memory backend with hybrid retrieval (vector + BM25 + RRF), Ebbinghaus temporal decay, and importance weighting. Same memory available across Claude Code, Cursor, Codex, and ChatGPT.",
"source": {
"source": "git-subdir",
"url": "alibaizhanov/mengram",
"path": "integrations/claude-code-plugin"
},
"author": {
"name": "Ali Baizhanov",
"email": "[email protected]",
"url": "https://mengram.io"
},
"homepage": "https://mengram.io",
"license": "Apache-2.0",
"category": "productivity",
"keywords": [
"memory",
"mcp",
"context",
"cross-device",
"hybrid-retrieval",
"anthropic",
"persistence"
]
}
]
}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 · 37 lines scan A 959f5d7d7f7f
mengram is a plugin published in the GitHub repository alibaizhanov/mengram (190 stars, last pushed 4d 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 2026-08-30.
Other plugins, from other repositories
plugins-weave
Claude Code plugins for making autonomous AI with long term episodic memory.
TelegramSecretary
Telegram Bot API の long-polling を cloud routine 上で常駐させ、認可済みチャットからのメッセージに秘書エージェント(SecretaryRole)が即応する対話チャネル.
VisualExpression
Visual expression system for AI personas with emotion-based face switching. Use at session start to display the expression UI, and switch expressions whenever the emotional state changes during conversation.
ConsiderateCoder
Development methodology plugin: Clean Architecture x TDD x three-tier delegation (communicator / orchestrator / worker) with /plan-sdd, /outsource and /dig commands.
ContextPreloader
Session context preloader - recreates claude.ai Project feature for Claude Code.
EmailingEssay
Autonomous essay writing and emailing from your AI.