vault

A voice-first personal assistant that captures thoughts and tasks through Telegram and stores them in Obsidian. It also includes goal tracking and scheduled reminders.

In plain words
What is it for?
Capture thoughts, tasks, and photos through Telegram, transcribe voice entries, track goals, save information in an Obsidian vault, and schedule reminders.
Why use it?
It gives you a way to record information from a messaging app instead of manually organizing it later. Voice capture can turn spoken entries into stored notes when transcription is configured.

Plugin for Claude Code

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.

Claude Code
/plugin marketplace add smixs/agent-second-brain
agentmods
npx agentmods add plugins/smixs/agent-second-brain/vault
Clone the repo
git clone --depth 1 https://github.com/smixs/agent-second-brain

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

vault 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.

vault/.claude-plugin/plugin.json · 31 lines

What it actually says

{
  "name": "d-brain",
  "version": "2.0.0",
  "description": "Voice-first personal assistant for capturing thoughts and tasks via Telegram, with goal tracking and Obsidian integration",
  "author": {
    "name": "[Your Name]",
    "url": "https://github.com/[yourusername]"
  },
  "license": "MIT",
  "capabilities": {
    "agents": true,
    "skills": true,
    "rules": true
  },
  "integrations": {
    "telegram": "Voice/text/photo capture",
    "obsidian": "PKM vault storage",
    "deepgram": "Voice transcription",
    "cron": "Built-in reminder/schedule engine"
  },
  "keywords": [
    "voice-capture",
    "telegram-bot",
    "obsidian",
    "pkm",
    "goals",
    "productivity",
    "personal-assistant"
  ]
}
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. yesterday First seen · 31 lines scan A 82ae60747c34

Subscribe to this mod's changes

vault is a plugin published in the GitHub repository smixs/agent-second-brain (359 stars, last pushed 26d ago), licensed MIT. 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.