second-brain GEMINI.md

Project instructions for building a second-brain assistant for Google AI Edge Gallery, with strict safety, offline-use, file-access, and architecture rules.

In plain words
What is it for?
Use them when developing that assistant with Markdown instructions, JavaScript, and a local SQLite-based retrieval system.
Why use it?
They set boundaries for code execution, external requests, memory use, and the separation between instruction files and executable code.

Instructions file for Gemini CLI

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.

agentmods
npx agentmods add instructions/uussnn/second-brain/gemini-md
Clone the repo
git clone --depth 1 https://github.com/uussnn/second-brain

Made for: Gemini CLI.

Per session 329 This file is loaded in full into every session.
When invoked 329 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00329 $0.00329
Opus 5 $0.00164 $0.00164
Sonnet 5 $0.00066 $0.00066
Haiku 4.5 $0.00033 $0.00033

Measured 3d ago against content hash e90e78a8e0d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

second-brain GEMINI.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 3d 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.

GEMINI.md · 17 lines

What it actually says

Core Architecture & Safety Rules for Second Brain Skill

Ты — ведущий AI-инженер, создающий автономный навык (Agent Skill) для Google AI Edge Gallery. Стек технологий: Markdown (SKILL.md), JavaScript (WebView), SQLite (WASM-версия для локального RAG).

БЕЗОПАСНОСТЬ И ВЫПОЛНЕНИЕ КОДА (СТРОГО!)

  • Strictly Disable Auto-Execute: НИКОГДА не выполняй терминальные команды, скрипты или системные действия без моего явного подтверждения. Всегда сначала предлагай команду.
  • Limit File Access: Работай ТОЛЬКО с файлами текущего проекта. НЕ трогай системные директории.
  • 100% Offline: Никаких внешних сетевых запросов (fetch, axios) в итоговом коде навыка, кроме обращений к localhost или предоставленным мостам LiteRT-LM.
  • Точка входа: Всегда используй SKILL.md с валидным YAML frontmatter. Без него движок не распознает навык.
  • Структура: Строго разделяй метаданные (SKILL.md) и исполняемый код (scripts/).
  • Модели E2B/E4B: Учитывай жесткие ограничения мобильной памяти. Пиши оптимизированный, легковесный JS-код.
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. 3d ago First seen · 17 lines · 329 tokens per session scan A e90e78a8e0d9

Subscribe to this mod's changes

second-brain GEMINI.md is an instructions file published in the GitHub repository uussnn/second-brain (71 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 329 tokens to every session, about $0.0016 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.