claude-obsidian GEMINI.md

Host instructions for Gemini CLI when working with claude-obsidian, a toolkit for building source-cited Obsidian knowledge bases. They define which files to read, how to find the user's vault, and how changes are handled safely.

In plain words
What is it for?
Use them when configuring Gemini CLI for claude-obsidian, locating the correct Obsidian vault, reading its skills, or preparing approved knowledge-base changes.
Why use it?
They prevent the agent from confusing the product's source code with a user's notes or making unapproved shared changes. They also provide setup commands for Gemini.

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/agricidaniel/claude-obsidian/gemini-md
Clone the repo
git clone --depth 1 https://github.com/AgriciDaniel/claude-obsidian

Made for: Gemini CLI.

Per session 219 This file is loaded in full into every session.
When invoked 219 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 $0.00219 $0.00219
Opus 5 $0.00110 $0.00110
Sonnet 5 $0.00044 $0.00044
Haiku 4.5 $0.00022 $0.00022

Measured yesterday against content hash 267b205d74e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-obsidian 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 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.

GEMINI.md · 25 lines

What it actually says

claude-obsidian: Gemini instructions

Read AGENTS.md as the canonical host-neutral contract. Skills live in skills/<name>/SKILL.md and the portable core lives in claude_obsidian/.

Install skill discovery with:

bash bin/setup-multi-agent.sh --host gemini
bash bin/setup-multi-agent.sh --host gemini --apply

The first command previews the links; the second applies that reviewed scope.

This repository is product source, not the default user vault. Create a separate vault with the dry-run-first init command or adopt an existing vault. Resolve that vault before reading wiki/hot.md or running a skill.

All shared mutations use one inspected claude-obsidian.transaction.v1 bundle. Parallel workers draft only. Do not use direct shared writes, automatic commits, or the deprecated per-file lock helper. Remote egress and destructive actions need explicit user consent.

Public canonical: https://github.com/AgriciDaniel/claude-obsidian

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 · 25 lines · 219 tokens per session scan A 267b205d74e9

Subscribe to this mod's changes

claude-obsidian GEMINI.md is an instructions file published in the GitHub repository AgriciDaniel/claude-obsidian (14,464 stars, last pushed 6d ago), licensed MIT. It adds 219 tokens to every session, about $0.0011 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.

Related

Other instructions, from other repositories

claude-canvas CLAUDE.md

Instructions for AgriciDaniel/claude-canvas, covering claude-canvas — ai-orchestrated visual production, what it does, directory structure, quick commands and canvas location.

AgriciDaniel/claude-canvas · 481 tokens

llm-brain CLAUDE.md

Instructions for kimsanguine/llm-brain, covering llm-brain — claude code 운영 지침, 가드레일 (절대 위반 금지), 프라이버시 경계 (agent memory os), 명령어 and ingest.

kimsanguine/llm-brain · 3,289 tokens

second-brain-starter-kit AGENTS.md

AGENTS.md instructions for tonydzi/second-brain-starter-kit, covering agents.md — working in this repo, what this repo is, layout, how to verify a change and conventions.

tonydzi/second-brain-starter-kit · 1,104 tokens

commonplace CLAUDE.md

Instructions for briannaworkman/commonplace: This repository holds two vaults. Nothing should be ingested or edited here at the root.

briannaworkman/commonplace · 192 tokens

cmds-llm-wiki AGENTS.md

Schema and harness document for the CMDS LLM Wiki vault. Defines the 3-layer architecture (Raw Sources / Wiki / Schema), ingest-query-lint operations, file conventions, and frontmatter standards. This is the single source of truth for LLM behavior in this vault.

johnfkoo951/cmds-llm-wiki · 14,302 tokens

cmds-llm-wiki CLAUDE.md

Schema and harness document for the CMDS LLM Wiki vault. Defines the 3-layer architecture (Raw Sources / Wiki / Schema), ingest-query-lint operations, file conventions, and frontmatter standards. This is the single source of truth for LLM behavior in this vault.

johnfkoo951/cmds-llm-wiki · 13,893 tokens