Obsidian Mind is an Obsidian vault that stores notes, links, indexes, and other accumulated context so AI coding agents can retain memory across sessions. It is designed for Claude Code and also supports Codex CLI and Gemini CLI through shared hooks, commands, and vault data. Its catalogue add-ons package the vault’s commands, agents, skills, hooks, instructions, settings, plugin, and MCP integration.
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 instructions/breferrari/obsidian-mind/gemini-mdgit clone --depth 1 https://github.com/breferrari/obsidian-mindWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/breferrari/obsidian-mind/gemini-md)<a href="https://agentmods.dev/instructions/breferrari/obsidian-mind/gemini-md"><img src="https://agentmods.dev/badge/instructions/breferrari/obsidian-mind/gemini-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01145 | $0.01145 |
| Opus 5 | $0.00573 | $0.00573 |
| Sonnet 5 | $0.00229 | $0.00229 |
| Haiku 4.5 | $0.00114 | $0.00114 |
Grade B, and why
obsidian-mind GEMINI.md scanned grade B with 1 finding 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 6d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
**Codex CLI**: Reads `AGENTS.md` natively. For direct access to `CLAUDE.md`, add to `~/.codex/config.toml`: This is a copy
100% identical to obsidian-mind AGENTS.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Obsidian Mind
This vault is built for Claude Code with a full operating manual in CLAUDE.md.
Read CLAUDE.md for all vault conventions — structure, note types, linking rules, frontmatter schemas, indexes, and workflows. Most of the content is agent-agnostic.
Hooks
The hook scripts in .claude/scripts/ are agent-agnostic TypeScript and shell, executed natively by Node via --experimental-strip-types — no build step, no runtime dependencies, no Claude SDK. Hook configs are provided for three agents:
| Agent | Config | Status |
|---|---|---|
| Claude Code | .claude/settings.json |
Full support |
| Codex CLI | .codex/hooks.json |
Shared hook scripts |
| Gemini CLI | .gemini/settings.json |
Shared hook scripts |
| Script | Purpose | Claude event | Codex event | Gemini event |
|---|---|---|---|---|
session-start.ts |
Inject vault context at startup | SessionStart | SessionStart | SessionStart |
classify-message.ts |
Classify messages, inject routing hints | UserPromptSubmit | UserPromptSubmit | BeforeAgent |
validate-write.ts |
Validate frontmatter and wikilinks | PostToolUse | PostToolUse | AfterTool |
pre-compact.ts |
Back up transcript before compaction | PreCompact | — | PreCompress |
Commands
Commands live in .claude/commands/ — agent-agnostic markdown with YAML frontmatter. brain/Skills.md is the catalog.
- Claude Code / Gemini CLI: invoke as
/om-standup,/om-dump, etc. - Codex CLI: type the command name as a regular prompt without the
/prefix (e.g.om-standup). Codex will find and execute the command file.
Memory
The vault's memory lives in brain/ — Memories.md, Patterns.md, Key Decisions.md, Gotchas.md. These are plain markdown files that any agent can read and write. When you learn something worth remembering, write it to the relevant brain/ topic note with a wikilink to context.
The ~/.claude/ auto-loaded memory index is Claude Code-specific — skip that section in CLAUDE.md. The vault-side brain/ notes are the source of truth.
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.
- 6d ago First seen · 71 lines · 1,145 tokens per session scan B 68fe756bd39d
obsidian-mind GEMINI.md is an instructions file published in the GitHub repository breferrari/obsidian-mind (4,605 stars, last pushed 3d ago), licensed MIT. It adds 1,145 tokens to every session, about $0.0057 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). It is 100% identical to obsidian-mind AGENTS.md, differing in 0 lines, and is treated as a copy.
Other instructions, from other repositories
obsidian-loop-wiki AGENTS.md
Instructions for uninhibited-scholar/obsidian-loop-wiki, covering agents.md — obsidian-loop-wiki, locate the vault first, node types (keep separated), ingest an article / organize the inbox and verification pass (definition of done).
third-brain-v7-skills CLAUDE.md
Instructions for Mark393295827/third-brain-v7-skills, covering third brain v8.1 skills — claude code, v8.1 multi-domain taxonomy specification, 20 core skills overview, 📥 knowledge pipeline and 🔄 daily loop.
third-brain-v7-skills GEMINI.md
Instructions for Mark393295827/third-brain-v7-skills, covering third brain v8.1 skills — gemini / antigravity cli, 20 core agent skills, 📥 knowledge pipeline, 🔄 daily loop and 🎨 behavior & creativity.
memex-plugin CLAUDE.md
Instructions for linxule/memex-plugin, covering memex - personal knowledge base, quick start, check vault status, search for something (rrf scoring is default) and search recent docs only (7d, 2w, 3m).
onebrain GEMINI.md
Instructions for onebrain-ai/onebrain, covering onebrain — gemini cli, load order, project-level gemini config, tool name mapping and agent instructions.
ariadne AGENTS.md
Instructions for pariyar07/ariadne, covering ariadne — agent instructions, what this repo contains, how skills are structured, routing and rules.