obsidian-second-brain turns an Obsidian vault into persistent, searchable memory for Claude Code and other command-line coding agents, storing knowledge as linked Markdown notes. It is for developers, founders, writers, and researchers who want agents to retain project context across sessions. Its catalogue entries provide commands, hooks, a plugin, a skill, and instructions for capturing, finding, and maintaining that memory.
Borrowing it
Nothing to install: this file belongs to eugeniughelbur/obsidian-second-brain. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/eugeniughelbur/obsidian-second-brain/main/CLAUDE.mdgit clone --depth 1 https://github.com/eugeniughelbur/obsidian-second-brainWrote 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/eugeniughelbur/obsidian-second-brain/claude-md)<a href="https://agentmods.dev/instructions/eugeniughelbur/obsidian-second-brain/claude-md"><img src="https://agentmods.dev/badge/instructions/eugeniughelbur/obsidian-second-brain/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/eugeniughelbur/obsidian-second-brain/claude-md"><img src="https://agentmods.dev/badge/instructions/eugeniughelbur/obsidian-second-brain/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01943 | $0.01943 |
| Opus 5 | $0.00971 | $0.00971 |
| Sonnet 5 | $0.00389 | $0.00389 |
| Haiku 4.5 | $0.00194 | $0.00194 |
Grade A, and why
obsidian-second-brain CLAUDE.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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Operating instructions for Claude Code when working inside this repo.
This is the source repo for obsidian-second-brain, a Claude Code skill that turns any Obsidian vault into a living AI-first second brain. The skill ships 47 slash commands across 4 layers (vault management, thinking tools, research toolkit, scheduled agents).
If you are Claude operating on a user's vault, you want _CLAUDE.md inside their vault, not this file. This file is for working on the skill's source code.
Repo layout
commands/- 47 slash command definitions, one.mdper command. This is the platform-neutral source. Adapters compile it for each platform.references/- shared specs that commands link to.ai-first-rules.mdis the canonical vault-write spec and is non-negotiable.scripts/- Python helpers (bootstrap_vault.py,vault_health.py, theresearch/toolkit), plusbuild.sh(the adapter orchestrator) andlib.sh.adapters/- platform translation layer.lib.shholds shared parsing helpers.claude-code/,codex-cli/,gemini-cli/,opencode/,hermes/,pi/,agent-skills/,grok-bot/each ship anadapter.sh.dist/- build output, one tree per platform. Gitignored. Regenerate withbash scripts/build.sh(all platforms) orbash scripts/build.sh --platform <name>.hooks/- Claude Code hooks shipped with the skill.SKILL.md- full operating manual loaded by Claude when the skill activates.architecture.md- how the layers fit together.README.md- public-facing docs on github.com.pyproject.toml- Python deps managed viauv.install.sh- one-shot installer that symlinks the skill into~/.claude/. (Legacy; for non-Claude platforms seedist/<platform>/INSTALL.mdafter building.)
The adapter pattern
Source files in commands/ use Claude Code's slash-command shape. The Claude Code adapter is an identity copy. The other adapters translate per platform: codex-cli, hermes, agent-skills, and grok-bot emit native skills (one SKILL.md per command; agent-skills is a single spec-compliant .agents/skills/ tree that Codex, OpenCode, and Google Antigravity all read, with a shared obsidian-core engine skill; grok-bot emits Grok Bot / Sand skills that use the user-obsidian-second-brain MCP server for vault I/O), pi emits a Pi package (.pi/prompts/ + .pi/skills/), and gemini-cli / opencode emit a dispatcher file (GEMINI.md / AGENTS.md) with an auto-generated routing table built from each command's description: frontmatter, plus the command bodies under .gemini/ / .opencode/. Tool-name references like Read tool are rewritten to neutral wording (read files) so the instructions still make sense outside Claude Code.
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.
- 9d ago First seen · 93 lines · 1,943 tokens per session scan A 18edd009f6c3
obsidian-second-brain CLAUDE.md is an instructions file published in the GitHub repository eugeniughelbur/obsidian-second-brain (4,364 stars, last pushed 2d ago), licensed MIT. It adds 1,943 tokens to every session, about $0.0097 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.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.