What is obsidian-ai CLAUDE.md?

Project instructions for Agentic Copilot, an Obsidian plugin that connects command-line AI tools to an Obsidian workspace. Obsidian is a desktop note-taking app that stores notes in a local folder called a vault.

Use them when developing Agentic Copilot, running its build or lint commands, testing it in an Obsidian vault, bumping versions, or preparing a release.

They explain how to build, check, develop, and release the plugin, including its desktop-only requirement and its confirmation flow for file edits.

How spencermarx/obsidian-ai configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to spencermarx/obsidian-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/spencermarx/obsidian-ai/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/spencermarx/obsidian-ai

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/spencermarx/obsidian-ai/claude-md/github.svg)](https://agentmods.dev/instructions/spencermarx/obsidian-ai/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/spencermarx/obsidian-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/spencermarx/obsidian-ai/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/spencermarx/obsidian-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/spencermarx/obsidian-ai/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,165 This file is loaded in full into every session.

When invoked 1,165 The same file — it is already loaded in full.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01165	$0.01165
Opus 5	$0.00583	$0.00583
Sonnet 5	$0.00233	$0.00233
Haiku 4.5	$0.00117	$0.00117

Measured 9d ago against content hash b7f0ed4a7a14, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

obsidian-ai CLAUDE.md scanned grade A 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 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

**Agentic Copilot** is an Obsidian plugin that bridges agentic CLI tools (Claude Code, Opencode, Gemini CLI) into Obsidian as a workspace copilot. It provides a chat panel, vault-aware context, slash commands, and file e

CLAUDE.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

Agentic Copilot is an Obsidian plugin that bridges agentic CLI tools (Claude Code, Opencode, Gemini CLI) into Obsidian as a workspace copilot. It provides a chat panel, vault-aware context, slash commands, and file edit diffs with confirmation workflows. Desktop only (requires Node.js child_process).

Build & Development Commands

npm run dev        # Watch mode (esbuild)
npm run build      # TypeScript check + production esbuild bundle
npm run lint       # ESLint (flat config, type-checked)
npm run lint:fix   # Auto-fix fixable issues
npm run version    # Bump version in manifest.json & versions.json

No test framework is configured.

Local development: Symlink the repo into <vault>/.obsidian/plugins/agentic-copilot, run npm run dev, and reload Obsidian (Cmd+R).

Release: Tag a bare version (e.g., 1.0.1) and push. GitHub Actions builds and creates a release with main.js, manifest.json, styles.css.

Architecture

The plugin follows a layered architecture:

Entry point (src/main.ts): Extends Obsidian's Plugin class. Registers the chat view, settings tab, ribbon icon, and all commands. Orchestrates agent detection, adapter resolution, and session lifecycle.

Adapter layer (src/adapters/): Pluggable interface (AgentAdapter) for different CLI tools. Each adapter knows how to detect its binary, build spawn args, and parse its output format. Implementations:

claude-code.ts — Parses --output-format stream-json structured output with content block tracking
opencode.ts — Parses plain text / JSON lines from -p headless mode
generic-cli.ts — Fallback for custom CLI tools; reads all stdout as plain text
detector.ts — Scans system PATH for known binaries, returns prioritized list

Session layer (src/session/): SessionManager spawns child processes via child_process.spawn(), pipes stdout through the adapter's parser, and emits events (message, status, error, complete). MessageQueue buffers streaming text deltas into complete messages, flushing on role/thinking-state transitions.

Read the full file on GitHub · 85 lines

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.

9d ago First seen · 85 lines · 1,165 tokens per session scan A b7f0ed4a7a14

Subscribe to this mod's changes

obsidian-ai CLAUDE.md is an instructions file published in the GitHub repository spencermarx/obsidian-ai (48 stars, last pushed 4mo ago), licensed MIT. It adds 1,165 tokens to every session, about $0.0058 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Code agentic-ai claude claude-ai claude-skills codex

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

obsidian-ai: Instructions file for Claude Code