What is obsidian-agent CLAUDE.md?

Project instructions for an Obsidian plugin that connects Obsidian, a note-taking application, to AI coding agents using the Agent Client Protocol, a standard way for software to communicate with agents.

Use them when installing, developing, type-checking, building, or changing the plugin's agent view, connection controls, lifecycle, or communication code.

They explain how the plugin starts an external agent, exchanges messages with it, and exposes the connection through Obsidian's user interface.

How WhiskeyJack96/obsidian-agent configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to WhiskeyJack96/obsidian-agent. 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/WhiskeyJack96/obsidian-agent/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/WhiskeyJack96/obsidian-agent

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/whiskeyjack96/obsidian-agent/claude-md/github.svg)](https://agentmods.dev/instructions/whiskeyjack96/obsidian-agent/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/whiskeyjack96/obsidian-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/whiskeyjack96/obsidian-agent/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/whiskeyjack96/obsidian-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/whiskeyjack96/obsidian-agent/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,365 This file is loaded in full into every session.

When invoked 1,365 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	$0.01365	$0.01365
Opus 5.5	$0.00546	$0.00546
Sonnet 5.5	$0.00273	$0.00273
Haiku 4.5	$0.00136	$0.00136

Measured 2mo ago against content hash 30b2b8f2ddf7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

obsidian-agent 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 2mo 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.

- Spawns external agent process using Node's `child_process.spawn`

CLAUDE.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 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.

Overview

This is an Obsidian plugin that implements an Agent Client Protocol (ACP) client, enabling integration with AI coding agents that support the ACP standard. The plugin spawns an external ACP-compatible agent process, communicates with it over JSON-RPC via stdin/stdout, and provides a chat UI within Obsidian.

Commands

Development

# Development build with watch mode
npm run dev

# Production build (includes type checking)
npm run build

# Version bump (used before releases)
npm run version

Installation

npm install

Architecture

Core Components

main.ts - Plugin entry point

Extends Obsidian's Plugin class
Registers the agent view type and ribbon icon
Manages plugin lifecycle (load/unload)
Creates and maintains a singleton ACPClient instance
Provides commands: open view, connect, disconnect

acp-client.ts - ACP protocol implementation

Spawns external agent process using Node's child_process.spawn
Converts Node.js streams to Web Streams for ACP library compatibility
Creates ClientSideConnection from @zed-industries/agent-client-protocol
Implements all required ACP client methods as protocol callbacks
Manages terminal subprocesses spawned by agent requests
Handles vault path resolution for file operations

agent-view.ts - Chat UI component

Extends Obsidian's ItemView to create custom view
Displays streaming agent messages, tool calls, plans, and permission requests
Handles in-place updates for tool calls (shows status badges)
Renders permission requests inline with approve/deny buttons
Auto-scrolls messages container
Manages connection controls and message input

settings.ts / settings-tab.ts - Configuration

Stores agent command path, arguments, and preferences
Provides settings UI in Obsidian settings panel

Communication Flow

User clicks Connect → AgentView.connect()
ACPClient.initialize() spawns agent process, creates Web Streams, initializes connection
ACPClient.createSession() sends newSession request with vault path as cwd
User sends message → ACPClient.sendPrompt() sends prompt request
Agent processes request, may call back to client methods (file ops, terminal, permissions)
Agent sends session updates via sessionUpdate callback
AgentView.handleUpdate() parses update type and renders UI accordingly

Read the full file on GitHub · 149 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.

2mo ago First seen · 149 lines · 1,365 tokens per session scan A 30b2b8f2ddf7

Subscribe to this mod's changes

obsidian-agent CLAUDE.md is an instructions file published in the GitHub repository WhiskeyJack96/obsidian-agent (15 stars, last pushed 11mo ago), licensed MIT. It adds 1,365 tokens to every session, about $0.0055 per session on Opus 5.5. 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.

obsidian-agent CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
obsidian-agent CLAUDE.mdWhiskeyJack96/obsidian-agent	Instructions file	15	11mo ago	MIT	A	1,365	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

obsidian-agent: Instructions file for Claude Code