What is obsidian-claude-ide AGENTS.md?

A project guide for developing an Obsidian plugin, including its commands, environment settings, development workflow, debugging tools, and architecture. Obsidian is a note-taking app that supports plugins.

Use it to build, test, install, and debug the plugin, including its connection to Claude Code.

It keeps development steps and project-specific details in one place, so common tasks and debugging instructions are easier to follow.

How petersolopov/obsidian-claude-ide configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to petersolopov/obsidian-claude-ide. 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/petersolopov/obsidian-claude-ide/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/petersolopov/obsidian-claude-ide

Made for: Codex, OpenCode.

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/petersolopov/obsidian-claude-ide/agents-md/github.svg)](https://agentmods.dev/instructions/petersolopov/obsidian-claude-ide/agents-md)

Your own site

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

Per session 1,978 This file is loaded in full into every session.

When invoked 1,978 The same file — it is already loaded in full.

Security scan A 0 findings. 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	$0.01978	$0.01978
Opus 5.5	$0.00791	$0.00791
Sonnet 5.5	$0.00396	$0.00396
Haiku 4.5	$0.00198	$0.00198

Measured 28d ago against content hash b464e49319e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

obsidian-claude-ide AGENTS.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 28d 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.

AGENTS.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

commands

npm run dev — watch mode, rebuilds on changes
npm run build — debug build
npm test — run unit/integration tests
npm run typecheck — TypeScript type check, run before committing
npm run obsidian:install-plugin — copy main.js and manifest.json to vault, reload plugin. Requires .env with OBSIDIAN_VAULT

environment

.env (gitignored, create manually):

OBSIDIAN_VAULT="path/to/your-vault"
OBSIDIAN_VAULT_NAME="vault-name"
OBSIDIAN_TEST_VAULT="path/to/your-test-vault"

OBSIDIAN_VAULT — vault where the plugin is installed for development
OBSIDIAN_VAULT_NAME — optional Obsidian CLI vault name, defaults to the basename of OBSIDIAN_VAULT
OBSIDIAN_TEST_VAULT — vault used for Community Plugin install/update testing

dev workflow

esbuild outputs main.js to the project root.

npm run build && npm run obsidian:install-plugin

debugging

obsidian dev:console
obsidian dev:errors

No need to ask the user to open DevTools or restart Obsidian.

architecture

Obsidian plugin that acts as an MCP server over WebSocket. Claude Code discovers the plugin via lock files in ~/.claude/ide/ and connects to exchange RPC messages (initialize, tools/list, tools/call). The plugin exposes Obsidian-specific tools: selection, open editors, workspace folders, file opening. esbuild bundles everything into a single main.js for Obsidian to load.

naming

Plugin name: Claude Code IDE, ID: claude-code-ide. Renamed from "Obsidian IDE" because community plugin review prohibits "Obsidian" in name, description, and ID. README header uses "Obsidian as IDE for Claude Code" for clarity. ID uses "claude-code-ide" because community plugins prohibit "obsidian-" prefix. In Claude Code /ide selector, "Obsidian" appears as the IDE — configured via ideName in the lock file.

regression

Requires a second Claude Code session from the vault directory, connected via /ide.

An agent can run these checks while the owner watches: it drives Obsidian through obsidian vault=<test vault> eval (open the note, set the selection, switch tabs; never a vault with real notes), starts claude --ide from the test vault directory in a terminal the owner can see, a tmux pane for example, and reads the ⧉ indicator there; the connection checks need no prompt to the model. Installing a build reloads the plugin and drops every connected session, so say so before each install.

Read the full file on GitHub · 191 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.

28d ago Changed · +21 lines · +383 tokens per session b464e49319e7
2mo ago First seen · 170 lines · 1,595 tokens per session scan A 862b565bd2da

Subscribe to this mod's changes

obsidian-claude-ide AGENTS.md is an instructions file published in the GitHub repository petersolopov/obsidian-claude-ide (103 stars, last pushed 28d ago), licensed MIT. It adds 1,978 tokens to every session, about $0.0079 per session on Opus 5.5. 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.

obsidian-claude-ide AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
obsidian-claude-ide AGENTS.mdpetersolopov/obsidian-claude-ide	Instructions file	103	28d ago	MIT	A	1,978	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	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	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

obsidian-claude-ide: Instructions file for Codex