opencode-obsidian AGENTS.md

Project-specific instructions for coding agents working on an Obsidian plugin that embeds the OpenCode assistant in a sidebar.

In plain words
What is it for?
Use them when modifying the plugin, its TypeScript code, sidebar view, settings, or local server process.
Why use it?
They explain the project layout, required tools, build command, and naming rules so changes fit the existing codebase.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/mtymek/opencode-obsidian/agents-md
Clone the repo
git clone --depth 1 https://github.com/mtymek/opencode-obsidian

Made for: Codex, OpenCode.

Per session 752 This file is loaded in full into every session.
When invoked 752 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00752 $0.00752
Opus 5 $0.00376 $0.00376
Sonnet 5 $0.00150 $0.00150
Haiku 4.5 $0.00075 $0.00075

Measured 2d ago against content hash ea1369441547, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

opencode-obsidian AGENTS.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 2d 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.

- `child_process.spawn()` for server process
AGENTS.md · 93 lines

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.

AGENTS.md - Obsidian OpenCode Plugin

Guidelines for AI coding agents working on the obsidian-opencode plugin.

Project Overview

Obsidian plugin that embeds the OpenCode AI assistant via an iframe. Spawns a local server process and displays its web UI in the Obsidian sidebar.

Tech Stack: TypeScript, Obsidian Plugin API, esbuild, Node.js child processes

Build Commands

bun install          # Install dependencies
bun run build        # Production (type-check + bundle)

Output: main.js (CommonJS bundle)

Project Structure

src/
├── main.ts           # Plugin entry, extends Plugin
├── types.ts          # Types and constants
├── OpenCodeView.ts   # Sidebar view (ItemView) with iframe
├── ProcessManager.ts # Server process lifecycle
└── SettingsTab.ts    # Settings UI (PluginSettingTab)

Coding guidelines

Naming Conventions

Type Convention Example
Classes PascalCase OpenCodePlugin, ProcessManager
Interfaces/Types PascalCase OpenCodeSettings, ProcessState
Constants UPPER_CASE or camelCase DEFAULT_SETTINGS, OPENCODE_VIEW_TYPE
Variables/functions camelCase getVaultPath, startServer
Private members camelCase (no prefix) private processManager
Files PascalCase (classes), lowercase (entry) ProcessManager.ts, main.ts

TypeScript Patterns

  • strictNullChecks enabled - handle null/undefined
  • Union types for state: "stopped" | "starting" | "running" | "error"
  • async/await over Promises
  • Explicit return types on public methods
getProcessState(): ProcessState {
  return this.processManager?.getState() ?? "stopped";
}

Obsidian API Patterns

  • Extend Plugin with onload()/onunload() lifecycle
  • Extend ItemView for views: getViewType(), onOpen(), onClose()
  • Extend PluginSettingTab for settings: display()
  • DOM helpers: createEl(), createDiv(), setIcon()
  • Register in onload(), clean up in onunload()

Read the full file on GitHub · 93 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.

  1. 2d ago First seen · 93 lines · 752 tokens per session scan A ea1369441547

Subscribe to this mod's changes

opencode-obsidian AGENTS.md is an instructions file published in the GitHub repository mtymek/opencode-obsidian (1,132 stars, last pushed 4mo ago), licensed MIT. It adds 752 tokens to every session, about $0.0038 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.

Related

Other instructions, from other repositories

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 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

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 · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

next.js 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