agentmods.dev

ezrag: Instructions file for Codex

AGENTS.md

ezrag AGENTS.md is an instructions file for Codex, OpenCode from benbjurstrom/ezrag. It costs 6,960 tokens per session, scanned A, original, 0BSD.

Repository instructions for EzRAG, an Obsidian plugin that adds semantic search using Google Gemini. Semantic search finds content by meaning rather than only matching exact words.

In plain words
What is it for?
Use them when changing EzRAG’s indexing, file processing, queues, connection handling, or Gemini integration.
Why use it?
They give newcomers the project map, key design concepts, and commands for developing and testing the plugin.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is benbjurstrom/ezrag's own configuration. It tells Codex and OpenCode how to work on ezrag itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ezrag configures →

not rated 19repo 10mo ago A scan 6,960 tokens original 0BSD
View source ↗ benbjurstrom/ezrag
Reuse

Borrowing it

Nothing to install: this file belongs to benbjurstrom/ezrag. 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/benbjurstrom/ezrag/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/benbjurstrom/ezrag

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.

agentmods badge for ezrag AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/benbjurstrom/ezrag/agents-md/github.svg)](https://agentmods.dev/instructions/benbjurstrom/ezrag/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/benbjurstrom/ezrag/agents-md"><img src="https://agentmods.dev/badge/instructions/benbjurstrom/ezrag/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.

agentmods 80×15 button for ezrag AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/benbjurstrom/ezrag/agents-md"><img src="https://agentmods.dev/badge/instructions/benbjurstrom/ezrag/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 6,960 This file is loaded in full into every session.
When invoked 6,960 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.06960 $0.06960
Opus 5.5 $0.02784 $0.02784
Sonnet 5.5 $0.01392 $0.01392
Haiku 4.5 $0.00696 $0.00696

Measured 2mo ago against content hash 23256c03e656, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ezrag 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 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.

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 · 718 lines

How it starts

The opening of the file, as written. The whole thing — 718 lines — stays where its author put it; the contents beside it link to each section on GitHub.

EzRAG - Obsidian Plugin for Semantic Search via Google Gemini

Quick Start for Developers

New to this codebase? Start here:

  1. Read this file for high-level overview and module guide

  2. Read ARCHITECTURE.md for detailed design, data models, and implementation notes

  3. Key entry points:

    • main.ts - Plugin lifecycle (start here to understand initialization)
    • src/lifecycle/indexingLifecycleCoordinator.ts - Centralized runner/connection gating & store provisioning
    • src/indexing/indexingController.ts - Indexing lifecycle management
    • src/indexing/indexManager.ts - Core indexing logic
    • src/indexing/filePreparationService.ts / documentMetadata.ts / documentReplacer.ts - Shared file ingestion helpers
    • src/indexing/persistentQueue.ts - Queue orchestration, retries, and connection-aware scheduling
    • src/gemini/geminiService.ts - Gemini API integration

  4. Build and test:

    npm install
npm run dev  # Watch mode for development

  5. Critical concepts to understand:

    • Runner pattern: Only one machine indexes per vault
    • Hot path optimization: No remote checks during file changes
    • Queue persistence: Uploads survive restarts
    • Smart reconciliation: Rebuild doesn't create duplicates

What is EzRAG?

EzRAG is an Obsidian plugin that indexes your notes into Google Gemini's File Search API, enabling semantic search and AI-powered chat over your vault. Key features:

  1. Automatic Indexing: Continuously syncs selected notes to Gemini as you edit
  2. Smart Change Detection: Uses content hashing to avoid redundant uploads
  3. Multi-Device Support: "Runner" pattern designates one machine to handle indexing
  4. Chat Interface: Query your notes using natural language
  5. MCP Server (planned): External tools can query your vault via Model Context Protocol

How It Works

The Runner Pattern (Critical Concept)

In multi-device setups (laptop + desktop), only one machine (the "runner") handles indexing:

Read the full file on GitHub · 718 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. 2mo ago First seen · 718 lines · 6,960 tokens per session scan A 23256c03e656

Subscribe to this mod's changes

ezrag AGENTS.md is an instructions file published in the GitHub repository benbjurstrom/ezrag (19 stars, last pushed 10mo ago), licensed 0BSD. It adds 6,960 tokens to every session, about $0.0278 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.

Data and AIRAG and vectors
Related

ezrag AGENTS.md compared with instructions from other repositories

ezrag AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ezrag AGENTS.mdbenbjurstrom/ezragInstructions file1910mo ago0BSDA6,960Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode