qurt AGENTS.md

qurt AGENTS.md is an instructions file for Codex, OpenCode from qurtai/qurt. It costs 476 tokens per session, scanned A, original, MIT.

Project instructions for qurt, a desktop AI assistant built with Electron, Vite, React, and TypeScript.

In plain words
What is it for?
Guiding changes, builds, and tests in the qurt project, including work involving providers, models, files, and agent tools.
Why use it?
They give an agent the project context, design goals, and development commands needed to work consistently in the 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/qurtai/qurt/agents-md
Clone the repo
git clone --depth 1 https://github.com/qurtai/qurt

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 qurt AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/qurtai/qurt/agents-md.svg)](https://agentmods.dev/instructions/qurtai/qurt/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/qurtai/qurt/agents-md"><img src="https://agentmods.dev/badge/instructions/qurtai/qurt/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 476 This file is loaded in full into every session.
When invoked 476 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.00476 $0.00476
Opus 5 $0.00238 $0.00238
Sonnet 5 $0.00095 $0.00095
Haiku 4.5 $0.00048 $0.00048

Measured 3d ago against content hash d23299798a39, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qurt 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 3d 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 · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Project Overview

qurt is an AI Coworker and assistant designed for provider freedom:

  • users bring their own API keys
  • users choose their preferred provider/model
  • the product avoids locking users into a single vendor
  • the long-term goal is fair, practical access to the strongest model or agent for a task
  • give users world-class agentic tool that is capable of doing real-value tasks

Current status:

  • desktop app only (Electron + Vite + React + TypeScript)
  • users can chat with AI and attach files/images for discussion
  • users can configure API keys and enabled models by provider
  • agents can use tools such as terminal, file change, browser control and web access to solve some users requests (it's like Cursor but outside of code)

Product Design Intent

  • make advanced AI usage feel simple for non-experts
  • preserve user control while introducing smarter assistant behaviors
  • help users compare and choose providers/models without bias
  • Allow agents to automate user's needs minimising risks to user's data

Build and Test

When working on tasks use these commands constantly

Build

  • Install dependencies: npm install
  • Start development app: npm run dev
  • Build app: npm run build (Use less, time consuming, tend to use at the end of the task)
  • Lint code: npm run lint

Test

  • Run tests: npm run test (or npm run test:coverage for coverage).
  • Keep lint clean on touched files before finishing work.

Workflow

  • Always create a branch for major changes
  • Use Conventional Commits for commit messages (see Commit Message Convention below).
  • Make sure new code is always tested

UI And Typography

  • Use Radix-based primitives from src/renderer/shared/components/ui/ for new controls.
  • prefer path aliases (@/...) over long relative imports
  • keep reusable parts in src/renderer/shared/components/

Content Tone Rules

  • FAQ and Updates copy must be user-facing and non-technical.
  • Do not mention internal implementation details (for example: file paths, stores, frameworks, or architecture moves).
  • Keep wording focused on user value, product behavior, and outcomes.

Read the full file on GitHub · 57 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. 3d ago First seen · 57 lines · 476 tokens per session scan A d23299798a39

Subscribe to this mod's changes

qurt AGENTS.md is an instructions file published in the GitHub repository qurtai/qurt (11 stars, last pushed 6mo ago), licensed MIT. It adds 476 tokens to every session, about $0.0024 per session on Opus 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.