githubwrapped AGENTS.md

A project instruction file for GitHubwrapped, a Motia application that builds event-driven backend systems.

In plain words
What is it for?
It helps develop HTTP endpoints, background event handlers, scheduled tasks, real-time streams, state management, and Motia workflow features with the local development server.
Why use it?
It gives AI coding tools the commands and project-specific rules needed to install dependencies, run the app, and follow its documented patterns.

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/crypticsaiyan/githubwrapped/agents-md
Clone the repo
git clone --depth 1 https://github.com/crypticsaiyan/githubwrapped

Made for: Codex, OpenCode.

Per session 1,966 This file is loaded in full into every session.
When invoked 1,966 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 $0.01966 $0.01966
Opus 5 $0.00983 $0.00983
Sonnet 5 $0.00393 $0.00393
Haiku 4.5 $0.00197 $0.00197

Measured yesterday against content hash b8e9a8b17858, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

githubwrapped 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 yesterday.

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 · 231 lines

How it starts

The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

AI Development Guide for Motia Projects

This file provides context and instructions for AI coding assistants working on Motia projects.

Project Overview

This is a Motia application - a framework for building event-driven, type-safe backend systems with:

  • HTTP API endpoints (API Steps)
  • Background event processing (Event Steps)
  • Scheduled tasks (Cron Steps)
  • Real-time streaming capabilities
  • Built-in state management
  • Visual workflow designer (Workbench)

Quick Start Commands

# Install dependencies
npm install

# Start development server (with hot reload)
npm run dev

# Start production server (without hot reload)
npm run start

# Generate TypeScript types from steps
npx motia generate-types

📚 Comprehensive Guides

This project includes detailed Cursor rules in .cursor/rules/ that contain comprehensive patterns and examples.

These guides are written in markdown and can be read by any AI coding tool. The sections below provide quick reference, but always consult the detailed guides in .cursor/ for complete patterns and examples.

Available Guides

Read these files in .cursor/rules/motia/ for detailed patterns:

  • motia-config.mdc - Essential project setup, package.json requirements, plugin naming
  • api-steps.mdc - Creating HTTP endpoints with schemas, validation, and middleware
  • event-steps.mdc - Background task processing and event-driven workflows
  • cron-steps.mdc - Scheduled tasks with cron expressions
  • state-management.mdc - State/cache management across steps
  • middlewares.mdc - Request/response middleware patterns
  • realtime-streaming.mdc - WebSocket and SSE patterns
  • virtual-steps.mdc - Visual flow connections in Workbench
  • ui-steps.mdc - Custom visual components for Workbench

Architecture guides in .cursor/architecture/:

  • architecture.mdc - Project structure, naming conventions, DDD patterns
  • error-handling.mdc - Error handling best practices

Read the full file on GitHub · 231 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. yesterday First seen · 231 lines · 1,966 tokens per session scan A b8e9a8b17858

Subscribe to this mod's changes

githubwrapped AGENTS.md is an instructions file published in the GitHub repository crypticsaiyan/githubwrapped (5 stars, last pushed 8mo ago), licensed MIT. It adds 1,966 tokens to every session, about $0.0098 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 2026-08-31.