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.
npx agentmods add instructions/johnpapa/shopathome/agents-mdgit clone --depth 1 https://github.com/johnpapa/shopathomeWrote 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.
[](https://agentmods.dev/instructions/johnpapa/shopathome/agents-md)<a href="https://agentmods.dev/instructions/johnpapa/shopathome/agents-md"><img src="https://agentmods.dev/badge/instructions/johnpapa/shopathome/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.02537 | $0.02537 |
| Opus 5 | $0.01269 | $0.01269 |
| Sonnet 5 | $0.00507 | $0.00507 |
| Haiku 4.5 | $0.00254 | $0.00254 |
Grade A, and why
shopathome 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shop at Home — Contributor & Agent Guide
Project Overview
Shop at Home is a full-stack shopping list application that lets customers securely add, edit, view, and remove grocery and household items. The project is designed as a learning resource for Azure Static Web Apps and Azure Container Apps, providing four frontend implementations (Angular, React, Svelte, Vue) backed by two API options (Azure Functions and Fastify).
Live demos: angular.shopathome.dev · react.shopathome.dev · svelte.shopathome.dev · vue.shopathome.dev
Repository Structure
shopathome/
├── angular-app/ # Angular 18 frontend (NgRx state management)
│ ├── src/app/ # Components, services, routing, store
│ └── package.json
├── react-app/ # React 17 frontend (Redux + Redux-Saga)
│ ├── src/ # Components, store, product views
│ └── package.json
├── svelte-app/ # Svelte 4 frontend (Vite build, TypeScript)
│ ├── src/ # Components, store, models
│ └── package.json
├── vue-app/ # Vue 3 frontend (Vuex state management)
│ ├── src/ # Components, views, store, router
│ └── package.json
├── api/ # Azure Functions API (serverless)
│ ├── products-get/ # GET /api/products
│ ├── products-post/ # POST /api/products
│ ├── products-put/ # PUT /api/products
│ ├── products-delete/ # DELETE /api/products
│ ├── discounts-get/ # GET /api/discounts
│ └── shared/ # Shared data layer (in-memory)
├── fastify-api-server/ # Fastify 4 API (containerized)
│ └── src/
│ ├── server.js # Server entry point (port 3000)
│ ├── routes/ # Route handlers (products, discounts)
│ └── shared/ # Shared data layer (in-memory)
├── .devcontainer/ # Dev container config (Svelte + API)
├── .github/workflows/ # Azure Static Web Apps deploy workflows
├── CONTRIBUTING.md # Contribution guidelines
└── README.md # Project overview and deployment guide
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.
- 4d ago First seen · 246 lines · 2,537 tokens per session scan A ee7c8c998b7e
shopathome AGENTS.md is an instructions file published in the GitHub repository johnpapa/shopathome (135 stars, last pushed 1mo ago), licensed MIT. It adds 2,537 tokens to every session, about $0.0127 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.
Other instructions, from other repositories
kolibri copilot-instructions.md
Copilot instructions for public-ui/kolibri, covering github copilot instructions for kolibri repository, kolibri overview, essential setup commands, 1. install node.js 22 and 2. enable pnpm.
kolibri AGENTS.md
AGENTS.md instructions for public-ui/kolibri, covering agent instructions, handling hints, 🚨 format-first rule, semantic versioning and project structure.
webf CLAUDE.md
Claude Code instructions for openwebf/webf, covering webf development guide, 📚 folder-specific guides, 🚀 quick start, repository structure and common commands.
webf AGENTS.md
AGENTS.md instructions for openwebf/webf, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
vue-modal AGENTS.md
Instructions for kolirt/vue-modal, covering @kolirt/vue-modal — guide for ai agents, critical rules (avoid the common mistakes), minimal correct setup, styling, animations & z-index (get this right in one pass) and documentation index.
elements AGENTS.md
AGENTS.md instructions for NVIDIA/elements, covering agents.md, instruction precedence for agents, repository overview, environment requirements and common commands.