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/g4brym/email-explorer/agents-mdgit clone --depth 1 https://github.com/G4brym/email-explorerWrote 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/g4brym/email-explorer/agents-md)<a href="https://agentmods.dev/instructions/g4brym/email-explorer/agents-md"><img src="https://agentmods.dev/badge/instructions/g4brym/email-explorer/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 | $0.01153 | $0.01153 |
| Opus 5 | $0.00576 | $0.00576 |
| Sonnet 5 | $0.00231 | $0.00231 |
| Haiku 4.5 | $0.00115 | $0.00115 |
Grade A, and why
email-explorer 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agents
This document outlines the key aspects of the email-explorer project to facilitate understanding and future development.
Project Overview
email-explorer is a full-stack email client built on Cloudflare Workers. It provides a web-based dashboard for managing emails, including sending, receiving, and organizing them into folders. The backend is a Hono-based API that interacts with Cloudflare's email routing, R2 for storage, and Durable Objects for managing individual mailboxes.
Core Technologies
- Backend:
- Framework: Hono - A lightweight, fast web framework for Cloudflare Workers.
- Language: TypeScript
- API Specification: OpenAPI (Swagger) - The API is defined in
openapi.json. - Database: Cloudflare D1 (via
workers-qb) - Used for storing email metadata, folders, and contacts within Durable Objects. - Storage: Cloudflare R2 - Used for storing mailbox settings and email attachments.
- Email Sending: Cloudflare Email Routing - Used for both sending and receiving emails.
- Frontend:
- Framework: Vue.js 3 - A progressive JavaScript framework for building user interfaces.
- Language: TypeScript
- Build Tool: Vite - A fast build tool for modern web development.
- Styling: Tailwind CSS - A utility-first CSS framework.
- State Management: Pinia - A modern state management library for Vue.js.
- Routing: Vue Router - The official router for Vue.js.
- Testing:
- Framework: Vitest - A fast unit testing framework.
- Integration Tests: Cloudflare's
vitest-pool-workersfor integration testing against a real Cloudflare environment.
Project Structure
The project is a monorepo with two main parts: the backend worker and the frontend dashboard.
/(Root):wrangler.jsonc: The configuration file for the Cloudflare Worker. It defines the worker's name, entry point, compatibility flags, and bindings to other Cloudflare services like R2, D1, and Durable Objects.package.json: Defines the project's dependencies and scripts for the backend.tsconfig.json: The TypeScript configuration for the backend.src/: The source code for the Cloudflare Worker.index.ts: The main entry point for the worker. It sets up the Hono router and defines the API endpoints.durableObject/: Contains the implementation of theMailboxDODurable Object.index.ts: TheMailboxDOclass, which manages all data and operations for a single mailbox.migrations.ts: The database schema and migrations for the D1 database used by the Durable Object.
tests/: Contains the integration tests for the API endpoints.
/dashboard:package.json: Defines the dependencies and scripts for the frontend dashboard.vite.config.ts: The configuration for the Vite build tool.src/: The source code for the Vue.js application.main.ts: The entry point for the Vue application.App.vue: The root Vue component.router/: The Vue Router configuration.stores/: The Pinia stores for managing application state.views/: The different pages of the application.components/: Reusable Vue components.services/: The API client for communicating with the backend.
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 · 90 lines · 1,153 tokens per session scan A 3fc2accbd0a3
email-explorer AGENTS.md is an instructions file published in the GitHub repository G4brym/email-explorer (156 stars, last pushed 2mo ago), licensed MIT. It adds 1,153 tokens to every session, about $0.0058 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
tiptap tiptap.instructions.md
Instructions for ueberdosis/tiptap, covering tiptap, what is tiptap, repository layout, npm scripts and linting & formatting.
daisyui packages.docs.instructions.md
Instructions for saadeghi/daisyui, a project described as: 🌼 🌼 🌼 🌼 🌼 The most popular, free and open-source Tailwind CSS component library.
vue-tui AGENTS.md
Instructions for vuejs-ai/vue-tui, covering common pitfalls & best practices, project context records (pcr), using vite+, the unified toolchain for the web and review checklist.
mulmoterminal CLAUDE.md
Instructions for receptron/mulmoterminal, covering claude.md — mulmoterminal, stack & package manager, run after changes, import a component at module scope, never inside a test and no emojis.
elysia-admin AGENTS.md
Instructions for meishanlaoyao/elysia-admin, covering elysia admin — codex global rules, dependency direction (strict), generation principles, module dev triggers and file reading discipline (token budget).
LocalSite-ai AGENTS.md
Instructions for weise25/LocalSite-ai, covering available svelte mcp tools, 1. list-sections, 2. get-documentation, 3. svelte-autofixer and 4. playground-link.