website-email: Instructions file for Codex

AGENTS.md

website-email AGENTS.md is an instructions file for Codex, OpenCode from mifdlaldev/website-email. It costs 2,126 tokens per session, scanned A, original, MIT.

Repository instructions for a self-hosted temporary email and one-time-password service. They describe the project knowledge base, specifications, structure, and important code paths.

In plain words
What is it for?
Use them when changing the website-email project, especially its Next.js app, SQLite database, email intake paths, or specification-driven workflow.
Why use it?
They help coding agents find the source of truth and understand how email ingestion, storage, and the application are organized.

Instructions file for CodexOpenCode

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

This is mifdlaldev/website-email's own configuration. It tells Codex and OpenCode how to work on website-email 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 website-email configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/youngboy/....

Reuse

Borrowing it

Nothing to install: this file belongs to mifdlaldev/website-email. 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/mifdlaldev/website-email/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/mifdlaldev/website-email

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 website-email AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mifdlaldev/website-email/agents-md"><img src="https://agentmods.dev/badge/instructions/mifdlaldev/website-email/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,126 This file is loaded in full into every session.
When invoked 2,126 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.02126 $0.02126
Opus 5.5 $0.00850 $0.00850
Sonnet 5.5 $0.00425 $0.00425
Haiku 4.5 $0.00213 $0.00213

Measured 2mo ago against content hash 70beb7428343, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

website-email AGENTS.md scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Worker smoke: `curl -H "x-api-key: $API_KEY" "$CLOUDFLARE_WORKER_URL/emails/test@domain"`
AGENTS.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PROJECT KNOWLEDGE BASE

Generated: 2026-07-23
Commit: 5999bad (branch master)

OpenSpec Project

This project uses OpenSpec for spec-driven development. Specifications are the source of truth for behavior.

  • Specs: openspec/specs/
  • Changes: openspec/changes/
  • Workflow for AI: openspec/AGENTS.md
  • Commands: /opsx:propose, /opsx:apply, /opsx:archive (or npx openspec ...)

OVERVIEW

Self-hosted receive-only temp email + OTP tools.
App: Next.js 14 (App Router) + local SQLite (better-sqlite3).
Ingest paths (both real): (1) host SMTP → SQLite, (2) Cloudflare Email Routing → Worker D1 → app HTTP pull.

STRUCTURE

website-email/
├── src/
│   ├── app/                 # Next.js UI + REST API routes
│   ├── core/                # entities, MIME parse, OTP extract
│   ├── data/                # SQLite db, migrate, queries
│   ├── infrastructure/
│   │   ├── smtp/            # inbound SMTP (separate process)
│   │   └── mcp/             # MCP stdio server
│   └── shared/              # env (zod), auth helpers, events, dns
├── cloudflare-email-worker/ # separate deployable (wrangler + D1)
├── data/                    # runtime SQLite (emails.db) — not source
├── docs/                    # human docs (index: docs/README.md)
├── openspec/                # specs (behavior source of truth) + changes
├── .env / .env.example
└── docker-compose.yml       # web only; SMTP usually on host

WHERE TO LOOK

Task Location Notes
Env validation src/shared/env.ts Zod; DOMAIN + API_KEY required
Local DB + worker fallback src/data/queries.ts → getEmailsByAddress Local SQLite first; worker only if CLOUDFLARE_WORKER_URL set
REST auth src/shared/api-helpers.ts + src/shared/auth.ts x-api-key = env API_KEY or active api_keys row
Public config src/app/api/config/route.ts { domain } only — never API_KEY
Inbox merge src/shared/email-merge.ts + queries.getEmailsByAddress local ∪ worker by id; local wins
Inbox UI src/components/inbox/* + src/app/page.tsx page orchestrates; components presentational
SMTP receive src/infrastructure/smtp/* Process: npx tsx src/infrastructure/smtp/start.ts
MCP tools src/infrastructure/mcp/* Script: npm run mcp
CF Worker cloudflare-email-worker/src/index.ts email + fetch handlers; D1 EMAIL_DB
Worker deploy config cloudflare-email-worker/wrangler.toml name freelancer-mail, D1 freelancer-mail-db
Fresh deploy script cloudflare-email-worker/deploy-fresh.sh D1 + schema + secret + deploy + patch app .env

Read the full file on GitHub · 158 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 · 158 lines · 2,126 tokens per session scan A 70beb7428343

Subscribe to this mod's changes

website-email AGENTS.md is an instructions file published in the GitHub repository mifdlaldev/website-email (0 stars, last pushed 3mo ago), licensed MIT. It adds 2,126 tokens to every session, about $0.0085 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

website-email AGENTS.md compared with instructions from other repositories

website-email AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
website-email AGENTS.mdmifdlaldev/website-emailInstructions file03mo agoMITA2,126Codex, 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