What is ovid AGENTS.md?

Project instructions for Ovid, a web service that accepts EPUB books, translates their chapters, and creates book covers. They describe its React, Cloudflare, database, storage, and translation-service setup.

Use them when changing upload handling, EPUB parsing, chapter translation, progress tracking, database writes, or generated covers and spines.

They give coding agents the architecture and important lessons behind book uploads, EPUB parsing, translation progress, and cover creation. This reduces the need to rediscover how the system works.

How GabrielDrapor/ovid configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to GabrielDrapor/ovid. 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/GabrielDrapor/ovid/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/GabrielDrapor/ovid

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/gabrieldrapor/ovid/agents-md/github.svg)](https://agentmods.dev/instructions/gabrieldrapor/ovid/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/gabrieldrapor/ovid/agents-md"><img src="https://agentmods.dev/badge/instructions/gabrieldrapor/ovid/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/gabrieldrapor/ovid/agents-md"><img src="https://agentmods.dev/badge/instructions/gabrieldrapor/ovid/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,759 This file is loaded in full into every session.

When invoked 1,759 The same file — it is already loaded in full.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.01759	$0.01759
Opus 5	$0.00879	$0.00879
Sonnet 5	$0.00352	$0.00352
Haiku 4.5	$0.00176	$0.00176

Measured 9d ago against content hash ba8a37672315, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ovid 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 9d 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 · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Ovid Deep Technical Reference

For quick reference, see CLAUDE.md. This document covers architecture details, EPUB parsing lessons, and implementation notes that are useful for deeper work.

Architecture Overview

See docs/ARCHITECTURE.md for the full system diagram.

Stack: React + Cloudflare Worker + D1 (SQLite) + R2 (assets) + Railway (translation service)

How Upload → Translation Works

User uploads EPUB via /api/books/upload; Worker stages the file in R2 and inserts a placeholder book row
waitUntil fires POST to Railway (TRANSLATOR_SERVICE_URL/upload-and-parse) — Railway owns everything from here (parsing, DB writes, credits, translation, covers)
Railway parses the EPUB (TOC, chapters, paragraphs, embedded cover) → stores in D1
Railway translates 5 chapters concurrently, writing each paragraph back to D1 immediately (checkpoint resume)
Frontend polls /api/book/:uuid/status for progress

Cover/Spine Generation

Railway's cover-composer.ts composites each book onto a pre-made blank cloth-hardcover template with Sharp (no AI at request time): original-cover inset with book-face detection, title/author typesetting, spine width scaled to book length
Blank templates are generated offline by scripts/generate-blanks.ts
image-processor.ts is the legacy SVG→PNG path, still used by the cover-preview debug page (/cover-preview/:uuid on Railway, password-gated)
Images stored in R2 at assets.ovid.jrd.pub
R2 CORS matters: the 3D shelf loads covers/spines as WebGL textures, so the bucket has a CORS rule (GET/HEAD from *). Every <img>/preload of these assets must set crossOrigin="anonymous" — a non-CORS response cached by the browser will poison later crossOrigin texture fetches and covers silently fall back to procedural canvases.

EPUB Parsing — Hard-Won Lessons

Use TOC, Not Spine

The spine lists reading order but items often lack titles and include non-content files (cover pages, copyright). Always use the TOC for chapter detection:

Read the full file on GitHub · 142 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.

9d ago First seen · 142 lines · 1,759 tokens per session scan A ba8a37672315

Subscribe to this mod's changes

ovid AGENTS.md is an instructions file published in the GitHub repository GabrielDrapor/ovid (66 stars, last pushed 20d ago), licensed MIT. It adds 1,759 tokens to every session, about $0.0088 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.

bilingual-reader bilingualism reader

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

ovid: Instructions file for Codex