agentmods.dev

ovid: Instructions file for Claude Code

CLAUDE.md

ovid CLAUDE.md is an instructions file for Claude Code from GabrielDrapor/ovid. It costs 3,594 tokens per session, scanned A, original, MIT.

Project instructions for Ovid’s development, testing, deployment, database, and book-management commands. Ovid is the EPUB translation service described by the related architecture instructions.

In plain words
What is it for?
Use them when running the app, checking formatting, executing tests, initializing or querying databases, deploying, or managing translated EPUB books.
Why use it?
They provide the repository’s supported commands for local development, production or staging deployment, tests, database work, and importing or removing books. This avoids guessing command names or environments.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is GabrielDrapor/ovid's own configuration. It tells Claude Code how to work on ovid 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 ovid configures →

not rated 66repo 21d ago A scan 3,594 tokens original MIT
View source ↗ GabrielDrapor/ovid ovid.ink
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/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/GabrielDrapor/ovid

Made for: Claude Code.

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 ovid CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/gabrieldrapor/ovid/claude-md/github.svg)](https://agentmods.dev/instructions/gabrieldrapor/ovid/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/gabrieldrapor/ovid/claude-md"><img src="https://agentmods.dev/badge/instructions/gabrieldrapor/ovid/claude-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 ovid CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/gabrieldrapor/ovid/claude-md"><img src="https://agentmods.dev/badge/instructions/gabrieldrapor/ovid/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,594 This file is loaded in full into every session.
When invoked 3,594 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.03594 $0.03594
Opus 5 $0.01797 $0.01797
Sonnet 5 $0.00719 $0.00719
Haiku 4.5 $0.00359 $0.00359

Measured 10d ago against content hash d9d13194db4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ovid CLAUDE.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 10d 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.

CLAUDE.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code working on this repo.

Commands

Dev & Deploy

  • yarn preview — Full-stack local dev (Worker + React on :8787)
  • yarn deploy — yarn build && wrangler deploy to production
  • yarn deploy -- --env staging — Deploy to staging
  • yarn build — Build React app only
  • yarn format — Prettier
  • yarn format:check — Check formatting

Testing

  • yarn test — Vitest unit tests
  • yarn test:watch — Vitest watch mode
  • yarn test:visual — Playwright visual regression
  • yarn test:visual:update — Update Playwright snapshots

Database

  • yarn db:init — Init local DB schema
  • yarn db:seed — Load sample data
  • yarn db:local -- "SQL" — Run SQL on local D1
  • yarn db:remote -- "SQL" — Run SQL on remote D1
  • yarn db:local:file -- path.sql — Execute SQL file locally
  • yarn db:remote:file -- path.sql — Execute SQL file remotely

Book Management (TypeScript CLI)

  • yarn import-book -- --file="book.epub" --target="zh" — Import + translate
  • yarn list-books:local / yarn list-books:remote — List books
  • yarn remove-book:local -- --uuid="..." / yarn remove-book:remote -- --uuid="..." — Remove book
  • yarn sync-remote-book -- --uuid="..." — Sync local book to remote D1
  • yarn backfill-links -- --uuid="..." [--env=remote] [--dry-run] — Re-parse the original EPUB (from R2 uploads/{uuid}/original.epub) and rewrite raw_html so pre-footnote-support books get internal links/note popovers; verifies stored translation XPaths still resolve before writing

Architecture

TypeScript-first across frontend, backend, CLI, and translator service.

Components

  • React SPA (src/components/) — BookShelf (3D closet, with a legacy 2D wall fallback), BilingualReaderV2, ErrorBoundary
  • CF Worker (src/worker/) — API server: auth, book-handlers, credits, db, types
  • Railway Translator (services/translator/) — Long-running translation service (Hono + Sharp)
    • Receives webhook from Worker on EPUB upload
    • Translates via OpenAI-compatible API (default: gpt-4o-mini). All LLM work (paragraph batches, chapter titles, per-node retries) flows through one global worker pool spanning chapters (TRANSLATE_CONCURRENCY, default 8)
    • Reads/writes D1 via REST API. Checkpoint resume is chapter-level: a chapter counts as done only when every node has a translations_v2 row; partially written chapters are wiped and redone on resume (translations_v2 has no UNIQUE constraint, so this is what keeps resume idempotent)
    • Generates each book's cover + spine by compositing onto a pre-made blank cloth-hardcover template (pure Sharp, no AI at request time) — see cover-composer.ts. Spine width scales with book length.
  • CLI Scripts (scripts/) — import-book, list-books, remove-book, sync-remote-book, generate-blanks
  • D1 SQLite — Users, sessions, books/chapters/translations (v2 tables), translation jobs, credits, reading progress
  • R2 Storage — Cover images, spine images, in-book images (books/{uuid}/images/). CORS enabled (GET/HEAD from *) — the 3D shelf loads these as WebGL textures
  • PWA — Installable (manifest + iOS metas); src/sw-register.ts registers the service worker and shows a refresh toast on new deploys. iOS standalone quirk: use 100dvh/safe-area-inset-bottom for full-screen layouts, not bare 100vh

Read the full file on GitHub · 162 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. 10d ago First seen · 162 lines · 3,594 tokens per session scan A d9d13194db4e

Subscribe to this mod's changes

ovid CLAUDE.md is an instructions file published in the GitHub repository GabrielDrapor/ovid (66 stars, last pushed 21d ago), licensed MIT. It adds 3,594 tokens to every session, about $0.0180 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-readerbilingualismreader
Related

Other instructions, from other repositories

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens