revv CLAUDE.md

revv CLAUDE.md is an instructions file for coding agents from alexandre-schaffner/revv. It costs 4,219 tokens per session, scanned A, a copy of revv AGENTS.md, MIT.

Repository instructions for Revv, a desktop app that reviews GitHub pull requests with AI. They describe its Bun and TypeScript monorepo, Svelte frontend, Rust desktop layer, local API, and SQLite database.

In plain words
What is it for?
Use them to install dependencies, start the app or server, run type checks and linting, build installers, create database migrations, and clean or reset development files.
Why use it?
They give a coding agent the project-specific commands and setup details needed to work consistently in a multi-package codebase.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/alexandre-schaffner/revv/claude-md
Clone the repo
git clone --depth 1 https://github.com/alexandre-schaffner/revv

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 revv CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/alexandre-schaffner/revv/claude-md.svg)](https://agentmods.dev/instructions/alexandre-schaffner/revv/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/alexandre-schaffner/revv/claude-md"><img src="https://agentmods.dev/badge/instructions/alexandre-schaffner/revv/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,219 This file is loaded in full into every session.
When invoked 4,219 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 98% copy Near-identical to another mod 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 $0.04219 $0.04219
Opus 5 $0.02109 $0.02109
Sonnet 5 $0.00844 $0.00844
Haiku 4.5 $0.00422 $0.00422

Measured 5d ago against content hash 52ada46a0bad, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

revv 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 5d 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.

Origin

This is a copy

98% identical to revv AGENTS.md — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 246 lines

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.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What This Is

Revv is an AI-powered code review desktop application. It's a Tauri v2 desktop app with a SvelteKit frontend and a local Bun/Elysia API server that syncs GitHub pull requests and enables AI-assisted review workflows.

Stack: Bun + TypeScript monorepo (Turborepo), Svelte 5, Elysia, Drizzle ORM on SQLite, Tauri v2 (Rust).

Commands

# Setup
bun install              # Install all workspace deps
cp .env.example .env     # Then fill in GITHUB_CLIENT_ID and GITHUB_CLIENT_SECRET

# Development
make dev                 # All services (web @ 5173, server @ 45678, Tauri desktop)
make dev-server          # Elysia API only

# Quality
make typecheck           # tsc across all packages
make lint                # Linters across all packages

# Build & Distribution
make build               # Build all packages
make dist                # Build platform installer (dmg/msi/deb)

# Database
cd apps/server && bunx drizzle-kit generate   # Generate migration from schema changes

# Cleanup
make clean               # Remove build artifacts
make reset-db            # Delete SQLite database (apps/server/revv.db)

Architecture

Monorepo Layout

  • apps/web — SvelteKit frontend rendered by the Tauri desktop shell (from the Vite dev server at localhost:5173 in dev, from ../web/build in prod). Revv is a desktop-only app; the frontend is not a standalone browser app.
  • apps/server — Elysia HTTP + SSE server (port 45678)
  • apps/desktop — Tauri v2 shell; minimal Rust, just window + plugin setup
  • packages/shared — Shared types, constants (API_PORT, APP_NAME), and SSE event message schemas

packages/shared is the source of truth for cross-app types. Import from @revv/shared.

Server (apps/server)

  • Effect system throughout: services use Effect.gen, Context.Tag, and Layer for DI and structured error handling. Don't bypass Effect when modifying services.
  • Services: GitHubService, RepositoryService, PullRequestService, PollScheduler, Broadcaster, Settings, TokenProvider
  • Auth: better-auth with GitHub OAuth. Bearer token strategy. OAuth callback URL: http://localhost:45678/api/auth/callback/github
  • Database: Drizzle ORM on SQLite (revv.db). Schema in src/db/schema.ts. Migrations live in src/db/migrations and are auto-applied on startup via drizzle-orm/bun-sqlite/migrator. Generate new ones with bunx drizzle-kit generate (run from apps/server).
  • Realtime (SSE): Clients open a single GET /api/events?token=… stream. Server broadcasts prs:updated, repos:updated, etc. via Broadcaster (account-scoped fan-out). Inbound commands use REST endpoints.

Read the full file on GitHub · 246 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. 5d ago First seen · 246 lines · 4,219 tokens per session scan A 52ada46a0bad

Subscribe to this mod's changes

revv CLAUDE.md is an instructions file published in the GitHub repository alexandre-schaffner/revv (10 stars, last pushed today), licensed MIT. It adds 4,219 tokens to every session, about $0.0211 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to revv AGENTS.md, differing in 8 lines, and is treated as a copy.

Related

Other instructions, from other repositories

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

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 · 5,182 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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,733 tokens