Borrowing it
Nothing to install: this file belongs to alexandre-schaffner/revv. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/alexandre-schaffner/revv/main/CLAUDE.mdgit clone --depth 1 https://github.com/alexandre-schaffner/revvWrote 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/alexandre-schaffner/revv/claude-md)<a href="https://agentmods.dev/instructions/alexandre-schaffner/revv/claude-md"><img src="https://agentmods.dev/badge/instructions/alexandre-schaffner/revv/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.
<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="Reviewed on agentmods" width="80" 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 5.1 | $0.06438 | $0.06438 |
| Opus 5.5 | $0.02575 | $0.02575 |
| Sonnet 5.5 | $0.01288 | $0.01288 |
| Haiku 4.5 | $0.00644 | $0.00644 |
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 7d 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.
This is a copy
98% identical to revv AGENTS.md — 131 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.
How it starts
The opening of the file, as written. The whole thing — 367 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 atlocalhost:5173in dev, from../web/buildin 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 setuppackages/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.Service, andLayerfor DI and structured error handling. Don't bypass Effect when modifying services. - Services:
GitHubService,RepositoryService,PullRequestService,PollScheduler,Broadcaster,Settings,TokenProvider - Auth:
better-authwith GitHub OAuth. Bearer token strategy. OAuth callback URL:http://localhost:45678/api/auth/callback/github - Database: Drizzle ORM on SQLite (
revv.db). Schema insrc/db/schema.ts. Migrations live insrc/db/migrationsand are auto-applied on startup viadrizzle-orm/bun-sqlite/migrator. Generate new ones withbunx drizzle-kit generate(run fromapps/server). - Realtime (SSE): Clients open a single
GET /api/events?token=…stream. Server broadcastsprs:updated,repos:updated, etc. viaBroadcaster(account-scoped fan-out). Inbound commands use REST endpoints.
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.
- 7d ago Changed · +35 lines · +557 tokens per session 9414a44b711d
- 20d ago Changed · +4 lines · +60 tokens per session 17e44ad02327
- 23d ago Changed · +23 lines · +524 tokens per session 4d10555d5ad1
- 1mo ago Changed · +59 lines · +1,078 tokens per session 0ba7927ac4f2
- 2mo ago First seen · 246 lines · 4,219 tokens per session scan A 52ada46a0bad
revv CLAUDE.md is an instructions file published in the GitHub repository alexandre-schaffner/revv (12 stars, last pushed today), licensed MIT. It adds 6,438 tokens to every session, about $0.0258 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 98% identical to revv AGENTS.md, differing in 131 lines, and is treated as a copy.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.