What is Ruvyxa CLAUDE.md?

Repository-specific instructions for working on Ruvyxa, a web framework whose compiler and server use Rust while its runtime and public programming interface use TypeScript. They explain which guidance to read, how the repository is organised, and which checks matter.

Use them when modifying Ruvyxa, especially its command-line tool, bundler, server, routing, middleware, diagnostics, runtime, or integrations. They also describe the checks and change guidance for this repository.

They give a coding agent the project context needed to avoid changing one half of the Rust-and-TypeScript system without updating the other. They also point it to the repository's source of truth for working rules.

How thirawat27/Ruvyxa configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to thirawat27/Ruvyxa. 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/thirawat27/Ruvyxa/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/thirawat27/Ruvyxa

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/thirawat27/ruvyxa/claude-md/github.svg)](https://agentmods.dev/instructions/thirawat27/ruvyxa/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/thirawat27/ruvyxa/claude-md"><img src="https://agentmods.dev/badge/instructions/thirawat27/ruvyxa/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/thirawat27/ruvyxa/claude-md"><img src="https://agentmods.dev/badge/instructions/thirawat27/ruvyxa/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,228 This file is loaded in full into every session.

When invoked 1,228 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	$0.01228	$0.01228
Opus 5.5	$0.00491	$0.00491
Sonnet 5.5	$0.00246	$0.00246
Haiku 4.5	$0.00123	$0.00123

Measured 2mo ago against content hash 399925c483ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Ruvyxa 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 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.

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 · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Instructions

Read AGENTS.md first. It is the source of truth for working in this repository: the repository shape, the operating rules, what each check gates, and the change guidance written from defects that actually shipped. This file does not repeat it — it orients a session and says what is specific to working here as an agent.

What this repository is

Ruvyxa is a web framework whose compiler and server are Rust, and whose runtime and public API are TypeScript. That split is the single most important thing to hold in mind, because most of the expensive mistakes here come from one half of a rule being changed without the other:

crates/ — the CLI (ruvyxa_cli), the bundler (ruvyxa_bundler: TypeScript/JSX compilation, resolution, linking, minification, source maps, boundary checks), the dev/production server (ruvyxa_dev_server), route discovery (ruvyxa_graph), middleware (ruvyxa_middleware), diagnostics, and the terminal UI.
packages/ — ruvyxa (the framework package, including the runtime/*.mjs modules the Rust CLI spawns or imports by path), create-ruvyxa, @ruvyxa/core, @ruvyxa/react, four optional integrations, eleven deploy adapters, and five prebuilt CLI binaries.
examples/demo is the broad feature fixture and is deployable — RUV2213 and the refusal of a dynamic server-components route are both gone. examples/deploy-smoke is the smallest app every self-hosted adapter can deploy, and it is what CI builds and launches on real Node, Bun, and Deno.

There is no esbuild, no Vite, no Webpack. The bundler is ours.

Working here

Never run git commit, git push, or git add. The owner commits their own work. Stop at verified and reported: say what changed, what you ran, and what came back.
Preserve changes you did not make. This working tree sometimes carries the owner's own edits from another terminal — check git diff HEAD, not just git diff, because staged changes do not appear in the latter.
Run the narrowest check that can fail while iterating, and the relevant subset of the full battery before handing off. Both lists, and what each one gates, are in AGENTS.md.
Prefer a fixture over a promise. When two implementations must agree and cannot share code, the answer is a file in tests/fixtures/ replayed by a test in each language — not a comment saying they are kept in sync. AGENTS.md lists the rules that drifted before they had one.

Read the full file on GitHub · 84 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.

2mo ago First seen · 84 lines · 1,228 tokens per session scan A 399925c483ce

Subscribe to this mod's changes

Ruvyxa CLAUDE.md is an instructions file published in the GitHub repository thirawat27/Ruvyxa (20 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,228 tokens to every session, about $0.0049 per session on Opus 5.5. 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.

React bundler compiler component framework node

Ruvyxa CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Ruvyxa CLAUDE.mdthirawat27/Ruvyxa	Instructions file	20	1mo ago	Apache-2.0	A	1,228	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

Ruvyxa: Instructions file for Claude Code