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.
npx agentmods add instructions/thirawat27/ruvyxa/agents-mdgit clone --depth 1 https://github.com/thirawat27/RuvyxaWrote 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/thirawat27/ruvyxa/agents-md)<a href="https://agentmods.dev/instructions/thirawat27/ruvyxa/agents-md"><img src="https://agentmods.dev/badge/instructions/thirawat27/ruvyxa/agents-md.svg" alt="Measured on agentmods" 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 | $0.11843 | $0.11843 |
| Opus 5 | $0.05921 | $0.05921 |
| Sonnet 5 | $0.02369 | $0.02369 |
| Haiku 4.5 | $0.01184 | $0.01184 |
Grade A, and why
Ruvyxa 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 596 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ruvyxa Monorepo Agent Guide
You are working in the Ruvyxa framework monorepo. Treat this file as the source of truth for agent work in the repository.
Repository Shape
crates/contains the Rust workspace.crates/ruvyxa_cliowns the Ruvyxa CLI commands:dev,build,check,start,preview,routes,analyze,adds,doctor,clean,trace,bench,test:parity, andplugin create. TheCommandenum incrates/ruvyxa_cli/src/main.rsis the list; nothing else enumerates them.crates/ruvyxa_bundlerowns TypeScript/JSX compilation, module resolution, linking, minification, source maps, and server/client boundary checks.crates/ruvyxa_dev_serverowns Axum serving, HMR, render cache, router, worker pool, style collection, and action/API/client endpoints. Itslib.rsis the crate root — configuration,serve, the router table, and the request path for project pages and API routes. Handlers for the reserved/__ruvyxa/*paths live inframework_endpoints.rs, the WebSockets inrealtime_endpoints.rs, and the development file watcher inwatcher.rs. Add a new framework endpoint toframework_endpoints.rsand its route to the table inlib.rs, not tolib.rsalone; the conformance test there checks the two agree.crates/ruvyxa_graphowns file-system route discovery, validation, rendering strategy detection, and route manifests. It depends onruvyxa_bundlerfor one reason: route validation reuses the bundler's source scanner rather than running a second text scan that could disagree.crates/ruvyxa_middlewareowns the Tower layer stack — CORS, rate limiting, request logging, response timing, custom headers, client-IP resolution — and the TypeScript plugin host. Its crate docs carry the contract shared by every rate limiter in the workspace; read it before adding a fifth.crates/ruvyxa_diagnosticsowns error codes,Result, and the path helpers every other crate agrees on (normalized_canonical_pathin particular — see the Windows note under Change Guidance).crates/ruvyxa_tuiowns terminal layout, spinners, progress, the mascot, the command header and success banner, the colour roles, and the decorative gradients.cargo run -p ruvyxa_tui --example previewdraws every one of those surfaces in one screen, which is the only way to see the animated ones without rebuilding an application.packages/contains the npm packages:ruvyxa— the framework package.runtime/*.mjsare the modules the Rust CLI resolves by path and spawns or imports;src/plugins/is the first-party plugin API behind theplugins.tsbarrel;packages/ruvyxa/scripts/sync-shared-runtime.mjsregenerates the committed copies of shared modules.create-ruvyxa— the scaffolder. Itstemplate/directory holds a generated copy of every starter, not justminimal.@ruvyxa/core— primitives both the Rust host and a deployed build need:route-match,origin-policy, the standalone server, shared server utilities.@ruvyxa/react— the client router,not-found, and the React-facing surface.@ruvyxa/auth,@ruvyxa/database,@ruvyxa/realtime,@ruvyxa/testing— optional integrations.@ruvyxa/adapter-*— eleven deploy adapters;@ruvyxa/cli-*— five prebuilt CLI binaries.
examples/demo/is the broad integration fixture, and it is deployable —RUV2213is gone, along with the refusal of a dynamic server-components route. A failure there is usually a question about the feature rather than about the emitted server, which is what the smoke fixture is for.examples/deploy-smoke/is the smallest application every self-hosted adapter can deploy, and is what CI builds and then launches on real Node, Bun, and Deno throughscripts/smoke-runtime-adapter.mjs. Keep it deployable: a route or feature no adapter supports belongs in the demo instead./rscthere is a dynamic server-components route on purpose — a pre-rendered one proves nothing about a deployment, because its payload is already in the file the adapter copies and no renderer runs.templates/holds five scaffolds —minimal,blog,crud,api,plugin.templates/minimal/is whatcreate-ruvyxacopies into a new project.packages/create-ruvyxa/template/is generated, not committed: it is gitignored, andpackages/create-ruvyxa/scripts/prepare-template.mjsdeletes and rebuilds it fromtemplates/*onprepack, renaming.gitignoretogitignorebecause npm strips a packaged dotfile. Edittemplates/; never that copy, and never add a second mechanism to keep the two in step — this file used to sayscripts/check-template-mirrors.mjsdid, and it does not. That script holds one genuinely hand-maintained pair:ruvyxa-runner.tsxin the template and inexamples/demo, so the fixture exercises what a scaffolded project ships with.pnpm release:validatefails on drift there.
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.
- today Changed · +14 lines · +302 tokens per session 63f370be6987
- 6d ago First seen · 582 lines · 11,541 tokens per session scan A 66683a5aa9b3
Ruvyxa AGENTS.md is an instructions file published in the GitHub repository thirawat27/Ruvyxa (20 stars, last pushed today), licensed Apache-2.0. It adds 11,843 tokens to every session, about $0.0592 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.
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.
wasp AGENTS.md
AGENTS.md instructions for wasp-lang/wasp, covering wasp monorepo, contribution policy, repository structure, build & development and code conventions.
core CLAUDE.md
Claude Code instructions for module-federation/core, covering claude task parallelization & development guidelines, core principles, maximum parallelization strategy, universal parallel task patterns and for any codebase task.
core AGENTS.md
AGENTS.md instructions for module-federation/core, covering agents.md, scope and precedence, source of truth (in priority order), environment parity and worktree mode (required in worktrees).
react-nprogress AGENTS.md
AGENTS.md instructions for tanem/react-nprogress, covering agent instructions for react-nprogress, project, key commands, code standards and comments.
next.js CLAUDE.md
Claude Code instructions for vercel/next.js, a project described as: The React Framework.