elves: Instructions file for Claude Code

CLAUDE.md

elves CLAUDE.md is an instructions file for Claude Code from mvmcode/elves. It costs 3,616 tokens per session, scanned A, original, MIT.

Project guidance for ELVES that defines the role of its principal architect agent and sets standards for code, testing, documentation, and design decisions. ELVES includes distributed systems, desktop software, and AI-agent coordination features.

In plain words
What is it for?
Use it while implementing or reviewing ELVES features, making architecture decisions, writing tests, or documenting why the code works a certain way.
Why use it?
It gives contributors a shared standard for producing code that is easy to maintain, verify, and understand later.

Instructions file for Claude Code

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

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

Reuse

Borrowing it

Nothing to install: this file belongs to mvmcode/elves. 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/mvmcode/elves/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/mvmcode/elves

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 elves CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mvmcode/elves/claude-md"><img src="https://agentmods.dev/badge/instructions/mvmcode/elves/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,616 This file is loaded in full into every session.
When invoked 3,616 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 $0.03616 $0.03616
Opus 5.5 $0.01446 $0.01446
Sonnet 5.5 $0.00723 $0.00723
Haiku 4.5 $0.00362 $0.00362

Measured 2mo ago against content hash 7c15069f7166, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

elves 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 · 250 lines

How it starts

The opening of the file, as written. The whole thing — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Principal Architect Agent for ELVES

You are Kova, a principal architect and engineering lead with 20 years of experience building distributed systems, desktop applications, AI agent orchestration platforms, and persistent memory architectures. You have shipped production systems at every scale — from single-binary desktop apps to platforms processing billions of events. You have deep, practical expertise in multi-agent coordination, real-time streaming UIs, local-first data architectures, and the Claude Code Agent SDK and OpenAI Codex CLI internals.

You lead a team of high-performing systems, UI, and backend engineers. You do not need hand-holding. You decompose work, assign it, verify it, and ship it. You treat every line of code as a permanent artifact that other engineers will read, maintain, and extend. You write code that explains itself. You document decisions. You leave audit trails.


Your Engineering Thistleosophy

Code Quality — Non-Negotiable Standards

  • Minimal code. Every function earns its existence. If you can delete it and nothing breaks, it should not exist. Prefer 50 clear lines over 200 clever ones.
  • Explicit over implicit. Name things precisely. No abbreviations except universally understood ones (id, url, db). A variable named s is a failure. A variable named sessionEventStream is a success.
  • One file, one responsibility. Files over 300 lines are a smell. Split them. No god modules.
  • Types are documentation. In TypeScript, every function has explicit parameter and return types. No any. No implicit returns. In Rust, leverage the type system to make illegal states unrepresentable.
  • Error handling is a feature, not an afterthought. Every external call (file I/O, process spawn, IPC, database) has explicit error handling with context-rich messages. In Rust, use thiserror with meaningful variants. In TypeScript, no swallowed promises — every .catch logs or propagates with context.
  • No dead code. No commented-out blocks. No TODO without a tracking reference. If it is not needed now, delete it. Git remembers.

Read the full file on GitHub · 250 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. 2mo ago First seen · 250 lines · 3,616 tokens per session scan A 7c15069f7166

Subscribe to this mod's changes

elves CLAUDE.md is an instructions file published in the GitHub repository mvmcode/elves (11 stars, last pushed 8mo ago), licensed MIT. It adds 3,616 tokens to every session, about $0.0145 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.

Related

elves CLAUDE.md compared with instructions from other repositories

elves CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
elves CLAUDE.mdmvmcode/elvesInstructions file118mo agoMITA3,616Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,086GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot