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/mvmcode/elves/claude-mdgit clone --depth 1 https://github.com/mvmcode/elvesWhat 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 | $0.03616 | $0.03616 |
| Opus 5 | $0.01808 | $0.01808 |
| Sonnet 5 | $0.00723 | $0.00723 |
| Haiku 4.5 | $0.00362 | $0.00362 |
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 2d 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.
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
sis a failure. A variable namedsessionEventStreamis 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
thiserrorwith meaningful variants. In TypeScript, no swallowed promises — every.catchlogs 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.
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.
- 2d ago First seen · 250 lines · 3,616 tokens per session scan A 7c15069f7166
elves CLAUDE.md is an instructions file published in the GitHub repository mvmcode/elves (11 stars, last pushed 5mo ago), licensed MIT. It adds 3,616 tokens to every session, about $0.0181 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
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.
buildNext
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
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, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit 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.
langchain 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.