elo CLAUDE.md

A development guide for Elo, a small expression language whose code can be compiled into Ruby, JavaScript, or PostgreSQL SQL. It describes the compiler’s parts and its design rules.

In plain words
What is it for?
Use it when changing Elo’s parser, syntax tree, type system, intermediate representation, standard library, or compiler output. It helps maintain equivalent results across the three target languages.
Why use it?
It tells coding agents how to keep new language features simple, portable, and safe. It also prevents features from being added without updating the project’s documentation.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/enspirit/elo/claude-md
Clone the repo
git clone --depth 1 https://github.com/enspirit/elo
Per session 1,073 This file is loaded in full into every session.
When invoked 1,073 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01073 $0.01073
Opus 5 $0.00536 $0.00536
Sonnet 5 $0.00215 $0.00215
Haiku 4.5 $0.00107 $0.00107

Measured 3d ago against content hash 5d56ab664d4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

elo 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 3d 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 · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Development Guide for Elo

This document provides instructions for AI assistants (like Claude) working on the Elo compiler project.

Project Overview

Elo is a small expression language that compiles to three target languages:

  • Ruby: Server-side scripting
  • JavaScript: Client-side execution
  • PostgreSQL SQL: Database queries

The compiler translates Elo expressions into semantically equivalent code in each target language.

Design principles

Following the vision, design and implementation choices MUST target a language that stays simple, well-designed, portable and safe, in that order. We SHOULD always restrict Elo's powerfullness if a wanted feature leads to a violation of those principles.

CRITICAL when adding a language construct or stdlib function, you MUST also document it in README (no details) and on website (with example).

Architecture

Elo currently has the following components :

  • A parser (src/parser.ts)
  • AST types and factory (src/ast.ts)
  • Type system (src/types.ts)
  • Intermediate Representation with type inference (src/ir.ts, src/transform.ts)
  • Standard library abstraction for type-based dispatch (src/stdlib.ts)
  • One compiler per target language (src/compilers/*.ts)
  • A binary command (bin/eloc and src/cli.ts)
  • A try-elo website to demonstrate Elo (web/)

Compilation Pipeline

  1. Parse: Source → AST (parser.ts)
  2. Transform: AST → Typed IR (transform.ts) - infers types and rewrites operators as function calls
  3. Emit: IR → Target code (compilers/*.ts) - uses StdLib for type-based dispatch

Test-Driven Development

Elo is developped in TDD. We have three levels of testing :

  • npm run test:unit : checks the behavior of core and utility functions
  • npm run test:integration : checks expected compilation output from sources
  • npm run test:acceptance : checks expected semantics against ruby, node and psql

CRITICAL : the three levels of tests MUST be maintained ; all tests MUST PASS at all times.

Read the full file on GitHub · 108 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. 3d ago First seen · 108 lines · 1,073 tokens per session scan A 5d56ab664d4f

Subscribe to this mod's changes

elo CLAUDE.md is an instructions file published in the GitHub repository enspirit/elo (173 stars, last pushed 4mo ago), licensed MIT. It adds 1,073 tokens to every session, about $0.0054 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.

Related

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).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

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.

github/spec-kit · 7,104 tokens

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.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

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.

vercel/next.js · 7,296 tokens