What is fluxon CLAUDE.md?

A guide for AI agents working on Fluxon, a backend programming language designed around concise, consistent code. The repository contains its Rust interpreter, documentation, examples, and research.

Use it when building, testing, running, or documenting Fluxon and its interpreter.

It helps an agent understand the language, find the right files, and follow the project's rules before changing code.

How fluxon-lang/fluxon configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to fluxon-lang/fluxon. 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/fluxon-lang/fluxon/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/fluxon-lang/fluxon

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/fluxon-lang/fluxon/claude-md/github.svg)](https://agentmods.dev/instructions/fluxon-lang/fluxon/claude-md)

Your own site

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

Per session 2,056 This file is loaded in full into every session.

When invoked 2,056 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	$0.02056	$0.02056
Opus 5.5	$0.00822	$0.00822
Sonnet 5.5	$0.00411	$0.00411
Haiku 4.5	$0.00206	$0.00206

Measured 2mo ago against content hash 689a552efb51, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fluxon 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 · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — How to work on Fluxon (for AI agents)

This file is for Claude Code and other AI agents. Before making any change to the project, read this file to the end. The goal: get a new agent productive fast, working in the right place and in the right style.

For human contributors: CONTRIBUTING.md. Runtime internals: ARCHITECTURE.md.

0. What this project is

Fluxon — a backend programming language that AI agents write well. Philosophy: "The language adapts to the AI, not the AI to the language." One task = one way (canonical form), few tokens, batteries-included (http/db/ai/ws/...).

This repo has two parts:

runtime/ — the language interpreter (Rust, tree-walking). This is where the main work happens. All code, tests, and builds live here.
docs/ + examples/ + research/ — the language specification, examples, and how the language was designed (experiments).

1. Language

Write code, comments, commit messages, PR titles/descriptions, and documentation in English. Technical terms and code identifiers (HashMap, eval_call, db.tx) stay as-is.

When talking to the user, the agent is language-neutral: reply in whatever language the user writes in. The codebase is English, but the conversation adapts to the user.

Note: research/ and the *.uz.md documents are kept in Uzbek on purpose (design history and future multi-language docs) — do not translate them.

Before adding a new battery or making a change, find the relevant file:

Task	File
Token types, `Token.spaced` flag	`runtime/src/token.rs`
Lexer: INDENT/DEDENT, string interpolation	`runtime/src/lexer.rs`
AST nodes (`Stmt`, `Expr`)	`runtime/src/ast.rs`
Parser: precedence climbing, parenless calls	`runtime/src/parser.rs`
Value types (`Value`, `NativeFn`)	`runtime/src/value.rs`
Interpreter: scope, control flow, dispatch	`runtime/src/interp.rs`
Core modules (`str/math/rand/json/time`)	`runtime/src/builtins.rs`
`http` battery (server + client)	`runtime/src/http_mod.rs`
`ai` battery (LLM — Anthropic Messages API)	`runtime/src/ai_mod.rs`
`db` battery (SQLite, tx, schema)	`runtime/src/db_mod.rs`
`auth` battery (JWT HS256 + password hash argon2id)	`runtime/src/auth_mod.rs`
`crypto` battery (sha256/hmac/b64/hex/uuid)	`runtime/src/crypto_mod.rs`
`tui` battery (colors + table/box/select/input — CLI UX)	`runtime/src/builtins/tui_mod.rs`
User-module `.pkg` manifest parsing + load-time validation	`runtime/src/interp/pkg.rs`
CLI entry point + integration tests	`runtime/src/main.rs`

Read the full file on GitHub · 181 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 · 181 lines · 2,056 tokens per session scan A 689a552efb51

Subscribe to this mod's changes

fluxon CLAUDE.md is an instructions file published in the GitHub repository fluxon-lang/fluxon (5 stars, last pushed 4mo ago), licensed MIT. It adds 2,056 tokens to every session, about $0.0082 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 2026-08-31.

LLM ai-agents fluxon interpreter programming-language

fluxon CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
fluxon CLAUDE.mdfluxon-lang/fluxon	Instructions file	5	4mo ago	MIT	A	2,056	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

fluxon: Instructions file for Claude Code