archstone: Instructions file for Claude Code

CLAUDE.md

archstone CLAUDE.md is an instructions file for Claude Code from Archstone-Romania/archstone. It costs 1,385 tokens per session, scanned A, original, Apache-2.0.

Instructions for working on Archstone, a compiler that turns a business’s described abilities into software an AI agent can use. It explains the repository’s purpose, development location, and workflow rules.

In plain words
What is it for?
Choosing the right repository for changes, following project-specific commands and branches, and understanding how the compiler, runtime, command-line tool, and protocol outputs fit together.
Why use it?
It helps an agent avoid treating the project as an ordinary server or editing a repository whose changes may later be replaced by release snapshots.

Instructions file for Claude Code

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

This is Archstone-Romania/archstone's own configuration. It tells Claude Code how to work on archstone 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 archstone configures →

Reuse

Borrowing it

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

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 archstone CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/archstone-romania/archstone/claude-md"><img src="https://agentmods.dev/badge/instructions/archstone-romania/archstone/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,385 This file is loaded in full into every session.
When invoked 1,385 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 $0.01385 $0.01385
Opus 5.5 $0.00554 $0.00554
Sonnet 5.5 $0.00277 $0.00277
Haiku 4.5 $0.00138 $0.00138

Measured 22d ago against content hash b403d2f24a0f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

archstone 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 22d 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 · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code and other coding agents working in this repository.

What this is

Archstone — a compiler for AI capabilities. A business describes what it can do once, in CDL (the Capability Definition Language); the compiler lowers that to a target-agnostic IR, and emitters generate what an agent needs. MCP today, other protocols as they arrive.

It is not an MCP server. It generates one, and that distinction is the product: change the protocol and you regenerate rather than rewrite.

Where development happens

This repository is the home of the core — CDL, the compiler, the IR, emitters, runtime, CLI, embedded SDK and provider adapters. Issues, pull requests, CI and releases belong here, and so does every core change — there is no other tree it has to be made in first.

Planning material — product strategy, commercial artifacts, pricing, research — lives in a private repository and always will. What reaches this one is the work and the technical argument for it, never the commercial reasoning behind choosing it.

The hosted commercial product will live in its own separate repository and depend on @archstone/* from npm. The core must never depend on it. That direction is permanent and is the mechanical form of the open-core commitment in docs/adr/0005-open-core-boundary-artifact-guarantee.md.

Branches

Every change goes through a branch and a pull request, including a one-line edit. Name the branch for what the task is, with one of exactly three prefixes:

Prefix For
feature/ new capability, new docs, a decision record, a refactor — anything additive or structural
bug/ a defect in shipped behaviour, fixed on the normal review cadence
hotfix/ a defect fixed out of cadence, because something is broken for users now

bug/ and hotfix/ are separated by urgency, not severity: the same defect is a bug/ when it can wait for review and a hotfix/ when it cannot.

Read the full file on GitHub · 107 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. 22d ago Changed · -7 lines · -126 tokens per session b403d2f24a0f
  2. 27d ago Changed · +8 lines · +125 tokens per session 453f0c1f66b7
  3. 1mo ago Changed · +71 tokens per session 02e19bf3ec29
  4. 1mo ago First seen · 106 lines · 1,315 tokens per session scan A 1d49b8db2435

Subscribe to this mod's changes

archstone CLAUDE.md is an instructions file published in the GitHub repository Archstone-Romania/archstone (6 stars, last pushed 21d ago), licensed Apache-2.0. It adds 1,385 tokens to every session, about $0.0055 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.

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 · 9,649 tokens

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.

vercel/next.js · 7,549 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, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 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 · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens