arezzo CLAUDE.md

arezzo CLAUDE.md is an instructions file for coding agents from ConvergentMethods/arezzo. It costs 2,857 tokens per session, scanned A, original, MIT.

Project instructions for Arezzo, a tool that converts intended Google Docs changes into correctly ordered Google Docs API requests. They also define the expected development workflow and where to read project status.

In plain words
What is it for?
Working on the Arezzo codebase, including reviewing its roadmap and session history and following its required development process.
Why use it?
They help an agent understand both the project's purpose and the process for planning, building, checking, and shipping changes.

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/convergentmethods/arezzo/claude-md
Clone the repo
git clone --depth 1 https://github.com/ConvergentMethods/arezzo

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 arezzo CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/convergentmethods/arezzo/claude-md.svg)](https://agentmods.dev/instructions/convergentmethods/arezzo/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/convergentmethods/arezzo/claude-md"><img src="https://agentmods.dev/badge/instructions/convergentmethods/arezzo/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,857 This file is loaded in full into every session.
When invoked 2,857 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 $0.02857 $0.02857
Opus 5 $0.01429 $0.01429
Sonnet 5 $0.00571 $0.00571
Haiku 4.5 $0.00286 $0.00286

Measured 3d ago against content hash d142d1f3b674, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

arezzo 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 · 292 lines

How it starts

The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code when working with code in this repository.


Role

CTO / Architect. Follows the four-phase protocol defined in ~/.claude/CLAUDE.md: Assess & Plan → Build → Verify → Ship.

Session Protocol

  1. Read ROADMAP.md for current phase and status
  2. Read SESSION_LOG.md (most recent entry) for temporal continuity
  3. Check for active plans in _strategy/plans/
  4. If session is getting long (>30 messages): "Run /compact to preserve context."

Model Tiering

Follows the Mandatory Model Gate defined in ~/.claude/CLAUDE.md.


What is this?

Arezzo is a deterministic compiler for Google Docs API operations, built by Convergent Methods, LLC. It compiles semantic agent-intent operations into correct Google Docs API batchUpdate request sequences with proper UTF-16 index arithmetic, element address resolution, and OT-compatible mutation ordering.

Named after Guido d'Arezzo (~991–1033), the monk who standardized music notation — turning vague melodic intent into precise, portable notation. Arezzo does the same for document operations.

One-sentence thesis: Deterministic layers turn silent wrongness into loud correctness failures.


Architectural Principles

  1. Arezzo NEVER reasons. The host LLM reasons. Arezzo compiles.
  2. All compilation is deterministic — same input always produces same output.
  3. The engine modules (compiler.py, parser.py, address.py, index.py) are the deterministic core. They must never import from the MCP layer.
  4. The MCP layer (server.py) is a thin wrapper that calls into the engine.
  5. Arezzo sits BETWEEN the agent and the Google Docs API. It is a compiler, not a plugin.
  6. Two-phase compilation: content mutations first (reverse index order), then format mutations (index-neutral, appended after content).

Master Planning Document

_strategy/ARCHITECTURE.md is the locked architecture document (from Will + Opus). ROADMAP.md is the ops layer roadmap. _strategy/plans/ holds phase-level execution plans when they exist.

Read the full file on GitHub · 292 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 · 292 lines · 2,857 tokens per session scan A d142d1f3b674

Subscribe to this mod's changes

arezzo CLAUDE.md is an instructions file published in the GitHub repository ConvergentMethods/arezzo (0 stars, last pushed 4mo ago), licensed MIT. It adds 2,857 tokens to every session, about $0.0143 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 2026-08-31.

Related

Other instructions, from other repositories