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/convergentmethods/arezzo/claude-mdgit clone --depth 1 https://github.com/ConvergentMethods/arezzoWrote 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.
[](https://agentmods.dev/instructions/convergentmethods/arezzo/claude-md)<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>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 | $0.02857 | $0.02857 |
| Opus 5 | $0.01429 | $0.01429 |
| Sonnet 5 | $0.00571 | $0.00571 |
| Haiku 4.5 | $0.00286 | $0.00286 |
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.
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
- Read
ROADMAP.mdfor current phase and status - Read
SESSION_LOG.md(most recent entry) for temporal continuity - Check for active plans in
_strategy/plans/ - If session is getting long (>30 messages): "Run
/compactto 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
- Arezzo NEVER reasons. The host LLM reasons. Arezzo compiles.
- All compilation is deterministic — same input always produces same output.
- The engine modules (
compiler.py,parser.py,address.py,index.py) are the deterministic core. They must never import from the MCP layer. - The MCP layer (
server.py) is a thin wrapper that calls into the engine. - Arezzo sits BETWEEN the agent and the Google Docs API. It is a compiler, not a plugin.
- 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.
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.
- 3d ago First seen · 292 lines · 2,857 tokens per session scan A d142d1f3b674
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.
Other instructions, from other repositories
better-workspace-mcp CLAUDE.md
Claude Code instructions for n24q02m/better-workspace-mcp, covering better-workspace-mcp, vendored boundary, sync upstream, modes and env cua http mode.
better-workspace-mcp AGENTS.md
AGENTS.md instructions for n24q02m/better-workspace-mcp, covering agent collaboration, quick reference, build & test, release and conventions.
lattice AGENTS.md
Instructions for plausibleventures/lattice, covering lattice — how to work in this repo, the eleven non-negotiables, layout, commands and house style.
fullbleed-official AGENTS.md
Instructions for fullbleed-engine/fullbleed-official, covering fullbleed repository guidance, product boundary, agent contracts, validation and release discipline.
mcp-google-multi CLAUDE.md
Instructions for bakissation/mcp-google-multi, covering working on mcp-google-multi, project shape, adding a tool, adding a service and generated tools (layer 2).
lattice CLAUDE.md
Instructions for plausibleventures/lattice: See AGENTS.md — it is the constitution for this repo and applies to every agent and every human equally. Start with .lattice/kit.json for the machine-readable index of what exists, and .lattice/tasks.json for what to do next.