What is nauro CLAUDE.md?

Repository instructions for Nauro, a Python project split into multiple related packages in one repository, known as a monorepo. Nauro is a context system for coding agents that stores project information outside individual repositories so it can be shared across them.

Use them when working on Nauro's command-line tool, local MCP server, shared Python logic, configuration, credentials, or tests. They identify where project data, the registry, and each package live.

They explain the storage and package boundaries an agent must understand before changing the code. This helps preserve shared context across repositories and keep each package's responsibilities separate.

How Nauro-AI/nauro configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Nauro-AI/nauro. 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/Nauro-AI/nauro/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Nauro-AI/nauro

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/nauro-ai/nauro/claude-md/github.svg)](https://agentmods.dev/instructions/nauro-ai/nauro/claude-md)

Your own site

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

Per session 2,852 This file is loaded in full into every session.

When invoked 2,852 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	$0.02852	$0.02852
Opus 5	$0.01426	$0.01426
Sonnet 5	$0.00570	$0.00570
Haiku 4.5	$0.00285	$0.00285

Measured 9d ago against content hash 674531b05068, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

nauro 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 9d 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 · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Nauro (monorepo)

@AGENTS.md

Nauro is a versioned project context system for AI coding agents. This is a uv workspace monorepo with two packages:

Package	Path	Python	Purpose
`nauro`	`packages/nauro/`	3.10+	CLI + local MCP server (stdio). Reads/writes `~/.nauro/projects/`
`nauro-core`	`packages/nauro-core/`	3.10+	Shared pure-Python logic: parsing, validation, context assembly, constants. No I/O; compute-only deps.

Each package has its own pyproject.toml and test suite; packages/nauro/ also carries a package-level CLAUDE.md (nauro-core does not). The remote MCP server (mcp-server/) lives in a separate private repository.

The one architectural fact that matters

The project store lives at ~/.nauro/projects/<project-id>/ — not inside any repo. This is the core design decision. A per-repo store would break cross-repo context, which is the problem Nauro exists to solve. The registry at ~/.nauro/registry.json is keyed by project id (ULID); each entry carries the project name as metadata plus one or more associated repo paths on the machine.

~/.nauro/
  registry.json                  # id-keyed entries: name, mode, repo paths
  projects/
    <project-id>/
      project.md                 # stable: goals, non-goals, users, constraints
      state_current.md           # volatile: current sprint, blockers, recent completions
      state_history.md           # append-only history of completed work
      stack.md                   # tech choices with rationale and rejected alternatives
      open-questions.md          # append-only unresolved threads
      decisions/
        001-title.md             # one file per decision, sequential, immutable
      snapshots/
        v001.json                # full store capture at a point in time

All files are freeform markdown. No database. No JSON for content — JSON only for registry.json and snapshots.

Cross-package architecture

~/.nauro/projects/<id>/          Local store (flat markdown + JSON snapshots)
        │
        ├── nauro CLI              reads/writes directly
        ├── local MCP (stdio)      reads/writes directly, spawned by Claude Code
        │
        └── nauro sync ──────►  S3 bucket (remote storage)
                                     │
                                     └── remote MCP (Lambda, separate repo) reads/writes via S3

Read the full file on GitHub · 187 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.

9d ago First seen · 187 lines · 2,852 tokens per session scan A 674531b05068

Subscribe to this mod's changes

nauro CLAUDE.md is an instructions file published in the GitHub repository Nauro-AI/nauro (10 stars, last pushed today), licensed Apache-2.0. It adds 2,852 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.

LLM agentic-ai ai-agents codex cursor developer-tools

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 · 7,296 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 · 5,153 tokens

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

nauro: Instructions file for Claude Code