nourish: Instructions file for Claude Code

CLAUDE.md

nourish CLAUDE.md is an instructions file for Claude Code from y5-snowies/nourish. It costs 7,388 tokens per session, scanned A, original, Apache-2.0.

Project instructions for y5, a Rust Wayland compositor that draws desktop windows and interfaces on Linux. They explain its vendored dependencies, workspace structure, binary location, and stable Rust setup.

In plain words
What is it for?
Finding the compositor entry point, understanding the workspace and rendering stack, and following the repository's build and development workflow.
Why use it?
They provide the discovery steps needed in a large multi-workspace project instead of relying on outdated file paths. This helps agents build or inspect the correct compositor crate.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is y5-snowies/nourish's own configuration. It tells Claude Code how to work on nourish 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 nourish configures →

Reuse

Borrowing it

Nothing to install: this file belongs to y5-snowies/nourish. 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/y5-snowies/nourish/upstream-integration/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/y5-snowies/nourish

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 nourish CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/y5-snowies/nourish/claude-md/github.svg)](https://agentmods.dev/instructions/y5-snowies/nourish/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/y5-snowies/nourish/claude-md"><img src="https://agentmods.dev/badge/instructions/y5-snowies/nourish/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 nourish CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/y5-snowies/nourish/claude-md"><img src="https://agentmods.dev/badge/instructions/y5-snowies/nourish/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 7,388 This file is loaded in full into every session.
When invoked 7,388 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 $0.07388 $0.07388
Opus 5 $0.03694 $0.03694
Sonnet 5 $0.01478 $0.01478
Haiku 4.5 $0.00739 $0.00739

Measured 5d ago against content hash f11af0d8e741, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

nourish 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 5d 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 · 480 lines

How it starts

The opening of the file, as written. The whole thing — 480 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 (claude.ai/code) when working with code in this repository.

It is written to describe conventions and discovery commands, not fixed file lists or directory names, so it stays correct as crates and workspaces are added or renamed. When you need a concrete name or path, run the discovery command shown rather than trusting a hard-coded value.

What this is

y5 is a Wayland compositor written in Rust. It is built on vendored forks of smithay (Wayland), bevy + wgpu + naga_oil (rendering) and iced + cryoglyph (UI), all under vendor/ and patched in-tree.

The shipped binary is y5_compositor — the crate that declares it via [[bin]] is the compositor's entry point. Locate it without assuming the path:

# crate dir that produces the y5_compositor binary
dirname "$(grep -rl --include=Cargo.toml 'name = "y5_compositor"' compositor*)"

Toolchain is stable (rust-toolchain.toml at the repo root); crates use Rust edition 2024 (stable since 1.85), so a current stable toolchain builds the tree. There are no nightly-only language features in use.

Build, check & run

Never run cargo build / cargo check / cargo test directly. The repo is 30 independent workspaces; cargo's default is a target/ per workspace root, so a bare cargo run in each builds a complete multi-GB dependency tree per root. That is how a checkout reaches 100+ GB. Use the scripts:

Intent Command
does it compile? environment/check.sh [workspace-dir]
build the binary environment/build.sh [winit|udev]
build + install environment/build.sh udev --deploy[=NAME]
run it nested environment/run-host.sh [winit|udev]
shipped artifact environment/build-optimized.sh udev

Each prints the built binary's path on stdout, logs on stderr.

There is one profile. Local work is always release-fast (release optimizations, no LTO); build.sh, run-host.sh and check.sh take no profile argument and reject one. debug is gone — its dependency tree cost ~4x as much disk and release-fast keeps debug = "line-tables-only", so backtraces still have line numbers. Fat-LTO release is build-optimized.sh alone: a 10-20 minute serial link, for release tags, never for "does it compile".

Read the full file on GitHub · 480 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. 5d ago Changed · +183 lines · +3,187 tokens per session f11af0d8e741
  2. 10d ago First seen · 297 lines · 4,201 tokens per session scan A 2f5a738d6488

Subscribe to this mod's changes

nourish CLAUDE.md is an instructions file published in the GitHub repository y5-snowies/nourish (228 stars, last pushed 6d ago), licensed Apache-2.0. It adds 7,388 tokens to every session, about $0.0369 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 2026-08-30.

Related

Other instructions, from other repositories

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 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 · 4,469 tokens