monorepo: Instructions file for Claude Code

CLAUDE.md

monorepo CLAUDE.md is an instructions file for Claude Code from logosdx/monorepo. It costs 3,007 tokens per session, scanned A, original, BSD-3-Clause.

Repository instructions for a monorepo, a codebase that contains multiple related packages, covering its commands, tests, development workflow, and releases.

In plain words
What is it for?
Running builds, full or individual tests, test watch mode, documentation builds, package creation, and Changesets-based releases.
Why use it?
They give the coding agent the project’s expected commands and release process, reducing mistakes when building, testing, or publishing packages.

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 logosdx/monorepo's own configuration. It tells Claude Code how to work on monorepo 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 monorepo configures β†’

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import { attempt } from '../../../../packages/utils/src/index.ts';.

Reuse

Borrowing it

Nothing to install: this file belongs to logosdx/monorepo. 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/logosdx/monorepo/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/logosdx/monorepo

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 monorepo CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/logosdx/monorepo/claude-md/github.svg)](https://agentmods.dev/instructions/logosdx/monorepo/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/logosdx/monorepo/claude-md"><img src="https://agentmods.dev/badge/instructions/logosdx/monorepo/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80Γ—15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80Γ—15 button for monorepo CLAUDE.md

Your own site Β· 80Γ—15
<a href="https://agentmods.dev/instructions/logosdx/monorepo/claude-md"><img src="https://agentmods.dev/badge/instructions/logosdx/monorepo/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,007 This file is loaded in full into every session.
When invoked 3,007 The same file β€” it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file β€” 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 $0.03007 $0.03007
Opus 5.5 $0.01203 $0.01203
Sonnet 5.5 $0.00601 $0.00601
Haiku 4.5 $0.00301 $0.00301

Measured 2mo ago against content hash bd4e649b68bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

monorepo CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories β€” prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency β€” measured 2mo 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 Β· 367 lines

How it starts

The opening of the file, as written. The whole thing β€” 367 lines β€” 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.

πŸš€ Commands

# Build/Test
pnpm build
pnpm test
pnpm tdd                    # Watch mode
pnpm test:only              # Run marked tests (it.only)
pnpm test:coverage

# Workflow
pnpm new                    # Create package
pnpm watch                  # Dev mode
pnpm build:docs
pnpm release               # Changesets

# Individual tests (from tests/)
pnpm test filepart         # Run test whose filename contains "filepart"
pnpm tdd                   # Watch specific tests

πŸ“¦ Release Cycle

We use Changesets, publishing straight from master.

Publishing is triggered by a package version change on master β€” merging the "Version Packages" PR is the signal. No separate release branch.

Quick Reference

```bash
# 1. Create changeset for your changes
pnpm changeset

# 2. Commit and push to master
git add . && git commit -m "feat: description" && git push

# 3. CI creates "Version Packages" PR - review and merge to master

# 4. Merging the PR bumps versions on master, which triggers CI to
#    automatically: Publish β†’ Update docs
```

Detailed Flow

  1. Create Changeset: pnpm changeset - describes changes and version bump
  2. Push to Master: CI runs tests and creates "Version Packages" PR
  3. Review PR: Verify versions and changelogs are correct
  4. Merge PR: version bump on master triggers the publish workflow
  5. Automated CI: publishes to npm, updates documentation

See CONTRIBUTING.md for complete release documentation.

πŸ—οΈ Architecture

Structure: pnpm monorepo, packages build independently, test together

Repository Structure Overview

monorepo/
β”œβ”€β”€ packages/                    # 9 @logosdx packages in layered architecture
β”‚   β”œβ”€β”€ utils/                  # Foundation layer (all packages depend on this)
β”‚   β”œβ”€β”€ dom/                    # Browser utilities (depends on utils)
β”‚   β”œβ”€β”€ fetch/                  # HTTP client (depends on utils)
β”‚   β”œβ”€β”€ observer/               # Event system (depends on utils)
β”‚   β”œβ”€β”€ localize/               # i18n system (depends on utils)
β”‚   β”œβ”€β”€ state-machine/          # State management (depends on utils)
β”‚   β”œβ”€β”€ storage/                # Persistence layer (depends on utils)
β”‚   └── react/                  # React bindings (optional peer deps on above)
β”‚
β”œβ”€β”€ tests/                       # Comprehensive test suite
β”‚   β”œβ”€β”€ src/                    # Test files mirroring package structure
β”‚   β”œβ”€β”€ benchmark/              # Performance tests (250k ops, memory monitoring)
β”‚   └── package.json            # Test dependencies (vitest, sinon, jsdom, fast-check)
β”‚
β”œβ”€β”€ docs/                       # VitePress documentation + TypeDoc integration
β”‚   β”œβ”€β”€ packages/               # Individual package documentation
β”‚   β”œβ”€β”€ public/images/          # Brand assets and static files
β”‚   └── *.md                    # Getting started, philosophy, cheat sheets
β”‚
β”œβ”€β”€ skills/logosdx/             # Claude Code skill with package reference guides
β”‚   β”œβ”€β”€ SKILL.md               # Skill definition and routing
β”‚   └── references/            # Per-package API reference files
β”œβ”€β”€ scripts/                    # Build, documentation, and workflow scripts
β”œβ”€β”€ internals/                  # Internal utilities and templates
β”œβ”€β”€ typedoc/                    # Generated API documentation
└── CLAUDE.md                   # This file - development guidance

Read the full file on GitHub Β· 367 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. 2mo ago First seen Β· 367 lines Β· 3,007 tokens per session scan A bd4e649b68bc

Subscribe to this mod's changes

monorepo CLAUDE.md is an instructions file published in the GitHub repository logosdx/monorepo (7 stars, last pushed 8d ago), licensed BSD-3-Clause. It adds 3,007 tokens to every session, about $0.0120 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

monorepo CLAUDE.md compared with instructions from other repositories

monorepo CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
monorepo CLAUDE.mdlogosdx/monorepoInstructions file78d agoBSD-3-ClauseA3,007Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode