cwtch: Instructions file for Claude Code

CLAUDE.md

cwtch CLAUDE.md is an instructions file for Claude Code from welshwandering/cwtch. It costs 1,129 tokens per session, scanned B, original, MIT.

Project instructions for cwtch, a macOS command-line tool for managing Claude Code profiles and syncing their configuration from Git. It stores credentials in the macOS Keychain and uses Bash, jq, and yq.

In plain words
What is it for?
Use it to work on profile management, configuration validation, Git synchronization, installation, and tests for this macOS-only command-line tool.
Why use it?
It documents the platform limits, dependencies, repository structure, and main concepts an agent needs before changing the tool.

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 welshwandering/cwtch's own configuration. It tells Claude Code how to work on cwtch 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 cwtch configures →

Reuse

Borrowing it

Nothing to install: this file belongs to welshwandering/cwtch. 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/welshwandering/cwtch/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/welshwandering/cwtch

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 cwtch CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/welshwandering/cwtch/claude-md"><img src="https://agentmods.dev/badge/instructions/welshwandering/cwtch/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,129 This file is loaded in full into every session.
When invoked 1,129 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.01129 $0.01129
Opus 5.5 $0.00452 $0.00452
Sonnet 5.5 $0.00226 $0.00226
Haiku 4.5 $0.00113 $0.00113

Measured 2mo ago against content hash 7f9dfe9ccd5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

cwtch CLAUDE.md scanned grade B with 1 finding 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 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

│ └── .credential # OAuth token (chmod 600)
CLAUDE.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - cwtch

Overview

cwtch (Welsh: "cuddle/cozy nook") — Manage Claude Code profiles and sync configuration from Git.

Note: This project is not affiliated with, sponsored by, or endorsed by Anthropic PBC.

Platform: macOS only (tested on macOS Tahoe). Uses macOS Keychain for credential storage.

Tech Stack

  • Language: Bash
  • Platform: macOS (requires security command for Keychain access)
  • Dependencies: jq for JSON parsing, yq for YAML parsing
  • Standards: Doctrine Shell Guide

Repository Structure

cwtch/
├── .github/
│   └── workflows/ci.yml    # GitHub Actions CI (lint, test, e2e)
├── bin/
│   └── cwtch               # Main CLI entry point
├── lib/
│   ├── common.sh           # Shared functions, profile management
│   ├── config.sh           # Cwtchfile parsing and validation
│   └── sync.sh             # Git sync and namespace linking
├── scripts/
│   └── install.sh          # Manual installer
├── tests/
│   ├── helpers.bash        # Shared test utilities
│   ├── cwtch.bats          # Top-level CLI tests
│   ├── profile.bats        # Profile management tests
│   ├── config.bats         # Cwtchfile validation tests
│   └── sync.bats           # Sync functionality tests
└── docs/
    ├── profiles.md         # Profile management reference
    └── configuration.md    # Cwtchfile and sync reference

Architecture

Core Concepts

  1. Profiles are thin — Store only credentials (.credential or .apikey)
  2. Configuration is declarative — Defined in ~/.cwtch/Cwtchfile
  3. Sources merge via namespaces — Multiple repos coexist as /namespace/command
  4. Symlinks for instant updates — No copying, just linking

Directory Layout

~/.cwtch/
├── Cwtchfile              # Configuration (YAML)
├── .current               # Current profile name
├── profiles/{name}/       # Credentials only
│   └── .credential        # OAuth token (chmod 600)
└── sources/{repo}/        # Cloned repositories

~/.claude/                 # Built by cwtch sync
├── settings.json          # Merged settings
├── CLAUDE.md              # Symlink → source
├── commands/{namespace}/  # Symlink → source
├── agents/{namespace}/    # Symlink → source
└── hooks/{namespace}/     # Symlink → source

Read the full file on GitHub · 130 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 · 130 lines · 1,129 tokens per session scan B 7f9dfe9ccd5e

Subscribe to this mod's changes

cwtch CLAUDE.md is an instructions file published in the GitHub repository welshwandering/cwtch (14 stars, last pushed 8mo ago), licensed MIT. It adds 1,129 tokens to every session, about $0.0045 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). 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

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 · 9,715 tokens

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 · 7,461 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, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 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 · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,750 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens