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/welshwandering/cwtch/claude-mdgit clone --depth 1 https://github.com/welshwandering/cwtchWrote 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/welshwandering/cwtch/claude-md)<a href="https://agentmods.dev/instructions/welshwandering/cwtch/claude-md"><img src="https://agentmods.dev/badge/instructions/welshwandering/cwtch/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 | $0.01129 | $0.01129 |
| Opus 5 | $0.00564 | $0.00564 |
| Sonnet 5 | $0.00226 | $0.00226 |
| Haiku 4.5 | $0.00113 | $0.00113 |
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 4d 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) 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
securitycommand for Keychain access) - Dependencies:
jqfor JSON parsing,yqfor 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
- Profiles are thin — Store only credentials (
.credentialor.apikey) - Configuration is declarative — Defined in
~/.cwtch/Cwtchfile - Sources merge via namespaces — Multiple repos coexist as
/namespace/command - 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
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.
- 4d ago First seen · 130 lines · 1,129 tokens per session scan B 7f9dfe9ccd5e
cwtch CLAUDE.md is an instructions file published in the GitHub repository welshwandering/cwtch (14 stars, last pushed 6mo ago), licensed MIT. It adds 1,129 tokens to every session, about $0.0056 per session on Opus 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.
Other instructions, from other repositories
Claude-PHP-SDK copilot-instructions.md
Instructions for claude-php/Claude-PHP-SDK, covering copilot instructions for claude php sdk, project goals, architecture & core components, directory structure (to be created) and key architectural patterns.
rmm-skills CLAUDE.md
Instructions for DeusMaximus/rmm-skills, covering rmm skills for claude — project guide, what this project is, project structure, key conventions and yaml frontmatter (skill.md files).
agentic-ai-learning-journey CLAUDE.md
Instructions for JSchOBL/agentic-ai-learning-journey, covering agentic ai learning journey, layout, conventions, non-negotiable and gotchas.
rubber-duckie CLAUDE.md
Instructions for AlexandrosGounis/rubber-duckie, covering claude.md, project, commands, architecture and startup / onboarding flow.
claude-code-tracker CLAUDE.md
Claude Code instructions for Njengah/claude-code-tracker, covering claude code session tracker, stack, commands, key files and workflows.
outside-dave CLAUDE.md
Claude Code instructions for jon-greeff-katsini/outside-dave, covering claude.md, what this repository is, layout, how the skills relate and writing or editing a skill.