gwt-zsh: Instructions file for Claude Code

CLAUDE.md

gwt-zsh CLAUDE.md is an instructions file for Claude Code from aasimsani/gwt-zsh. It costs 890 tokens per session, scanned A, original, MIT.

Development instructions for the gwt-zsh project, a Z shell tool. They define commit naming, testing, releases, and interactive interface conventions.

In plain words
What is it for?
Use them when developing gwt-zsh, including writing conventional commits, running zunit tests, meeting the stated coverage requirement, and following the release workflow.
Why use it?
They give an agent project-specific rules for making changes, checking them, and preparing releases consistently.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is aasimsani/gwt-zsh's own configuration. It tells Claude Code how to work on gwt-zsh 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 gwt-zsh configures →

Reuse

Borrowing it

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

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 gwt-zsh CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/aasimsani/gwt-zsh/claude-md"><img src="https://agentmods.dev/badge/instructions/aasimsani/gwt-zsh/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 890 This file is loaded in full into every session.
When invoked 890 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 $0.00890 $0.00890
Opus 5 $0.00445 $0.00445
Sonnet 5 $0.00178 $0.00178
Haiku 4.5 $0.00089 $0.00089

Measured 9d ago against content hash d5a39871675b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

gwt-zsh 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 · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GWT-ZSH Development Guidelines

Conventional Commits

Use conventional commit format for all commits:

<type>(<scope>): <description>

[optional body]

Types

  • feat: New feature (triggers release)
  • fix: Bug fix (triggers release)
  • docs: Documentation only
  • test: Adding/updating tests
  • refactor: Code change that neither fixes a bug nor adds a feature
  • chore: Maintenance tasks

Examples

feat(prune): add interactive worktree pruning
fix(config): handle empty directory list
docs: update README with new flags
test: add coverage for --list flag

Release Workflow

Release on every feature commit:

  1. After merging a feat or fix commit to main
  2. Run the release script: ./scripts/release.zsh <version>
  3. Version bump follows semver:
    • feat -> minor version bump (1.0.0 -> 1.1.0)
    • fix -> patch version bump (1.0.0 -> 1.0.1)

Testing

  • Run tests before committing: zunit
  • Coverage threshold: 95%
  • Pre-commit hook enforces tests: git config core.hooksPath .githooks

UI/UX Guidelines

Interactive Menus

Always use fzf for interactive selection menus with fallback for when fzf is not installed:

if command -v fzf &> /dev/null; then
    # fzf version with multi-select, colors, etc.
    selected=$(printf '%s\n' "${options[@]}" | fzf --multi \
        --header="Header text" \
        --prompt="❯ " \
        --pointer="▶" \
        --marker="✓" \
        --color="prompt:cyan,pointer:green,marker:green,header:dim" \
        --reverse \
        --height=50%)
else
    # Fallback to numbered selection
    # ... basic numbered input
fi

Terminal Colors

Use ZSH's print -P with format codes:

  • %F{green} / %f - Foreground color
  • %B / %b - Bold
  • %F{240} - Dim gray
  • Symbols: (exists), (missing), (success), (prompt)

Architecture

Navigation System

gwt provides two navigation mechanisms for worktree chains:

Command Function How it works
gwt .. / gwt --base _gwt_navigate_base() Reads gwt.baseWorktreePath from worktree-local git config
gwt ... / gwt --root _gwt_navigate_root() Uses git rev-parse --git-common-dir to find main worktree

Read the full file on GitHub · 103 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. 9d ago First seen · 103 lines · 890 tokens per session scan A d5a39871675b

Subscribe to this mod's changes

gwt-zsh CLAUDE.md is an instructions file published in the GitHub repository aasimsani/gwt-zsh (11 stars, last pushed 3mo ago), licensed MIT. It adds 890 tokens to every session, about $0.0044 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

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

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 · 3,735 tokens