tuck: Instructions file for Claude Code

CLAUDE.md

tuck CLAUDE.md is an instructions file for Claude Code from Pranav-Karra-3301/tuck. It costs 3,791 tokens per session, scanned A, original, MIT.

Project instructions for Tuck, a TypeScript command-line tool for managing configuration files across computers with Git.

In plain words
What is it for?
Use them when developing Tuck's command-line features, configuration-file management, Git operations, or safety behavior.
Why use it?
They clarify what Tuck does and does not manage, along with its safety, backup, and technology expectations.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is Pranav-Karra-3301/tuck's own configuration. It tells Claude Code how to work on tuck 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 tuck configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import { prompts, logger } from '../ui/index.js';.

Reuse

Borrowing it

Nothing to install: this file belongs to Pranav-Karra-3301/tuck. 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/Pranav-Karra-3301/tuck/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Pranav-Karra-3301/tuck

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 tuck CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/pranav-karra-3301/tuck/claude-md/github.svg)](https://agentmods.dev/instructions/pranav-karra-3301/tuck/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/pranav-karra-3301/tuck/claude-md"><img src="https://agentmods.dev/badge/instructions/pranav-karra-3301/tuck/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 tuck CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/pranav-karra-3301/tuck/claude-md"><img src="https://agentmods.dev/badge/instructions/pranav-karra-3301/tuck/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,791 This file is loaded in full into every session.
When invoked 3,791 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 $0.03791 $0.03791
Opus 5 $0.01895 $0.01895
Sonnet 5 $0.00758 $0.00758
Haiku 4.5 $0.00379 $0.00379

Measured 9d ago against content hash 747600f7fcad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

tuck 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 · 468 lines

How it starts

The opening of the file, as written. The whole thing — 468 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - Claude Code Instructions for tuck

This file provides context and instructions for Claude Code when working on the tuck project.

Project Identity

tuck is a modern, beautiful dotfiles manager CLI built with TypeScript. It embodies the philosophy that developer tools should be:

  • Beautiful by default — Every interaction should feel polished and intentional
  • Safe above all else — Never lose data, always confirm destructive actions, create backups
  • Git-native — Leverage git's power while abstracting its complexity
  • Zero-config to start — Work out of the box, powerful when configured

What tuck IS:

  • A CLI tool for managing dotfiles across machines
  • A git repository manager specialized for configuration files
  • A cross-platform tool (macOS, Linux, Windows)
  • A beautiful, modern terminal experience

What tuck is NOT:

  • A general-purpose backup tool
  • A secrets manager (never store secrets in dotfiles)
  • A system configuration manager
  • A replacement for ansible/puppet/chef

Technical Stack

Runtime:     Node.js 18+ (ESM modules)
Language:    TypeScript 5.x (strict mode)
Package Mgr: pnpm 9+
CLI:         Commander.js
Prompts:     @clack/prompts
Styling:     chalk, boxen, ora, figures, log-symbols
Git:         simple-git
Files:       fs-extra, glob
Config:      cosmiconfig
Validation:  zod
Updates:     update-notifier
Testing:     Vitest
Build:       tsup

Directory Structure

src/
├── commands/     # CLI command implementations
│   ├── init.ts       # tuck init - Initialize tuck
│   ├── add.ts        # tuck add - Track a file
│   ├── remove.ts     # tuck remove - Untrack a file
│   ├── sync.ts       # tuck sync - Sync changes
│   ├── push.ts       # tuck push - Push to remote
│   ├── pull.ts       # tuck pull - Pull from remote
│   ├── restore.ts    # tuck restore - Restore to the system
│   ├── status.ts     # tuck status - Show status
│   ├── list.ts       # tuck list - List tracked files
│   ├── diff.ts       # tuck diff - Show differences
│   ├── config.ts     # tuck config - Manage configuration
│   ├── apply.ts      # tuck apply - Apply dotfiles from repo
│   ├── undo.ts       # tuck undo - Restore from Time Machine snapshots
│   ├── scan.ts       # tuck scan - Detect dotfiles on system
│   ├── secrets.ts    # tuck secrets - Manage secrets/placeholders
│   ├── encryption.ts # tuck encryption - Manage backup encryption
│   ├── doctor.ts     # tuck doctor - Health/safety diagnostics
│   ├── verify.ts     # tuck verify - Verify system/repo/manifest agree
│   ├── bundle.ts     # tuck bundle - Manage bundles (file groups)
│   ├── context.ts    # tuck context - Track AI agent configs
│   ├── mcp.ts        # tuck mcp - Model Context Protocol server
│   ├── preset.ts     # tuck preset - Apply/publish curated bundles
│   └── repo.ts       # tuck repo - Machine-local repo bindings
├── lib/          # Core library modules
│   ├── audit.ts        # Audit-log writing
│   ├── backup.ts       # Backup functionality
│   ├── binary.ts       # Binary file detection
│   ├── commandPath.ts  # Command/executable path resolution
│   ├── config.ts       # Configuration management
│   ├── detect.ts       # Dotfile detection and categorization
│   ├── doctor.ts       # Diagnostics engine
│   ├── fileTracking.ts # File tracking utilities
│   ├── files.ts        # File system operations
│   ├── git.ts          # Git operations wrapper
│   ├── github.ts       # GitHub CLI integration
│   ├── hooks.ts        # Pre/post hook execution
│   ├── jsonOutput.ts   # JSON envelope helpers
│   ├── manifest.ts     # File tracking manifest
│   ├── manifestFile.ts # Manifest file read/write
│   ├── materialize.ts  # Materialize templates/encrypted files on apply
│   ├── merge.ts        # Smart merging for shell/PowerShell files
│   ├── mergeConflicts.ts # Merge-conflict handling
│   ├── paths.ts        # Path utilities and resolution
│   ├── patternsRegistry.ts # Detection pattern registry
│   ├── platform.ts     # Cross-platform (incl. Windows) helpers
│   ├── providerSetup.ts # Git provider setup wizard
│   ├── remoteChecks.ts # Remote repository checks
│   ├── remoteSetup.ts  # Remote setup helpers
│   ├── repoScope.ts    # Repo-scoped tracking resolution
│   ├── state.ts        # Platform state dir (audit log, snapshots)
│   ├── stateModel.ts   # State model types/helpers
│   ├── template.ts     # Template rendering
│   ├── timemachine.ts  # Snapshot/time-machine backups
│   ├── trackPipeline.ts # Track pipeline orchestration
│   ├── tuckignore.ts   # .tuckignore file handling
│   ├── updater.ts      # Update notifications
│   ├── validation.ts   # Input validation utilities
│   ├── writeContext.ts # Sandboxed write context (--root)
│   ├── crypto/       # At-rest encryption (AES-256-GCM)
│   │   ├── encryption.ts     # Core AES-256-GCM/scrypt primitives
│   │   ├── fileEncryption.ts # File encrypt/decrypt
│   │   ├── manager.ts        # Encryption manager (setup/enable/rotate)
│   │   ├── index.ts          # Barrel exports
│   │   └── keystore/         # OS keystore backends
│   │       ├── fallback.ts       # Encrypted-file fallback keystore
│   │       ├── macos.ts          # macOS Keychain
│   │       ├── linux.ts          # Linux secret service
│   │       ├── windows.ts        # Windows credential store
│   │       ├── types.ts          # Keystore interface
│   │       └── index.ts          # Backend selection
│   ├── providers/    # Git provider implementations
│   │   ├── types.ts      # Provider interface definitions
│   │   ├── github.ts     # GitHub provider
│   │   ├── gitlab.ts     # GitLab provider
│   │   ├── custom.ts     # Custom/generic git provider
│   │   ├── local.ts      # Local-only (no remote) provider
│   │   └── index.ts      # Provider selection
│   ├── secretBackends/ # External secret manager backends
│   │   ├── onepassword.ts # 1Password backend
│   │   ├── bitwarden.ts   # Bitwarden backend
│   │   ├── pass.ts        # pass (GPG) backend
│   │   ├── local.ts       # Local backend
│   │   ├── mappings.ts    # Placeholder → backend path mappings
│   │   ├── resolver.ts    # Secret resolution
│   │   ├── cache.ts       # Resolution cache
│   │   ├── types.ts       # Backend interface
│   │   └── index.ts       # Backend selection
│   └── secrets/      # Secret detection and management
│       ├── scanner.ts    # Secret scanning logic
│       ├── patterns.ts   # Secret detection patterns
│       ├── redactor.ts   # Secret redaction utilities
│       ├── regexSafety.ts # ReDoS-safe regex guards
│       ├── store.ts      # Secure secret storage
│       ├── external.ts   # External secret manager integration
│       └── index.ts      # Barrel exports
├── ui/           # Terminal UI components
│   ├── banner.ts     # ASCII art and boxes
│   ├── logger.ts     # Styled logging
│   ├── prompts.ts    # Interactive prompts
│   ├── spinner.ts    # Loading spinners
│   ├── progress.ts   # Progress indicators
│   ├── table.ts      # Table formatting
│   ├── merge.ts      # Merge-conflict UI
│   └── theme.ts      # UI theme definitions
├── schemas/      # Zod validation schemas
│   ├── config.schema.ts        # Configuration schema
│   ├── manifest.schema.ts      # Manifest schema
│   ├── secrets.schema.ts       # Secrets schema
│   ├── repos.schema.ts         # Repo-bindings schema
│   ├── secretMappings.schema.ts # Secret-mappings schema
│   └── snapshot.schema.ts      # Snapshot schema
├── constants.ts  # App constants
├── types.ts      # TypeScript types
├── errors.ts     # Custom error classes
└── index.ts      # Entry point

Read the full file on GitHub · 468 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 · 468 lines · 3,791 tokens per session scan A 747600f7fcad

Subscribe to this mod's changes

tuck CLAUDE.md is an instructions file published in the GitHub repository Pranav-Karra-3301/tuck (15 stars, last pushed 1mo ago), licensed MIT. It adds 3,791 tokens to every session, about $0.0190 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