para CLAUDE.md

para CLAUDE.md is an instructions file for coding agents from 2mawi2/para. It costs 3,272 tokens per session, scanned A, original, MIT.

Repository instructions for Para, a Rust tool that lets developers work on multiple features at the same time using Git worktrees. A worktree is a separate working folder connected to the same Git repository.

In plain words
What is it for?
Use them when developing Para to run its required checks, build its binaries, manage installation, and work with its Rust and MCP components.
Why use it?
They give coding agents consistent project-specific guidance for setup, building, formatting, linting, testing, and installation.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/2mawi2/para/claude-md
Clone the repo
git clone --depth 1 https://github.com/2mawi2/para

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 para CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/2mawi2/para/claude-md.svg)](https://agentmods.dev/instructions/2mawi2/para/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/2mawi2/para/claude-md"><img src="https://agentmods.dev/badge/instructions/2mawi2/para/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,272 This file is loaded in full into every session.
When invoked 3,272 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.03272 $0.03272
Opus 5 $0.01636 $0.01636
Sonnet 5 $0.00654 $0.00654
Haiku 4.5 $0.00327 $0.00327

Measured 3d ago against content hash bff5918f0546, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

para 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 3d 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 · 286 lines

How it starts

The opening of the file, as written. The whole thing — 286 lines — 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.

Project Overview

Para is a "Parallel IDE Workflow Helper" - a Rust implementation that enables developers to work on multiple features simultaneously using Git worktrees and their favorite IDEs. It's specifically designed for AI-assisted development workflows, allowing multiple Claude Code instances to work on different branches without conflicts.

Essential Development Commands

Setup and Testing

just test             # Run all checks (tests + linting + formatting) - ALWAYS use this
just test <filter>    # Run specific tests only (skips linting/formatting for speed)
                     # Examples: just test finish, just test integration, just test core::git
just lint             # Run clippy linting for all files
just fmt              # Auto-fix Rust formatting
just build            # Build debug binary (with bun/npm fallback for MCP server)
just build-release    # Build optimized release binary

Common Development Tasks

just install          # Install Rust para binary globally
just uninstall        # Remove para from system
just setup-hooks      # Configure git pre-commit/pre-push hooks
just status           # Check dependencies and project health
just clean            # Clean development artifacts
just release          # Create new release (patch version bump)

Testing Guidelines:

  • Always use just test for final verification (includes linting + formatting)
  • Use just test <filter> during development for faster iteration on specific tests
  • Use just lint to check linting on all modules
  • The just commands have clean, focused output - avoid raw cargo commands

TypeScript/MCP Testing

just test-ts          # Run TypeScript tests for MCP server
just lint-ts          # Run ESLint on TypeScript code
just fmt-ts           # Format TypeScript code

Architecture Overview

Modular Rust Design

src/
├── cli/              # Command-line interface, argument parsing, and command implementations
│   └── commands/     # Individual command implementations (start, finish, resume, etc.)
│       ├── mcp/      # MCP server management (init, strategies for finding servers)
│       ├── list/     # Session listing with formatters and analyzers
│       └── resume/   # Session resumption with context and task transformation
├── config/           # Configuration management, validation, and interactive wizard
├── core/             # Core business logic, session management, and IDE integration
│   ├── git/          # Git operations, worktree management, and repository handling
│   │   └── diff.rs   # Git diff calculation and statistics
│   └── status.rs     # Session status tracking and reporting
├── ui/               # Terminal UI components
│   └── monitor/      # Interactive session monitoring UI
│       ├── coordinator.rs    # Main UI coordination
│       ├── renderer.rs       # UI rendering logic
│       ├── state_manager.rs  # State management
│       └── actions.rs        # UI action handling
├── utils/            # Utility functions, error handling, and helper modules
│   └── validation.rs # Session name validation
└── main.rs           # Application entry point

Read the full file on GitHub · 286 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. 3d ago First seen · 286 lines · 3,272 tokens per session scan A bff5918f0546

Subscribe to this mod's changes

para CLAUDE.md is an instructions file published in the GitHub repository 2mawi2/para (19 stars, last pushed 11mo ago), licensed MIT. It adds 3,272 tokens to every session, about $0.0164 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 2026-09-01.