What is par_gpt CLAUDE.md?

Project instructions for PAR GPT, a command-line program for talking to different AI language models. It can work as a basic chat tool or as an agent that loads tools when needed.

Use them when setting up the project, updating dependencies, running formatting, linting, type checks, tests, packaging, or its Docker-based code sandbox.

They give coding agents the project’s setup, package manager, language versions, and required checks before changes are committed.

How paulrobello/par_gpt configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to paulrobello/par_gpt. 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/paulrobello/par_gpt/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/paulrobello/par_gpt

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/paulrobello/par_gpt/claude-md/github.svg)](https://agentmods.dev/instructions/paulrobello/par_gpt/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/paulrobello/par_gpt/claude-md"><img src="https://agentmods.dev/badge/instructions/paulrobello/par_gpt/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/paulrobello/par_gpt/claude-md"><img src="https://agentmods.dev/badge/instructions/paulrobello/par_gpt/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,557 This file is loaded in full into every session.

When invoked 1,557 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.

Model	Per session	Once invoked
Fable 5.1	$0.01557	$0.01557
Opus 5	$0.00779	$0.00779
Sonnet 5	$0.00311	$0.00311
Haiku 4.5	$0.00156	$0.00156

Measured 8d ago against content hash 35d94c52d84b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

par_gpt 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 8d 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 · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 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

PAR GPT is a flexible command-line interface for interacting with multiple AI language models. It operates in two modes: basic LLM mode and Agent mode with dynamic tool loading. Built with Python 3.12 or higher (3.13 recommended) using UV package manager, Typer for CLI, and Rich for terminal output.

Development Commands

Setup and Environment

make setup          # First-time setup with UV
make resetup        # Recreate virtual environment from scratch
make depsupdate     # Update all dependencies

Code Quality (Run Before Commits)

make checkall       # Format, lint, typecheck, and run tests - REQUIRED before commits
make format         # Format code with ruff
make lint           # Lint code with ruff
make typecheck      # Type check with pyright
make test           # Run the pytest test suite (tests live in tests/)
make pre-commit     # Run pre-commit hooks manually

Development Utilities

make sandbox        # Start Docker code sandbox container
make clean          # Clean build directories
make package        # Build the package

Command Invocation Tips

Instead of using echo "prompt" | uv run par_gpt agent use uv run par_gpt "prompt"

Development Patterns

Lazy Loading Architecture

PAR GPT uses a two-layer lazy loading system:

Generic Layer (par_utils.LazyImportManager):
- Thread-safe import caching
- Module and item-specific lazy loading
- Used directly in AI tools for simple imports
Application Layer (par_gpt.lazy_import_manager.PARGPTLazyImportManager):
- Extends the generic LazyImportManager
- Provides command-specific loading methods:
  - load_agent_imports() - For agent mode
  - load_basic_llm_imports() - For LLM mode
  - load_media_imports() - For image/TTS operations
  - And many more specialized loaders
- Used in CLI config and command infrastructure

Read the full file on GitHub · 206 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.

8d ago First seen · 206 lines · 1,557 tokens per session scan A 35d94c52d84b

Subscribe to this mod's changes

par_gpt CLAUDE.md is an instructions file published in the GitHub repository paulrobello/par_gpt (11 stars, last pushed 6d ago), licensed MIT. It adds 1,557 tokens to every session, about $0.0078 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.

agents ai cli

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

par_gpt: Instructions file for Claude Code