Promptheus CLAUDE.md

Promptheus CLAUDE.md is an instructions file for coding agents from abhichandra21/Promptheus. It costs 3,686 tokens per session, scanned A, original, MIT.

A repository instruction file for Promptheus, a command-line tool that improves written prompts by asking questions or refining them directly.

In plain words
What is it for?
Use it when developing or running Promptheus in interactive mode, skip-questions mode, refine mode, JSON or plain-text output, or shell pipelines.
Why use it?
It records how to install, run, test, and connect Promptheus to other command-line tools.

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/abhichandra21/promptheus/claude-md
Clone the repo
git clone --depth 1 https://github.com/abhichandra21/Promptheus

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 Promptheus CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/abhichandra21/promptheus/claude-md.svg)](https://agentmods.dev/instructions/abhichandra21/promptheus/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/abhichandra21/promptheus/claude-md"><img src="https://agentmods.dev/badge/instructions/abhichandra21/promptheus/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,686 This file is loaded in full into every session.
When invoked 3,686 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 5.1 $0.03686 $0.03686
Opus 5 $0.01843 $0.01843
Sonnet 5 $0.00737 $0.00737
Haiku 4.5 $0.00369 $0.00369

Measured 5d ago against content hash 1620820d47ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

Promptheus 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 5d 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 · 460 lines

How it starts

The opening of the file, as written. The whole thing — 460 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.

Development Commands

Installation and Setup

# Install in development mode
pip install -e .

# Or use the traditional setup.py approach
python setup.py develop

Running the Application

# Run the CLI tool
promptheus "Your prompt here"

# Run via Python module
python -m promptheus.main "Your prompt here"

# Interactive mode (REPL-style)
promptheus

# Skip questions mode (improve prompt directly)
promptheus -s "Your prompt"
promptheus --skip-questions "Your prompt"

# Refine mode (force questions)
promptheus -r "Your prompt"

# Different output formats
promptheus -o plain "Your prompt"   # Default: plain text
promptheus -o json "Your prompt"    # JSON output

# Pipe integration examples
promptheus "Write a story" | claude exec           # Chain with other AI tools
claude "$(promptheus 'Create a haiku')"            # Command substitution
promptheus "Explain Docker" | tee output.txt       # Save and display (auto-quiet)
echo "topic" | promptheus | cat > result.txt       # Chain transformations
promptheus -o json "schema" | jq '.prompt'         # JSON processing

Testing

# Run automated tests
pytest -q

# Manual smoke tests
promptheus --skip-questions "Test prompt"
python -m promptheus.main --skip-questions "Smoke test"

# Test different input methods
promptheus -f test_prompt.txt
promptheus @test_prompt.txt
cat test_prompt.txt | promptheus

# Environment validation
promptheus validate --providers gemini
promptheus validate --test-connection

Development Utilities

# Code formatting
black .

# Check for linting issues (if available)
python -m flake8 src/promptheus/ --ignore=E501,W503

# Type checking (if available)
python -m mypy src/promptheus/

Architecture Overview

Core Components

Main Application (src/promptheus/main.py)

  • Entry point and CLI interface using argparse
  • Implements adaptive interaction model that detects task types (analysis vs generation)
  • Handles interactive loop mode (REPL) for continuous prompt processing
  • Manages the question-answer-refinement workflow
  • Contains the core process_single_prompt() orchestrator function
  • Supports history commands: promptheus history, /history, /load <n>, /clear-history

Read the full file on GitHub · 460 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. 5d ago First seen · 460 lines · 3,686 tokens per session scan A 1620820d47ec

Subscribe to this mod's changes

Promptheus CLAUDE.md is an instructions file published in the GitHub repository abhichandra21/Promptheus (17 stars, last pushed 5mo ago), licensed MIT. It adds 3,686 tokens to every session, about $0.0184 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.