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.
npx agentmods add instructions/abhichandra21/promptheus/claude-mdgit clone --depth 1 https://github.com/abhichandra21/PromptheusWrote 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.
[](https://agentmods.dev/instructions/abhichandra21/promptheus/claude-md)<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>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 | $0.03686 | $0.03686 |
| Opus 5 | $0.01843 | $0.01843 |
| Sonnet 5 | $0.00737 | $0.00737 |
| Haiku 4.5 | $0.00369 | $0.00369 |
Grade A, and why
Promptheus CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 460 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Development Commands
Installation and Setup
# Install in development mode
pip install -e .
# Or use the traditional setup.py approach
python setup.py develop
Running the Application
# Run the CLI tool
promptheus "Your prompt here"
# Run via Python module
python -m promptheus.main "Your prompt here"
# Interactive mode (REPL-style)
promptheus
# Skip questions mode (improve prompt directly)
promptheus -s "Your prompt"
promptheus --skip-questions "Your prompt"
# Refine mode (force questions)
promptheus -r "Your prompt"
# Different output formats
promptheus -o plain "Your prompt" # Default: plain text
promptheus -o json "Your prompt" # JSON output
# Pipe integration examples
promptheus "Write a story" | claude exec # Chain with other AI tools
claude "$(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
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.
- 5d ago First seen · 460 lines · 3,686 tokens per session scan A 1620820d47ec
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.
Other instructions, from other repositories
nano-banana-image-skill CLAUDE.md
Instructions for Emily2040/nano-banana-image-skill, covering nano banana image skill, start here, repo intent, editing rules and preferred answer shape.
Awesome-Prompt-Engineering AGENTS.md
Instructions for natnew/Awesome-Prompt-Engineering, covering agents.md, repository north star, agent role, trust boundary and read order.
Awesome-Prompt-Engineering CLAUDE.md
Instructions for natnew/Awesome-Prompt-Engineering, covering claude.md, north star, claude's role, claude behaviour rule and always-loaded context.
minimax-h3-skill CLAUDE.md
Instructions for teskor-hub/minimax-h3-skill, covering minimax h3 skill — working notes, what this is, after every edit: hand over the push commands, where things live and three deliverables, kept in sync.
agi-in-md CLAUDE.md
Instructions for Cranot/agi-in-md, covering agi in md, the compression taxonomy, key results, foundation (rounds 1-24) and levels 8-13 (rounds 25-26).
comfy-prompt-studio AGENTS.md
Instructions for yxhpy/comfy-prompt-studio, covering agents.md - ai 代理配置文档, ai 提供商, 1. ollama (默认), 2. gemini and 提示词生成服务.