Borrowing it
Nothing to install: this file belongs to abhichandra21/Promptheus. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/abhichandra21/Promptheus/main/GEMINI.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/gemini-md)<a href="https://agentmods.dev/instructions/abhichandra21/promptheus/gemini-md"><img src="https://agentmods.dev/badge/instructions/abhichandra21/promptheus/gemini-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.
<a href="https://agentmods.dev/instructions/abhichandra21/promptheus/gemini-md"><img src="https://agentmods.dev/badge/instructions/abhichandra21/promptheus/gemini-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01276 | $0.01276 |
| Opus 5.5 | $0.00510 | $0.00510 |
| Sonnet 5.5 | $0.00255 | $0.00255 |
| Haiku 4.5 | $0.00128 | $0.00128 |
Grade A, and why
Promptheus GEMINI.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 2mo 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Promptheus Project Context
This document provides a comprehensive overview of the Promptheus project, its architecture, and development conventions to be used as instructional context.
1. Project Overview
Promptheus is a sophisticated, AI-powered command-line interface (CLI) tool written in Python. Its primary purpose is to help users craft and refine prompts. The tool takes a user's initial prompt and, through a series of AI-driven steps, outputs a better, more effective prompt for the user to then take and use with any Large Language Model (LLM).
Core Features:
- Multi-Provider Support: It uses LLM backends (Google, Anthropic Claude, OpenAI, Groq, Qwen, GLM) for its internal refinement process.
- Adaptive Interaction: The tool intelligently detects the user's task type:
- Generation Tasks: It offers to ask clarifying questions to add detail.
- Analysis Tasks: It performs an automatic, non-interactive "light refinement" to improve the prompt's clarity.
- Iterative Refinement: Users can "tweak" a generated prompt with natural language commands in an interactive loop.
- Rich Interactive UI: The interface is built with
richandquestionary, providing a polished and user-friendly experience. - Flexible Configuration: Configuration is handled via a clear hierarchy: CLI arguments (
--provider), environment variables (PROMPTHEUS_PROVIDER), and.envfiles. - Prompt History: All refined prompts are automatically saved to a history file for later reference and reuse.
- Subcommand Interface: Provides dedicated subcommands for utility functions like
list-models,validate, andhistoryfor a clean and modern CLI experience. - Dynamic Model Discovery: Model information is dynamically fetched from the models.dev API and cached locally for 24 hours.
Architecture:
The project follows a modular and modern Python architecture:
src/promptheus/main.py: The main application entry point. It handles parsing command-line arguments, orchestrates the refinement workflow, and manages the user interface.src/promptheus/cli.py: Defines the entire command-line interface, including all subcommands and their arguments, using Python'sargparsemodule.src/promptheus/commands.py: Implements the logic for the utility subcommands (list-models,validate,template,history).src/promptheus/config.py: A dedicated configuration manager that detects and validates API keys and settings from environment variables and.envfiles. It usesproviders.jsonfor provider-specific metadata.src/promptheus/providers.py: The core abstraction layer. It defines anLLMProviderabstract base class and concrete implementations (GeminiProvider,AnthropicProvider,OpenAICompatibleProvider, etc.).src/promptheus/prompts.py: Stores the system instruction templates that guide the internal LLM calls for question generation, refinement, and tweaking.src/promptheus/history.py: Manages persistent storage of prompt history with timestamp tracking.
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.
- 2mo ago First seen · 84 lines · 1,276 tokens per session scan A 507b95fc3bd3
Promptheus GEMINI.md is an instructions file published in the GitHub repository abhichandra21/Promptheus (17 stars, last pushed 24d ago), licensed MIT. It adds 1,276 tokens to every session, about $0.0051 per session on Opus 5.5. 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.
Promptheus GEMINI.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Promptheus GEMINI.mdabhichandra21/Promptheus | Instructions file | 17 | 24d ago | MIT | A | 1,276 | Gemini CLI |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |