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/AGENTS.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/agents-md)<a href="https://agentmods.dev/instructions/abhichandra21/promptheus/agents-md"><img src="https://agentmods.dev/badge/instructions/abhichandra21/promptheus/agents-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/agents-md"><img src="https://agentmods.dev/badge/instructions/abhichandra21/promptheus/agents-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 | $0.01303 | $0.01303 |
| Opus 5.5 | $0.00521 | $0.00521 |
| Sonnet 5.5 | $0.00261 | $0.00261 |
| Haiku 4.5 | $0.00130 | $0.00130 |
Grade A, and why
Promptheus AGENTS.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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
Runtime code lives under src/promptheus/. main.py owns the CLI entry point, providers.py wraps the adapters for multiple LLM providers (Gemini, Claude, OpenAI, Groq, Qwen, GLM), config.py manages environment-driven settings, and history.py persists prompt sessions. Shared assets (e.g., models.json, logging_config.py, utils.py) sit alongside. Tests mirror this layout in tests/, while helper tools such as sample_prompts.txt remain at the repository root. Add new runtime modules inside src/promptheus/ and keep provider-specific helpers beside existing integrations to simplify discovery.
Build, Test, and Development Commands
Install dependencies in editable mode before contributing:
pip install -e .[dev]
pip install -r requirements.txt # extras for env_validator
Run the CLI locally with either binary or module syntax:
promptheus "Draft an onboarding email"
python -m promptheus.main --skip-questions "Smoke test"
# Quiet mode for scripting (clean stdout/stderr separation)
promptheus "Generate a report" > output.txt # Auto-quiet when piping
promptheus "Write code" | cat # Auto-quiet when piping
# Different output formats
promptheus -o json "Create function" | jq .
promptheus -o plain "Write haiku"
Validate credentials before hitting remote APIs:
promptheus validate --providers google
promptheus validate --test-connection # to test actual API connectivity
Coding Style & Naming Conventions
Target Python 3.8+ with four-space indentation, snake_case for functions/variables, and CapWords for classes. Mirror existing type hints (see main.py) and keep modules under ~300 lines by extracting helpers where needed. Format with black ., keep imports sorted, and align terminal output with the rich styles already used in the CLI panels/table helpers.
Testing Guidelines
Tests live in tests/ and follow the test_<module>.py naming pattern. Prefer fast, offline unit tests that stub provider calls rather than exercising live APIs. Run pytest -q before sending a PR, and supplement with a manual CLI smoke test (promptheus --skip-questions "Smoke test") when you touch interactive flows or history features.
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 · 103 lines · 1,303 tokens per session scan A 769042287cdc
Promptheus AGENTS.md is an instructions file published in the GitHub repository abhichandra21/Promptheus (17 stars, last pushed 24d ago), licensed MIT. It adds 1,303 tokens to every session, about $0.0052 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 AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Promptheus AGENTS.mdabhichandra21/Promptheus | Instructions file | 17 | 24d ago | MIT | A | 1,303 | Codex, OpenCode |
| 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 |