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/mdfranz/saruca/gemini-mdgit clone --depth 1 https://github.com/mdfranz/sarucaWrote 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/mdfranz/saruca/gemini-md)<a href="https://agentmods.dev/instructions/mdfranz/saruca/gemini-md"><img src="https://agentmods.dev/badge/instructions/mdfranz/saruca/gemini-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 | $0.02538 | $0.02538 |
| Opus 5 | $0.01269 | $0.01269 |
| Sonnet 5 | $0.00508 | $0.00508 |
| Haiku 4.5 | $0.00254 | $0.00254 |
Grade A, and why
saruca 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 3d 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 — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Core Instructions for Python
Python Coding Style
- Use Python or
jqto parse and analyze log files for initial exploration - For large files preview with hq and head if they are larger than 20MB
- Review existing Python code in the current directory before writing new code to solve problems.
- Use
uvto create virtual environments and install libraries. Maintain arequirements.txtfile. - Use
orjsoninstead of the built-injsonlibrary for better performance. - Use Python
polarsto convert JSON to parquet if needed. - Use Python
pandasfor statistical analysis if beneficial.
Instructions for Marimo
I am a specialized AI assistant designed to help create data science notebooks using marimo. I focus on creating clear, efficient, and reproducible data analysis workflows with marimo's reactive programming model.
If you make edits to the notebook, only edit the contents inside the function decorator with @app.cell. marimo will automatically handle adding the parameters and return statement of the function. For example, for each edit, just return:
@app.cell
def _():
<your code here>
return
Marimo fundamentals
Marimo is a reactive notebook that differs from traditional notebooks in key ways:
- Cells execute automatically when their dependencies change
- Variables cannot be redeclared across cells
- The notebook forms a directed acyclic graph (DAG)
- The last expression in a cell is automatically displayed
- UI elements are reactive and update the notebook automatically
Code Requirements
- All code must be complete and runnable
- Follow consistent coding style throughout
- Include descriptive variable names and helpful comments
- Import all modules in the first cell, always including
import marimo as mo - Never redeclare variables across cells
- Ensure no cycles in notebook dependency graph
- The last expression in a cell is automatically displayed, just like in Jupyter notebooks.
- Don't include comments in markdown cells
- Don't include comments in SQL cells
- Never define anything using
global.
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.
- 3d ago First seen · 380 lines · 2,538 tokens per session scan A f7930e856626
saruca GEMINI.md is an instructions file published in the GitHub repository mdfranz/saruca (1 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 2,538 tokens to every session, about $0.0127 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 2026-08-31.
Other instructions, from other repositories
PINA AGENTS.md
AGENTS.md instructions for PINA-org/PINA, covering pina — physics-informed neural architectures, quick reference, workflow: problem → model → solver → trainer, problem types and condition types.
OpenBioMed CLAUDE.md
Instructions for PharMolix/OpenBioMed, covering claude.md, project overview, key commands, environment setup and training.
cc-statistics CLAUDE.md
Instructions for androidZzT/cc-statistics, covering claude.md, project, setup, usage and architecture.
sciplot-academic copilot-instructions.md
Instructions for rippleshe/sciplot-academic, covering sciplot academic - github copilot 使用指南, 🚨 默认触发规则(最高优先级), 🔥 触发关键词(出现任何一个立即触发), 🔥 触发场景(满足任一立即触发) and 🔥 隐含触发(95% 触发).
PyAutoArray AGENTS.md
Instructions for PyAutoLabs/PyAutoArray, covering pyautoarray — agent instructions, what this repo is, related repos, architecture and quick commands.
FaST-LMM AGENTS.md
Instructions for fastlmm/FaST-LMM, covering coding notes for agents, general policies, cross-repository release coordination, numerical correctness and error handling.