What is SutroYaro GEMINI.md?

Research-workspace instructions for the Sutro Group, a study group investigating energy-efficient AI training. They define its experiment process, records of established findings, benchmark task, and cache-related efficiency measure.

Use them when planning or running experiments on the sparse-parity benchmark, measuring average reuse distance, recording discoveries, or coordinating research tasks.

They help researchers and agents follow the lab's process and avoid repeating experiments whose results are already recorded.

How cybertronai/SutroYaro configures Gemini CLI

Reuse

Borrowing it

Nothing to install: this file belongs to cybertronai/SutroYaro. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/cybertronai/SutroYaro/main/GEMINI.md

Clone the repo

git clone --depth 1 https://github.com/cybertronai/SutroYaro

Made for: Gemini CLI.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/cybertronai/sutroyaro/gemini-md/github.svg)](https://agentmods.dev/instructions/cybertronai/sutroyaro/gemini-md)

Your own site

<a href="https://agentmods.dev/instructions/cybertronai/sutroyaro/gemini-md"><img src="https://agentmods.dev/badge/instructions/cybertronai/sutroyaro/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/cybertronai/sutroyaro/gemini-md"><img src="https://agentmods.dev/badge/instructions/cybertronai/sutroyaro/gemini-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,086 This file is loaded in full into every session.

When invoked 2,086 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.02086	$0.02086
Opus 5.5	$0.00834	$0.00834
Sonnet 5.5	$0.00417	$0.00417
Haiku 4.5	$0.00209	$0.00209

Measured 1mo ago against content hash 688d569116e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

SutroYaro 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 1mo 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.

GEMINI.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GEMINI.md - Sutro Group Research Workspace

Project Context

This is a research workspace for the Sutro Group, a study group exploring energy-efficient AI training. The group meets weekly at South Park Commons in San Francisco.

Read These First

LAB.md — Protocol for running experiments (templates, lifecycle, rules)
AGENT.md — Machine-executable experiment loop for autonomous sessions
DISCOVERIES.md — What's proven so far (read before every experiment)
CONTRIBUTING.md — How external contributors submit experiments and findings
TODO.md — Open research tasks
docs/tasks/INDEX.md — Current task tracker with priorities
docs/research/survey.md — Practitioner's Field Guide ranking all 36 experiments
docs/research/peer-research-protocol.md — Full design doc for multi-researcher autonomous research

Core Concepts

Sparse Parity: The benchmark task — learn XOR/parity from random {-1,+1} inputs. n=20 bits, k=3 secret, 17 noise. The "drosophila" of energy-efficient training.
Average Reuse Distance (ARD): Proxy metric for energy efficiency. Small ARD = data stays in cache = cheap. Large ARD = expensive external memory access.
Data Movement Complexity (DMC): Better proxy metric (Ding et al., arXiv:2312.14441). DMC = sum of sqrt(stack_distance) for all float accesses. Tracks alongside ARD in MemTracker. Baseline: ARD 4,104 / DMC 300,298.
Cache Energy Model: register 5pJ, L1 (64KB) 20pJ, L2 (256KB) 100pJ, HBM 640pJ per float access (Bill Dally numbers).
TrackedArray / Auto DMD: TrackedArray wraps numpy arrays so every operation (ufuncs, indexing, slicing) auto-records reads and writes on an LRUStackTracker. Removes manual instrumentation errors. See docs/research/tracked-numpy.md.

Current Best Methods

Method	Time (n=20/k=3)	ARD	DMC	Notes
KM-min (1 sample)	~0.001s	20	3,578	New DMC leader. 1 influence sample suffices for parity.
GF(2) Gaussian Elimination	509 us	~420	~203K	240x faster than SGD, k-independent. Auto-tracked via TrackedArray; old harness reported 8,607.
KM Influence Estimation	0.001-0.006s	92	20,633	ARD leader. 5 influence samples per bit.
SMT Backtracking	0.002s	3,360	348,336	Constraint satisfaction approach
SGD (baseline)	0.12s	8,504	1,278,460	LR=0.1, batch=32, hidden=200

Read the full file on GitHub · 153 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.

1mo ago First seen · 153 lines · 2,086 tokens per session scan A 688d569116e8

Subscribe to this mod's changes

SutroYaro GEMINI.md is an instructions file published in the GitHub repository cybertronai/SutroYaro (17 stars, last pushed 5mo ago), licensed Unlicense. It adds 2,086 tokens to every session, about $0.0083 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.

Research Scientific ai-research energy-efficient-training machine-learning pure-python sparse-parity

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

SutroYaro: Instructions file for Gemini CLI

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

GEMINI.md - Sutro Group Research Workspace

Project Context

Read These First

Core Concepts

Current Best Methods

What this file has done since we first saw it

Other instructions, from other repositories

vscode buildNext.instructions.md

next.js AGENTS.md

vscode oss-third-party-notices.instructions.md

langchain AGENTS.md

vscode copilot-instructions.md

vscode model-prompts.instructions.md