What is SBK AGENTS.md?

A repository guide for SBK, a Java program that measures the performance of S3-compatible storage, message queues, file systems, and databases. It tells coding agents where things are and how to build and verify changes.

Use it when changing SBK, running its builds or checks, or adding benchmark work for a storage system or message queue.

It prevents agents from guessing the repository layout, supported targets, or verification commands. This makes work on benchmark code more consistent across different coding tools.

How kmgowda/SBK configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to kmgowda/SBK. 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/kmgowda/SBK/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/kmgowda/SBK

Made for: Codex, OpenCode.

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/kmgowda/sbk/agents-md/github.svg)](https://agentmods.dev/instructions/kmgowda/sbk/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/kmgowda/sbk/agents-md"><img src="https://agentmods.dev/badge/instructions/kmgowda/sbk/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.

Your own site · 80×15

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

Per session 5,725 This file is loaded in full into every session.

When invoked 5,725 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	$0.05725	$0.05725
Opus 5.5	$0.02290	$0.02290
Sonnet 5.5	$0.01145	$0.01145
Haiku 4.5	$0.00573	$0.00573

Measured yesterday against content hash 75855bba1cef, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

SBK 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 yesterday.

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.

AGENTS.md · 497 lines

How it starts

The opening of the file, as written. The whole thing — 497 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — AI Agent Guide for the SBK Repository

Universal entry point for all AI agents. This file is the standard entry point for AI coding agents (Devin, Claude Code, Cursor, GitHub Copilot, Continue, Aider, OpenAI Codex, Windsurf, etc.) working in this repository. It tells the agent what SBK is, how to build and verify it, what conventions to follow, where things live, and what the common gotchas are.

Agent-specific configurations:

Devin: See .devin/skills/ for executable skills

Cursor: See .cursor/rules/sbk.mdc; .cursorrules is the legacy pointer

Aider: See .aider.conf.yml for Aider configuration

Codex and Windsurf: consume this root AGENTS.md directly

Benchmark execution: any agent may use the portable .devin/skills/sbk-benchmark-runner/ and .devin/skills/sbk-distributed-benchmark-runner/ knowledge packs

Humans: see README.md for the end-user manual and docs/sbk-internals.md for the internal design.

1. What this repository is

SBK (Storage Benchmark Kit) is a Java framework for benchmarking any S3-compatible / message-queue / file-system / database storage. It runs identical measurement code against any backend via a small pluggable driver SPI.

Languages. Java only (no Kotlin, no Scala). Build with Gradle (wrapper in tree: ./gradlew). JDK 25 required.
Modules. 7 core modules + 52 enabled storage drivers. The source tree also contains disabled drivers and a driver template. Each module is a Gradle subproject.
License. Apache 2.0.
Branch model. Trunk-based; PRs target master.

Module map (memorise this)

Module	Role	When you edit it
`perl/`	PerL — Performance Logger library (lock-free queues, latency windows, percentile math). Heart of the framework.	Rarely. Only when changing core measurement behaviour.
`sbk-web-console/`	Independent Local Web Console runtime (HTTP server/client, protocol DTOs, UI resources).	When changing shared WebLogger transport or browser behavior.
`sbk-api/`	The benchmark harness. Defines `Storage<T>` SPI, `RWLogger` SPI, `SbkBenchmark`, `Sbk` main bootstrap.	When changing the harness, CLI flags, the SPI, or how loggers work.
`sbm/`	SBM — Storage Benchmark Monitor (gRPC aggregator on port 9717).	When changing distributed aggregation.
`sbk-yal/`	YML-driven launcher (single-node).	Rarely.
`sbk-gem/`	SBK-GEM — SSH-based distributed launcher.	When changing the multi-host orchestration.
`sbk-gem-yal/`	YML-driven SBK-GEM.	Rarely.
`drivers/<name>/`	One subdirectory per storage backend. 52 are enabled in the aggregate build; disabled drivers and a template also remain in tree.	When adding or fixing a driver. This is the most common change.

Read the full file on GitHub · 497 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.

yesterday First seen · 497 lines · 5,725 tokens per session scan A 75855bba1cef

Subscribe to this mod's changes

SBK AGENTS.md is an instructions file published in the GitHub repository kmgowda/SBK (36 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 5,725 tokens to every session, about $0.0229 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 2026-11-07.

Analytics and metrics HDFS Java Languages distributed-storage dockers filesystem grafana kafka

SBK AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
SBK AGENTS.mdkmgowda/SBK	Instructions file	36	1mo ago	Apache-2.0	A	5,725	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	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	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

SBK: Instructions file for Codex