agentmods.dev

sbk-benchmark-runner

sbk-benchmark-runner is a skill for Codex from kmgowda/SBK. It costs 104 tokens per session (991 once invoked), scanned A, original, Apache-2.0.

Plan, configure, run, and interpret single-load-generator Storage Benchmark Kit benchmarks with SBK or SBK-YAL. Use when an agent must select a local or service-backed driver, discover current options, create a reproducible CLI or YML workload, run a smoke/performance test, use…

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions AGENTS.md; $skill-name invocation.

not rated 36repo 1mo ago A scan 104 tokens original Apache-2.0
Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kmgowda/sbk/sbk-benchmark-runner
View source ↗ kmgowda/SBK kmgowda.github.io
Install

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.

Any agent
npx skills add kmgowda/SBK --skill sbk-benchmark-runner
Clone the repo
git clone --depth 1 https://github.com/kmgowda/SBK

Made for: Codex.

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.

agentmods badge for sbk-benchmark-runner

README.md
[![agentmods](https://agentmods.dev/badge/skills/kmgowda/sbk/sbk-benchmark-runner/github.svg)](https://agentmods.dev/skills/kmgowda/sbk/sbk-benchmark-runner)
Your own site
<a href="https://agentmods.dev/skills/kmgowda/sbk/sbk-benchmark-runner"><img src="https://agentmods.dev/badge/skills/kmgowda/sbk/sbk-benchmark-runner/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.

agentmods 80×15 button for sbk-benchmark-runner

Your own site · 80×15
<a href="https://agentmods.dev/skills/kmgowda/sbk/sbk-benchmark-runner"><img src="https://agentmods.dev/badge/skills/kmgowda/sbk/sbk-benchmark-runner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 991 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00104 $0.00991
Opus 5.5 $0.00042 $0.00396
Sonnet 5.5 $0.00021 $0.00198
Haiku 4.5 $0.00010 $0.00099

Measured today against content hash 86fd42330519, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sbk-benchmark-runner 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 today.

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.

.devin/skills/sbk-benchmark-runner/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SBK Benchmark Runner

Follow the repository-wide safety and verification rules in AGENTS.md. If diagnosis leads to a proposed code change, consult docs/HOT_PATHS.md before editing any sensitive reader, writer, driver-operation, PerL, logger-forwarding, or SBM path and obey its explicit human-approval gate. Use the installed distribution at ./build/install/sbk/bin/. Treat generated -help output and the selected driver's README as authoritative; options vary by driver and logger.

Select the execution model

  1. Use sbk for one load-generator process configured on the command line.
  2. Use sbk-yal for the same process configured from a reusable YML file.
  3. A backend reached over the network still uses ordinary sbk or sbk-yal when only one load-generator host is required.
  4. Use $sbk-distributed-benchmark-runner only for multiple load-generator hosts or manual aggregation through SBM.

Read driver-connectivity.md before choosing a driver. Read single-node-workflows.md for commands and YML examples. Read methodology-and-results.md before making performance claims.

For Dell ECS/ObjectScale, also read the repository-level drivers/minio/docs/ECS_OBS_AGENT_RUNBOOK.md and drivers/minio/docs/ECS_OBS_BENCHMARK_RUNBOOK.md completely before constructing or executing a workload.

Run safely

  1. Confirm JDK 25 and build the distribution when it is absent or stale: ./gradlew installDist.
  2. Discover options without guessing:
    • ./build/install/sbk/bin/sbk -help
    • ./build/install/sbk/bin/sbk -class <driver> -help
    • add -out <logger> before -help for logger options.
  3. Read drivers/<driver>/README.md and inspect the driver's checked-in properties file for defaults.
  4. Verify prerequisites: target path or service, credentials, permissions, network route, free space, and cleanup policy.
  5. Run a short, bounded smoke test first. Prefer a dedicated test namespace, bucket, topic, table, or file.
  6. Run the measured workload multiple times, preserving the exact command/YML, SBK version, JDK version, host facts, backend version, and raw output.
  7. Reject or qualify a run containing I/O errors, timeouts, invalid latencies, unexpected discarded latencies, missing records, or target-side failures.

Read the full file on GitHub · 81 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. today First seen · 81 lines · 104 tokens per session scan A 86fd42330519

Subscribe to this mod's changes

sbk-benchmark-runner is a skill published in the GitHub repository kmgowda/SBK (36 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 104 tokens to every session and 991 once invoked, about $0.0004 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.

HDFSPlanningTestingdistributed-storagedockersfilesystemgrafanakafka
Related

sbk-benchmark-runner compared with skills from other repositories

sbk-benchmark-runner next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
sbk-benchmark-runnerkmgowda/SBKSkill361mo agoApache-2.0A104Codex
analyzing-github-ci-performanceTracer-Cloud/opensreSkill13kyesterdayApache-2.0A67Claude Code, Codex
fixing-github-security-alertsTracer-Cloud/opensreSkill13kyesterdayApache-2.0A30Claude Code, Codex
scheduling-github-ci-repairsTracer-Cloud/opensreSkill13kyesterdayApache-2.0A56Claude Code, Codex
onboarding-github-ciTracer-Cloud/opensreSkill13kyesterdayApache-2.0A46Claude Code, Codex
operating-github-ci-fixerTracer-Cloud/opensreSkill13kyesterdayApache-2.0A48Claude Code, Codex
operating-github-security-fixerTracer-Cloud/opensreSkill13kyesterdayApache-2.0A66Claude Code, Codex