agentmods.dev

schelk

A Linux-only command-line skill for repeatable benchmarking on large stateful datasets, such as database data directories. It keeps a clean baseline disk, runs tests on a separate working disk, and restores only changed blocks.

In plain words
What is it for?
It is for installing and configuring schelk, preparing baseline storage, running benchmark-and-recovery cycles, promoting a new baseline, and recovering from unsafe states.
Why use it?
It makes repeated benchmarks faster while avoiding copy-on-write or overlay layers, which can distort or complicate storage tests.

Skill for Claude CodeCodex

51 7d ago B scan 88 tokens original Apache-2.0
View the source file tempoxyz/schelk
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.

agentmods
npx agentmods add skills/tempoxyz/schelk/docs
Any agent
npx skills add tempoxyz/schelk --skill docs
Clone the repo
git clone --depth 1 https://github.com/tempoxyz/schelk

Made for: Claude Code, Codex.

Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,233 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
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 $0.00088 $0.02233
Opus 5 $0.00044 $0.01117
Sonnet 5 $0.00018 $0.00447
Haiku 4.5 $0.00009 $0.00223

Measured 2d ago against content hash 3a38faa78f9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

schelk scanned grade B with 1 finding 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 2d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

sudo modprobe brd rd_size=4194304
docs/SKILL.md · 285 lines

How it starts

The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.

schelk

schelk is a Linux-only benchmarking helper for large on-disk datasets such as database or reth datadirs. It keeps a pristine virgin block device, runs benchmarks on a scratch block device, and uses dm-era metadata on a ramdisk to learn which blocks changed. Recovery then copies only the changed blocks from virgin back to scratch, so the benchmark loop is fast without running on top of CoW or overlay machinery.

Use this skill when the user wants to install schelk, prepare baseline volumes, run the mount -> benchmark -> recover loop, promote a new baseline, or recover from an unsafe state.

Start From The URL

Do not assume the repository is already cloned locally.

If the user points you at this skill by URL, treat this as the entrypoint:

If the repo is not available locally and you need the source or docs, clone it first:

git clone https://github.com/tempoxyz/schelk.git
cd schelk

Read These First

When behavior is unclear, prefer these project documents over guesswork:

Core Rules

  • Treat init-new, init-from, full-recover, and promote as destructive.
  • Do not guess device paths. Have the user confirm the exact --virgin, --scratch, --ramdisk, and --mount-point before destructive commands.
  • Refuse to proceed on non-Linux hosts. This repository intentionally fails to build on macOS and Windows.
  • All operational commands require root privileges.
  • Do not mount or write to the virgin or scratch devices outside schelk.
  • Use --no-copy only if the user explicitly states that virgin and scratch are already byte-identical.
  • After a host reboot or power loss while mounted, assume incremental recovery is unsafe. Use full-recover.
  • If the user wants multiple schelk instances in parallel, assign a unique --dm-era-name and a separate --state-path for each instance.
  • Do not overpromise perfect device reset semantics. schelk restores logical blocks, not NVMe controller internal state.

Read the full file on GitHub · 285 lines

Files

What ships with it

3 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. 2d ago First seen · 285 lines · 0 tokens per session scan B 3a38faa78f9e

Subscribe to this mod's changes

schelk is a skill published in the GitHub repository tempoxyz/schelk (51 stars, last pushed 7d ago), licensed Apache-2.0. It adds 88 tokens to every session and 2,233 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

DatabasesDebuggingTesting
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens