benchsdk-cli SKILL.md skillA

benchsdk-cli from computesdk/benchmarks is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add computesdk/benchmarks/benchsdk-cli@git:20261028.9f38cfa

Pins git:20261028.9f38cfa in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
computesdk/benchmarks
Path
.agents/skills/benchsdk-cli/SKILL.md
Versions recorded
5
Latest version
git:20261028.9f38cfa, committed Oct 28, 2026
First version recorded
Aug 25, 2026
Size
7,903 bytes
Repository stars
131
License
MIT

Install, authenticate, and use the unified bench CLI to query and run ComputeSDK benchmarks. Covers device-code OAuth, API keys, config files, and non-interactive/CI use.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# `bench` CLI

The `bench` binary is the unified CLI for the ComputeSDK benchmarks platform.
`bench run` executes benchmark files; all other commands query platform data.

## Installation

The CLI ships with `@benchsdk/runner`. From the benchmarks repo root:

```bash
pnpm install
pnpm -r --filter "./packages/**" build
```

Run via the built binary:

```bash
node packages/benchsdk-runner/dist/bin.cjs --version
```

Or add `packages/benchsdk-runner` to your `PATH` so `bench --version` works.

## Authentication

The CLI tries credentials in this order:

1. `--api-key <key>`
2. `BENCHMARKS_PLATFORM_TOKEN` (a better-auth session token — does not refresh)
3. `BENCHMARKS_PLATFORM_API_KEY` (an org-scoped `bp_...` key)
4. OAuth tokens from `~/.benchsdk/credentials.json` (from `bench auth login`)

API keys and tokens are useful for non-interactive environments. OAuth is
interactive and stores a refresh token under `~/.benchsdk`. At least one
credential is required for any command that touches the platform.

### Device-code login

```bash
bench auth login --base-url https://platform.computesdk.com
```

This prints a URL and a user code. Approve the device in the browser; the CLI
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add computesdk/benchmarks/benchsdk-cli@sha256:819c56ce296d3703

The line at the top of this page pins the label git:20261028.9f38cfa, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_ov6unz5ltcj2kesj.svg)](https://markdownregistry.com/a/art_ov6unz5ltcj2kesj)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Aug 25, 2026 and Oct 28, 2026, about one every 16 days.

versioncommittedcommitsizeaudit
git:20261028.9f38cfa latest2026-10-28 9f38cfa 7,903 BA view · diff
git:20261023.9c7058e2026-10-23 9c7058e 6,599 BA view · diff
git:20260901.7578a1d2026-09-01 7578a1d 5,196 BA view · diff
git:20260826.30957122026-08-26 3095712 5,155 BA view · diff
git:20260825.68045742026-08-25 6804574 5,202 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (7903 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

computesdk/benchmarks · 131 stars · license MIT · pushed 2026-11-06 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_ov6unz5ltcj2kesj
GET https://markdownregistry.com/api/v1/resolve?ref=computesdk/benchmarks/benchsdk-cli
GET https://markdownregistry.com/api/v1/blob/819c56ce296d3703154c428a599db02981e74b50db9ecd7013e4ad9d1fcff487

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from computesdk/benchmarks

local-platform-e2e SKILL.md skill
computesdk/benchmarks · .agents/skills/local-platform-e2e/SKILL.md · Stand up benchmarks-platform locally (Postgres + MinIO + ClickHouse in docker) and run a real @benchsdk/runner…
git:20261023.9c7058e · audit C · 131 stars
writing-benchmarks SKILL.md skill
computesdk/benchmarks · .agents/skills/writing-benchmarks/SKILL.md · Author or improve a ComputeSDK benchmark. Turn a unit of work into a declarative *.bench.ts file (config + task with…
git:20260926.564377d · audit A · 131 stars
add-sandbox-provider SKILL.md skill
computesdk/benchmarks · .claude/skills/add-sandbox-provider/SKILL.md · Prep a new sandbox provider for the ComputeSDK benchmarks (wire up the dependency, env var, providers list, and CI…
git:20260826.3095712 · audit A · 131 stars
llms.txt llms.txt file
computesdk/benchmarks · llms.txt
git:20260826.3095712 · audit A · 131 stars

Every file in computesdk/benchmarks

Browse by kind, by grade A, or by owner.