New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Benchsdk CLI

by computesdk in computesdk/benchmarks

Install, authenticate, and use the unified bench CLI to query and run ComputeSDK benchmarks.

MITAuto-check passedBackend & APIs

Install Benchsdk CLI

skills CLI
$ npx skills add computesdk/benchmarks --skill benchsdk-cli -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install computesdk/benchmarks benchsdk-cli --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/computesdk/benchmarks.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/benchsdk-cli .claude/skills/benchsdk-cli && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
benchsdk-cli
GitHub stars
126
Token cost
~1.3k tokens
SKILL.md length
465 words
Files
1
Skills in repo
4
Repo updated
First seen
Licence
MIT

At a glance

Install, authenticate, and use the unified bench CLI to query and run ComputeSDK benchmarks.

  • Works in 4 steps: api-key → BENCHMARKS_PLATFORM_TOKEN (a better-auth… → BENCHMARKS_PLATFORM_API_KEY (an… → …
  • Tasks that involve OAuth and OpenID Connect
  • SKILL.md covers Installation, Authentication, Configuration file and Common commands, plus 7 more sections
  • Calls pnpm and node; reaches platform.computesdk.com; needs BENCHMARKS_PLATFORM_API_KEY and BENCHMARKS_PLATFORM_TOKEN

What it does

Benchsdk CLI is an agent skill from computesdk/benchmarks. 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.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Backend & APIs, covering OAuth and OpenID Connect. The repository describes itself as: Compare performance across sandbox, storage, browsers, and ai gateway providers. The licence is MIT.

When your agent uses it

  • Tasks that involve OAuth and OpenID Connect

Example prompts

  • “/benchsdk-cli”

Requirements

  • A credential in BENCHMARKS_PLATFORM_TOKEN
  • A credential in BENCHMARKS_PLATFORM_API_KEY

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. api-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)

What it can do on your machine

Read from SKILL.md and the folder at commit bcf2052. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • pnpm
    • node

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • platform.computesdk.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • BENCHMARKS_PLATFORM_API_KEY
    • BENCHMARKS_PLATFORM_TOKEN

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Benchsdk CLI loads about 1.3k tokens when it runs. Until then it costs about 46 tokens; SKILL.md has 465 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~46
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from computesdk/benchmarks at commit bcf2052, republished under its MIT licence (© computesdk). 465 words, ~1,290 tokens.

Download SKILL.mdSave it as .claude/skills/benchsdk-cli/SKILL.md (or your agent's skills folder).
name
benchsdk-cli
description
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.

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 polls and stores the access/refresh token pair. Access tokens last 1 hour; refresh tokens are 30-day sliding windows and rotate on every refresh.

Check status
bash
bench auth status
bench auth status --json
Log out
bash
bench auth logout

This removes ~/.benchsdk/credentials.json.

Configuration file

~/.benchsdk/config.json stores non-secret defaults:

json
{
  "baseUrl": "https://platform.computesdk.com",
  "org": "computesdk",
  "format": "table"
}

--base-url, --org, and --format override this file. Credentials live in ~/.benchsdk/credentials.json and are created with 0600 file permissions.

Common commands

Organizations
bash
bench org list
bench org use computesdk

bench org use switches the active organization and rewrites the stored access token with the new organization claim.

Benchmarks
bash
bench benchmarks list
bench benchmarks list --limit 20 --offset 40
bench benchmarks list --json
Runs
bash
bench runs list my-benchmark
bench runs show my-benchmark <runId>
Results
bash
bench results my-benchmark
bench results my-benchmark --run <runId>
bench results my-benchmark --format json
Artifacts
bash
bench artifacts list my-benchmark <runId>
bench artifacts list my-benchmark <runId> --worker <workerId>
Export
bash
bench export my-benchmark --out ./exports
bench export my-benchmark --run <runId> --out ./exports

Running benchmarks

bench run still executes benchmark files via @benchsdk/runner:

bash
bench run path/to/file.bench.ts --iterations 4 --concurrency 2

You can also use an org-scoped bp_ key for non-interactive runs:

bash
BENCHMARKS_PLATFORM_API_KEY=bp_... bench run path/to/file.bench.ts

Non-interactive / CI use

Set environment variables so the CLI never tries to open a browser:

bash
export BENCHMARKS_PLATFORM_URL=https://platform.computesdk.com
export BENCHMARKS_PLATFORM_API_KEY=bp_...

bench benchmarks list --json --limit 100

If no credentials are present, the CLI fails fast with an AuthError.

Environment variables

  • BENCHMARKS_PLATFORM_URL — platform root URL (default: https://platform.computesdk.com)
  • BENCHMARKS_PLATFORM_API_KEY — API key
  • BENCHMARKS_PLATFORM_TOKEN — bearer/session token
  • CI — when set, the CLI avoids interactive prompts
Show full SKILL.md (179 more words)Show less

Global flags

  • --base-url <url> — override the platform URL
  • --api-key <key> — use an API key for this command
  • --org <slug> — override the active organization
  • --format json|table — output format
  • --json — shortcut for --format json
  • --verbose — print stack traces and extra diagnostics on errors
  • --version
  • --help and bench <command> --help

Exit codes

  • 0 — success
  • 1 — general error or API failure
  • 2 — authentication error

Troubleshooting

  • bench --version shows 0.0.0 — the dist/ output is stale or the package.json was not found. Rebuild with pnpm --filter @benchsdk/cli build.
  • Cannot find module .../dist/bin.cjs — build @benchsdk/runner first: pnpm --filter @benchsdk/runner build.
  • Your session has expired — the refresh token is expired or revoked. Run bench auth login again, or use BENCHMARKS_PLATFORM_API_KEY.
  • 401/403 on list commands — verify the active org with bench auth status or pass --org <slug>.
  • The CLI auto-refreshes access tokens within 5 minutes of expiry. If a command fails with an auth error, the refresh token may also be expired.

Secrets needed

None for local development with BENCHMARKS_PLATFORM_API_KEY if one is provided. For OAuth login in CI, prefer BENCHMARKS_PLATFORM_API_KEY or BENCHMARKS_PLATFORM_TOKEN instead of bench auth login.

© computesdk, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/benchsdk-cli of computesdk/benchmarks.

Open the folder on GitHubat commit bcf2052

Compare with similar skills

Benchsdk CLI next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Benchsdk CLI compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Benchsdk CLI this skillcomputesdk/benchmarks126—~1.3kAutomated safety check: PassMIT
Fortify Developmentcoollabsio/coolify63k4 repos~1.9kAutomated safety check: PassMIT
Antipattern Preventiondoorkeeper-gem/doorkeeper5.5k—~1.1kAutomated safety check: PassMIT
OmniRoute Provider Managementdiegosouzapw/OmniRoute74k—~2.4kAutomated safety check: PassMIT
Stripe Best Practiceskanchengw/cnllm1753 repos~925Automated safety check: PassApache-2.0
Notion Worker Third-Party Auth Guidemakenotion/workers-template4391 repos~3.5kAutomated safety check: NotesMIT

Similar skills

  • Fortify Development

    coollabsio/coolify

    ACTIVATE when the user works on authentication in Laravel. An agent skill from coollabsio/coolify.

    63k GitHub starsUsed in 4 repos~1.9k tokens
    Backend & APIsAuto-check passed

  • Antipattern Prevention

    doorkeeper-gem/doorkeeper

    Avoid common Ruby and Rails antipatterns that degrade maintainability and performance.

    5.5k GitHub stars~1.1k tokensUpdated today
    Backend & APIsAuto-check passed

  • OmniRoute Provider Management

    diegosouzapw/OmniRoute

    Manages AI provider connections, API keys, OAuth flows and connection tests through OmniRoute's REST API across its 327-provider catalog.

    74k GitHub stars~2.4k tokensUpdated today
    Backend & APIsAuto-check passed

  • Stripe Best Practices

    kanchengw/cnllm

    Guides Stripe integration decisions — API selection (Checkout Sessions vs PaymentIntents), Connect platform setup (Accounts v2, controller properties), billing/subscriptions, Treasury financial…

    175 GitHub starsUsed in 3 repos~925 tokens
    Backend & APIsAuto-check passed

  • Notion Worker Third-Party Auth Guide

    makenotion/workers-template

    Official

    Decides whether a Notion Worker should use a brokered credential, a plaintext environment secret, or OAuth to authenticate against a non-Notion service.

    439 GitHub starsUsed in 1 repo~3.5k tokens
    Backend & APIsAuto-check: notes

  • Dependency Safety

    doorkeeper-gem/doorkeeper

    Ensure gems are safe, necessary, and properly constrained when adding, updating, or reviewing dependencies in Doorkeeper.

    5.5k GitHub stars~931 tokensUpdated today
    Backend & APIsAuto-check passed

More from computesdk/benchmarks

  • Add Sandbox Provider

    computesdk/benchmarks

    Prep a new sandbox provider for the ComputeSDK benchmarks (wire up the dependency, env var, providers list, and CI workflow).

    126 GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Local Platform E2E

    computesdk/benchmarks

    Stand up benchmarks-platform locally (Postgres + MinIO + ClickHouse in docker) and run a real @benchsdk/runner benchmark against it, with no cloud or provider credentials.

    126 GitHub stars~3k tokensUpdated today
    Auto-check: notes

  • Writing Benchmarks

    computesdk/benchmarks

    Author or improve a ComputeSDK benchmark. An agent skill from computesdk/benchmarks.

    126 GitHub stars~2.1k tokensUpdated today
    Auto-check: notes

Categories

Questions about Benchsdk CLI

What does Benchsdk CLI do?

Install, authenticate, and use the unified bench CLI to query and run ComputeSDK benchmarks. Benchsdk CLI is an agent skill from computesdk/benchmarks. Install, authenticate, and use the unified bench CLI to query and run ComputeSDK benchmarks.

When should I use Benchsdk CLI?

Benchsdk CLI fits situations like: tasks that involve OAuth and OpenID Connect.

How do I install Benchsdk CLI in Claude Code?

Run `npx skills add computesdk/benchmarks --skill benchsdk-cli -a claude-code`. Or copy the skill folder (.agents/skills/benchsdk-cli in computesdk/benchmarks) into .claude/skills/benchsdk-cli in your project. Claude Code loads it when a task matches its description.

How do I install Benchsdk CLI in Codex?

Run `npx skills add computesdk/benchmarks --skill benchsdk-cli -a codex`. Or copy the skill folder (.agents/skills/benchsdk-cli in computesdk/benchmarks) into .agents/skills/benchsdk-cli in your project. Codex loads it when a task matches its description.

Can I use Benchsdk CLI in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add computesdk/benchmarks --skill benchsdk-cli -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/benchsdk-cli, .gemini/skills/benchsdk-cli, .github/skills/benchsdk-cli and .opencode/skills/benchsdk-cli in your project.

What does Benchsdk CLI need to run?

Going by SKILL.md and its folder, Benchsdk CLI needs the command-line tools its instructions call (pnpm and node) and credentials named BENCHMARKS_PLATFORM_API_KEY and BENCHMARKS_PLATFORM_TOKEN. Our summary lists: A credential in BENCHMARKS_PLATFORM_TOKEN; A credential in BENCHMARKS_PLATFORM_API_KEY.

Does Benchsdk CLI access the network?

SKILL.md names 1 domain. In commands or code: platform.computesdk.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Benchsdk CLI safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Benchsdk CLI use?

Benchsdk CLI is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Benchsdk CLI use?

About 1.3k tokens (SKILL.md is roughly 5.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Benchsdk CLI?

Skills that share tags, products or a category with Benchsdk CLI: Fortify Development (coollabsio/coolify, 63k stars), Antipattern Prevention (doorkeeper-gem/doorkeeper, 5.5k stars), OmniRoute Provider Management (diegosouzapw/OmniRoute, 74k stars) and Stripe Best Practices (kanchengw/cnllm, 175 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Benchsdk CLI?

computesdk (a GitHub organization) maintains it in computesdk/benchmarks, which has 126 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 7, 2026.

Source: computesdk/benchmarks on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.