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.
npx agentmods add skills/computesdk/benchmarks/benchsdk-clinpx skills add computesdk/benchmarks --skill benchsdk-cligit clone --depth 1 https://github.com/computesdk/benchmarksWhat 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 | $0.00042 | $0.01359 |
| Opus 5 | $0.00021 | $0.00679 |
| Sonnet 5 | $0.00008 | $0.00272 |
| Haiku 4.5 | $0.00004 | $0.00136 |
Grade A, and why
benchsdk-cli 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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:
pnpm install
pnpm -r --filter "./packages/**" build
Run via the built binary:
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:
--api-key <key>BENCHMARKS_PLATFORM_TOKEN(a better-auth session token — does not refresh)BENCHMARKS_PLATFORM_API_KEY(an org-scopedbp_...key)- OAuth tokens from
~/.benchsdk/credentials.json(frombench auth login)
API keys and tokens are useful for non-interactive environments. OAuth is
interactive and stores a refresh token under ~/.benchsdk.
Device-code login
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
bench auth status
bench auth status --json
Log out
bench auth logout
This removes ~/.benchsdk/credentials.json.
Configuration file
~/.benchsdk/config.json stores non-secret defaults:
{
"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
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
bench benchmarks list
bench benchmarks list --limit 20 --offset 40
bench benchmarks list --json
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.
- 2d ago First seen · 199 lines · 42 tokens per session scan A 96d7c9ceac24
benchsdk-cli is a skill published in the GitHub repository computesdk/benchmarks (110 stars, last pushed 4d ago), licensed MIT. It adds 42 tokens to every session and 1,359 once invoked, about $0.0002 per session on Opus 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…