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/vercel/next.js/sandbox-benchnpx skills add vercel/next.js --skill sandbox-benchgit clone --depth 1 https://github.com/vercel/next.jsWrote 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.
[](https://agentmods.dev/skills/vercel/next.js/sandbox-bench)<a href="https://agentmods.dev/skills/vercel/next.js/sandbox-bench"><img src="https://agentmods.dev/badge/skills/vercel/next.js/sandbox-bench.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00212 | $0.04056 |
| Opus 5 | $0.00106 | $0.02028 |
| Sonnet 5 | $0.00042 | $0.00811 |
| Haiku 4.5 | $0.00021 | $0.00406 |
Grade A, and why
sandbox-bench 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 3d 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 — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sandbox bench: paired A/B perf runs for React and Next.js changes
Measures what a change is actually worth, end to end: two revisions
("arms") built into otherwise-identical Next.js apps, exercised by the
bench/render-pipeline harness on Vercel Sandbox VMs, compared with
paired statistics that treat the VM boot as the unit of replication.
All heavy work happens on sandbox VMs; the laptop only orchestrates.
Scripts live in scripts/ next to this file and run from anywhere.
Arms are git refs, resolved in cached clones of react and next.js;
the Next side defaults to canary. Everything is cached
content-addressed: first use of a new pair builds caches (~45-60 min
extra, once); later runs boot straight into measurement.
One-time setup
node scripts/config.mjs show— if it reports NOT CONFIGURED, ask the user which Vercel team and project the sandbox VMs should run under (these are billed resources; never guess, never default), thennode scripts/config.mjs set team=<slug> project=<name>. Config lives in~/.config/sandbox-bench/config.json— never commit team/project names into the repo.- The Vercel CLI session must have access to that team. On a 403,
stop launching (don't retry through it) and check whether access is
already back:
vercel whoami --scope <team-slug>plus one scoped read call (e.g.vercel sandbox ls) — grants drop and recover on their own, and a transient 403 needs no login at all. If verification still fails, runvercel login <team-slug>yourself as a background task (the token lives with the CLI session, not with the user). It opens a browser/device confirmation — relay the URL if one is printed — but keep re-running the verification pair every minute or two while it waits: access often returns before the login flow reports success, and once verification passes, kill the pending login and resume. After a 403 outage, expect in-flight runs to have died: runnode scripts/bench-status.mjsand follow its recovery actions (measurement VMs will have hit their ~5h timeout if the outage was long — those cells need relaunching, not collecting). - react and next.js clones land in the cache on first use (or point
reactRepo/nextRepoin the config at existing checkouts).
What ships with it
12 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.
- references/methodology.md 5.1 KB
- scripts/bench-analyze.mjs 2.8 KB runs code
- scripts/bench-collect.mjs 4.4 KB runs code
- scripts/bench-common.mjs 25 KB runs code
- scripts/bench-db.mjs 17 KB runs code
- scripts/bench-stats.mjs 8.7 KB runs code
- scripts/bench-status.mjs 3.0 KB runs code
- scripts/config.mjs 5.4 KB runs code
- scripts/sandbox-e2e.mjs 36 KB runs code
- scripts/sandbox-gate.mjs 12 KB runs code
- scripts/sandbox-ssr.mjs 21 KB runs code
- scripts/sandbox-sweep.mjs 2.9 KB runs code
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.
- 3d ago First seen · 321 lines · 212 tokens per session scan A f21d8fe37f89
sandbox-bench is a skill published in the GitHub repository vercel/next.js (142,020 stars, last pushed 3d ago), licensed MIT. It adds 212 tokens to every session and 4,056 once invoked, about $0.0011 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
migrate-radix-to-base
Migrates React projects and components from Radix UI to Base UI. Use when asked to migrate from radix, move to base-ui, convert radix primitives, or switch a shadcn project's base library. Handles single components ("migrate accordion") and whole projects.
example
Create new example charts for Recharts documentation website.
investigate
Find root cause for a bug or an issue in Recharts and propose a solution.
vr-test
Create visual regression tests.
notion-to-blog
Transfer a blog post from Notion to the Wasp blog. Fetches content, downloads and optimizes images, and creates a properly formatted MDX file.
social-content
When the user wants help creating, scheduling, or optimizing social media content for LinkedIn, Twitter/X, Instagram, TikTok, Facebook, or other platforms. Also use when the user mentions 'LinkedIn post,' 'Twitter thread,' 'social media,' 'content calendar,' 'social scheduling,' 'engagement,' or 'viral content.' This…