Vercel Sandbox Browser
vercel-labs/agent-browser
Runs agent-browser with headless Chrome inside Vercel Sandbox microVMs so Vercel-deployed apps can automate a browser without binary size limits.
Runs a metrics-first audit of a deployed Vercel project, gating investigations on real signals to produce ranked, citation-backed cost and performance recommendations.
Install Vercel Optimize Audit
$ npx skills add vercel-labs/agent-skills --skill vercel-optimize -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install vercel-labs/agent-skills vercel-optimize --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/vercel-labs/agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/vercel-optimize .claude/skills/vercel-optimize && rm -rf skills-srcUse ~/.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/
Install the "vercel-optimize" agent skill from https://github.com/vercel-labs/agent-skills/tree/main/skills/vercel-optimize into .claude/skills/vercel-optimize/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vercel-optimize", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/vercel-labs/agent-skills/tree/main/skills/vercel-optimizeType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add vercel-labs/agent-skills --skill vercel-optimize -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install vercel-labs/agent-skills vercel-optimize --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/vercel-labs/agent-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/vercel-optimize .agents/skills/vercel-optimize && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "vercel-optimize" agent skill from https://github.com/vercel-labs/agent-skills/tree/main/skills/vercel-optimize into .agents/skills/vercel-optimize/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vercel-optimize", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add vercel-labs/agent-skills --skill vercel-optimize -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install vercel-labs/agent-skills vercel-optimize --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/vercel-labs/agent-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/vercel-optimize .cursor/skills/vercel-optimize && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "vercel-optimize" agent skill from https://github.com/vercel-labs/agent-skills/tree/main/skills/vercel-optimize into .cursor/skills/vercel-optimize/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vercel-optimize", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/vercel-labs/agent-skills.git --path skills/vercel-optimize--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add vercel-labs/agent-skills --skill vercel-optimize -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install vercel-labs/agent-skills vercel-optimize --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/vercel-labs/agent-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/vercel-optimize .gemini/skills/vercel-optimize && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "vercel-optimize" agent skill from https://github.com/vercel-labs/agent-skills/tree/main/skills/vercel-optimize into .gemini/skills/vercel-optimize/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vercel-optimize", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install vercel-labs/agent-skills vercel-optimizeInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add vercel-labs/agent-skills --skill vercel-optimize -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/vercel-labs/agent-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/vercel-optimize .github/skills/vercel-optimize && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "vercel-optimize" agent skill from https://github.com/vercel-labs/agent-skills/tree/main/skills/vercel-optimize into .github/skills/vercel-optimize/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vercel-optimize", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add vercel-labs/agent-skills --skill vercel-optimize -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install vercel-labs/agent-skills vercel-optimize --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/vercel-labs/agent-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/vercel-optimize .opencode/skills/vercel-optimize && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "vercel-optimize" agent skill from https://github.com/vercel-labs/agent-skills/tree/main/skills/vercel-optimize into .opencode/skills/vercel-optimize/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vercel-optimize", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
vercel-optimize- GitHub stars
- 32k
- Used in
- 8 other repos
- Token cost
- ~4.3k tokens
- SKILL.md length
- 1,645 words
- Files
- 162 (incl. scripts, references)
- Skills in repo
- 4
- Repo updated
- First seen
- Licence
- None found
At a glance
Runs a metrics-first audit of a deployed Vercel project, gating investigations on real signals to produce ranked, citation-backed cost and performance recommendations.
- Works in 4 steps: Collect, scan, and merge signals → Gate candidates → Verify recommendations → …
- Reducing a Vercel bill by finding the costly routes and functions
- SKILL.md covers Prerequisites, Framework Support, Run Directory and Pipeline, plus 4 more sections
- Runs JavaScript scripts from its folder; calls vercel, node and jq; needs VERCEL_TOKEN
What it does
The audit is observability-first: the agent does not read source files until `signals.json` exists and a deterministic gate, run by `scripts/gate-investigations.mjs`, points to a route, file or project setting. Recommendations start from Vercel production metrics rather than repo-wide searching, reading is limited to files a candidate names or its route-local imports, and citations may come only from `references/docs-library.json`, with invalid or version-mismatched ones stripped. Report wording follows `references/voice.md`.
Prerequisites are Vercel CLI v53 or newer with the `metrics`, `usage`, `contract` and `api` commands, a logged-in session, a linked app directory, Node.js 20 or newer, and Observability Plus for route-level findings. Tokens must never be typed into shell commands. Next.js (both routers) and SvelteKit are supported, Nuxt has fewer framework-specific recommendations, Astro is limited, and Hono, Remix or unknown frameworks are blocked unless you accept a limited audit. Topics include bill reduction, caching, Function Invocations, Build Minutes, Core Web Vitals and Fluid compute.
When your agent uses it
- Reducing a Vercel bill by finding the costly routes and functions
- Investigating slow routes using real production metrics
- Looking for caching opportunities in a Next.js app on Vercel
- Breaking down Function Invocations, Build Minutes and data transfer costs
Example prompts
- “Why is our Vercel bill so high? Audit the project and rank the fixes.”
- “Find the slowest routes in production and tell me which ones to cache.”
- “Break down Function Invocations and Fast Data Transfer by route for this project.”
- “Compare our Core Web Vitals problems against what the Vercel metrics show.”
Requirements
- Vercel CLI v53 or newer, logged in and linked to the project
- Node.js 20 or newer
- Observability Plus for route-level recommendations
Workflow steps
4 steps, taken from the step headings in SKILL.md.
- Collect, scan, and merge signals
- Gate candidates
- Verify recommendations
- Render report and final message
What it can do on your machine
Read from SKILL.md and the folder at commit 063bee9. 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
Ships 1 file in scripts/ (JavaScript, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
vercelnodejq
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use vercel, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
VERCEL_TOKEN
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Vercel Optimize Audit loads about 4.3k tokens when it runs, and up to ~54k if it reads all its reference files. Until then it costs about 146 tokens; SKILL.md has 1,645 words of instructions outside code blocks.
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); the scripts in this folder are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 1,645 words (~4,328 tokens).
“Run an observability-first Vercel optimization audit. Do not inspect source files until signals.json exists and a deterministic gate points to a route, file, or project setting.”
- name
- vercel-optimize
- metadata.version
- 1.2.0
Files
SKILL.md and 161 other files (scripts, references) in skills/vercel-optimize of vercel-labs/agent-skills.
- SKILL.md
- AGENTS.md
- CONTRIBUTING.md
- README.md
- lib/auth-route.mjs
- lib/budget-summary.mjs
- lib/citations.mjs
- lib/cost-coverage.mjs
- lib/dedup-recs.mjs
- lib/deep-dive.mjs
- lib/display-labels.mjs
- lib/extract-claims.mjs
- lib/framework-support.mjs
- lib/gates/build-minutes-fanout.mjs
- lib/gates/cold-start.mjs
- lib/gates/contract.mjs
- lib/gates/cwv-poor.mjs
- lib/gates/external-api-slow.mjs
- lib/gates/hard-gates.mjs
- … and 143 more
Open the folder on GitHubat commit 063bee9
Used in 8 other repositories
We found 15 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 8 other GitHub owners. This page covers the copy in vercel-labs/agent-skills, which our catalogue first saw on October 7, 2026.
- robotostudio/turbo-start-sanity.agents/skills/vercel-optimize
- zoonk/zoonk.agents/skills/vercel-optimize
- jakubwarkusz/themes.agents/skills/vercel-optimize
- fujioky/reach.agents/skills/vercel-optimize
- aiskillstore/marketplaceskills/vercel-labs/vercel-optimize
- Asymmetric-al/core.agents/skills/vercel-optimize.claude/skills/vercel-optimize+1 more
- sickn33/agentic-awesome-skillsskills/vercel-optimizeplugins/agentic-awesome-skills/skills/vercel-optimize+1 more
- lingxling/awesome-skills-cnvercel-labs-agent-skills/skills/vercel-optimizeantigravity-awesome-skills/skills/vercel-optimize+2 more
Compare with similar skills
Vercel Optimize Audit 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Vercel Optimize Audit this skillvercel-labs/agent-skills | 32k | 8 repos | ~4.3k | Automated safety check: Pass | None | |
| Vercel Sandbox Browservercel-labs/agent-browser | 44k | — | ~2k | Automated safety check: Pass | Apache-2.0 | |
| Cloudflare Workers Frameworkssecondsky/claude-skills | 227 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Sanity Best Practicesrobotostudio/turbo-start-sanity | 182 | — | ~940 | Automated safety check: Pass | MIT | |
| App BuilderUndertone0809/rudder | 292 | — | ~2k | Automated safety check: Pass | Apache-2.0 | |
| Add React Analyticsgotempsh/temps | 822 | — | ~2.7k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
Cloudflare Workers Frameworks
secondsky/claude-skills
Framework integration for Cloudflare Workers. An agent skill from secondsky/claude-skills.
Sanity Best Practices
robotostudio/turbo-start-sanity
Sanity development best practices for schema design, GROQ queries, TypeGen, Visual Editing, images, Portable Text, Studio structure, localization, migrations, Sanity Functions, Blueprints, and…
App Builder
Undertone0809/rudder
Create and iteratively improve local web products from natural-language requests, then prepare them to run as Rudder Apps.
Add React Analytics
gotempsh/temps
Add Temps analytics to React applications with comprehensive tracking capabilities including page views, custom events, scroll tracking, engagement monitoring, session recording, and Web Vitals…
- Official
Sanity Best Practices
sanity-io/agent-toolkit
Sanity development best practices for schema design, GROQ queries, TypeGen, Visual Editing, images, Portable Text, Studio structure, localization, migrations, Sanity Functions, webhooks, Blueprints…
More from vercel-labs/agent-skills
- Official
Deploy to Vercel
vercel-labs/agent-skills
Deploys applications to Vercel as previews by default, picking a deploy method from the project's link state, git remote and team.
- Official
Vercel CLI With Tokens
vercel-labs/agent-skills
Deploys and manages Vercel projects through the CLI using an access token from the environment or a .env file instead of interactive login.
- Official
Writing Guidelines
vercel-labs/agent-skills
Review docs/prose for Writing Guidelines compliance. An agent skill from vercel-labs/agent-skills.
Related
Categories
Questions about Vercel Optimize Audit
What does Vercel Optimize Audit do?
Runs a metrics-first audit of a deployed Vercel project, gating investigations on real signals to produce ranked, citation-backed cost and performance recommendations. mjs`, points to a route, file or project setting.json`, with invalid or version-mismatched ones stripped.
When should I use Vercel Optimize Audit?
Vercel Optimize Audit fits situations like: reducing a Vercel bill by finding the costly routes and functions; investigating slow routes using real production metrics; looking for caching opportunities in a Next.js app on Vercel; breaking down Function Invocations, Build Minutes and data transfer costs.
How do I install Vercel Optimize Audit in Claude Code?
Run `npx skills add vercel-labs/agent-skills --skill vercel-optimize -a claude-code`. Or copy the skill folder (skills/vercel-optimize in vercel-labs/agent-skills) into .claude/skills/vercel-optimize in your project. Claude Code loads it when a task matches its description.
How do I install Vercel Optimize Audit in Codex?
Run `npx skills add vercel-labs/agent-skills --skill vercel-optimize -a codex`. Or copy the skill folder (skills/vercel-optimize in vercel-labs/agent-skills) into .agents/skills/vercel-optimize in your project. Codex loads it when a task matches its description.
Can I use Vercel Optimize Audit 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 vercel-labs/agent-skills --skill vercel-optimize -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/vercel-optimize, .gemini/skills/vercel-optimize, .github/skills/vercel-optimize and .opencode/skills/vercel-optimize in your project.
What does Vercel Optimize Audit need to run?
Going by SKILL.md and its folder, Vercel Optimize Audit needs JavaScript for the scripts in its folder, the command-line tools its instructions call (vercel, node and jq) and credentials named VERCEL_TOKEN. Our summary lists: Vercel CLI v53 or newer, logged in and linked to the project; Node.js 20 or newer; Observability Plus for route-level recommendations.
Does Vercel Optimize Audit access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Vercel Optimize Audit 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Vercel Optimize Audit use?
No licence was found for Vercel Optimize Audit or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Vercel Optimize Audit use?
About 4.3k tokens (SKILL.md is roughly 17k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 50k tokens, read only when the agent opens those files.
What are the alternatives to Vercel Optimize Audit?
Skills that share tags, products or a category with Vercel Optimize Audit: Vercel Sandbox Browser (vercel-labs/agent-browser, 44k stars), Cloudflare Workers Frameworks (secondsky/claude-skills, 227 stars), Sanity Best Practices (robotostudio/turbo-start-sanity, 182 stars) and App Builder (Undertone0809/rudder, 292 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Vercel Optimize Audit?
vercel-labs (a GitHub organization, an official publisher) maintains it in vercel-labs/agent-skills, which has 32,008 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on August 28, 2026.
Source: vercel-labs/agent-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.