A group of specialist coding agents for building, deploying, researching, auditing, or fixing Next.js applications hosted on Vercel.

Use it for Next.js and Vercel development, deployment, performance checks, accessibility audits, and related fixes.

It divides complex Next.js and Vercel work among specialists, helping cover deployment, performance, accessibility, and website-building concerns.

v-swarm — Skill for Claude Code by frankxai/claude-skills-library

Install

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.

Any agent

npx skills add frankxai/claude-skills-library --skill v-swarm

Clone the repo

git clone --depth 1 https://github.com/frankxai/claude-skills-library

Made for: Claude Code.

Or install claude-skills-library, the plugin that ships this one along with the rest of its 114 skills.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/frankxai/claude-skills-library/v-swarm/github.svg)](https://agentmods.dev/skills/frankxai/claude-skills-library/v-swarm)

Your own site

<a href="https://agentmods.dev/skills/frankxai/claude-skills-library/v-swarm"><img src="https://agentmods.dev/badge/skills/frankxai/claude-skills-library/v-swarm/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/frankxai/claude-skills-library/v-swarm"><img src="https://agentmods.dev/badge/skills/frankxai/claude-skills-library/v-swarm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 141 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,008 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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 5.1	$0.00141	$0.04008
Opus 5.5	$0.00056	$0.01603
Sonnet 5.5	$0.00028	$0.00802
Haiku 4.5	$0.00014	$0.00401

Measured 2mo ago against content hash 0391d8e0ec10, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

v-swarm 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 2mo 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.

free-skills/v-swarm/SKILL.md · 284 lines

How it starts

The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.

v-swarm — Vercel/Next.js Excellence Orchestration

Activation: this skill loads when /v fires or when the user asks for Vercel/Next.js work. The skill body below is the orchestration logic. Detailed knowledge lives in references/.

Lane classification

Pick exactly one lane per /v invocation. If the ask spans multiple, pick the dominant one and surface the others as follow-ups.

Lane	Triggers in user ask	Decision rule
BUILD	"build", "create", "new page/component", "add", "scaffold"	User wants something new in the codebase
DEPLOY	"deploy", "ship", "release", "push to prod", "go live"	User wants something on the actual production URL
AUDIT	"audit", "review", "check", "lighthouse", "scan", "is X good"	User wants an assessment, not a change
RESEARCH	"what's the best", "should I", "compare", "is X ready", "Lee Robinson recommends"	User wants a recommendation grounded in authority
FIX	"broken", "slow", "error", "regression", "not working", "why is"	User has a symptom, wants a root cause

If unclear: ask one question, never more. Default question: "Lane — build something new, deploy what's there, audit what's live, research what to do, or fix something that's broken?"

Swarm recipes

Each lane has a recipe. Spawn agents in parallel using the superpowers:dispatching-parallel-agents skill. Never sequence agents that can run independently.

BUILD

Parallel:
  Agent: frankx-website-builder
    task: implement the requested page/component, follow CLAUDE.md voice + glassmorphic design system
  Agent: ui-ux-design-guidance
    task: review proposed UX, surface accessibility gaps, suggest interaction patterns
  Skill load: nextjs-expert + vercel:nextjs + vercel:react-best-practices
  Optional: /v0-generate for rapid prototype if user mentioned "prototype" or "draft"

Then sequential:
  - Reconcile builder output with UX feedback
  - Run pre-deploy checks (lane = AUDIT subset) on the new code path
  - Surface diff for review

Read the full file on GitHub · 284 lines

Files

What ships with it

4 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.

Changes

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.

2mo ago First seen · 284 lines · 141 tokens per session scan A 0391d8e0ec10

Subscribe to this mod's changes

v-swarm is a skill published in the GitHub repository frankxai/claude-skills-library (47 stars, last pushed yesterday), licensed MIT. It adds 141 tokens to every session and 4,008 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-09-03.

Claude Code DevOps and cloud Frontend Productivity ai-tools anthropic prompt-engineering skills

v-swarm next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
v-swarmfrankxai/claude-skills-library	Skill	47	yesterday	MIT	A	141	Claude Code
token-saverchidekina/aria-superpowers	Skill	2	1mo ago	none	C	85	Claude Code, Codex
wayfindervinvcn/mattpocock-skills-zh-CN	Skill	5.6k	10d ago	MIT	A	40	Claude Code, Codex
scaffold-exercisesvinvcn/mattpocock-skills-zh-CN	Skill	5.6k	10d ago	MIT	A	46	Claude Code, Codex
domain-modelingvinvcn/mattpocock-skills-zh-CN	Skill	5.6k	10d ago	MIT	A	38	Claude Code, Codex
migrate-to-shoehornvinvcn/mattpocock-skills-zh-CN	Skill	5.6k	10d ago	MIT	A	53	Claude Code, Codex
ask-mattvinvcn/mattpocock-skills-zh-CN	Skill	5.6k	10d ago	MIT	A	28	Claude Code, Codex