A workflow for building a new website from validated pieces in a personal collection, such as templates, design systems, components, animations, menus, prompts, and recipes.

Use it to combine stored website pieces into a new site from a brief, including choices about colours and other design decisions.

It reuses material that has already been tested and checks what the collection contains before deciding what to build. If the collection is empty, it can build from scratch and offer to save the result.

kit-montar — Skill for Claude Code and Codex by harebeats

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 harebeats/cannonball --skill kit-montar

Clone the repo

git clone --depth 1 https://github.com/harebeats/cannonball

Made for: Claude Code, Codex.

Or install cannonball, the plugin that ships this one along with the rest of its 10 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/harebeats/cannonball/kit-montar/github.svg)](https://agentmods.dev/skills/harebeats/cannonball/kit-montar)

Your own site

<a href="https://agentmods.dev/skills/harebeats/cannonball/kit-montar"><img src="https://agentmods.dev/badge/skills/harebeats/cannonball/kit-montar/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/harebeats/cannonball/kit-montar"><img src="https://agentmods.dev/badge/skills/harebeats/cannonball/kit-montar.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 245 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 12,292 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. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Rogue Agent · line 17
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
medium MCP Rug Pull · line 547
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Fix: Pin the version: npx @scope/[email protected]

How audits are shown

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	$0.00245	$0.12292
Opus 5	$0.00122	$0.06146
Sonnet 5	$0.00049	$0.02458
Haiku 4.5	$0.00024	$0.01229

Measured 3d ago against content hash 5306601e5de1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

kit-montar 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.

The scan reads SKILL.md. This mod also ships 27 executable files (scripts/armadilhas.py, scripts/assets.py, scripts/buscar.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/kit-montar/SKILL.md · 960 lines

How it starts

The opening of the file, as written. The whole thing — 960 lines — stays where its author put it; the contents beside it link to each section on GitHub.

kit-montar — site novo a partir do acervo

Antes de qualquer comando: resolva o `SKILL_DIR`

Todo comando abaixo roda um script que viaja junto desta skill, em SKILL_DIR/scripts/. Defina SKILL_DIR como o caminho absoluto da pasta que contém ESTE SKILL.md que você acabou de ler — o seu harness informou esse caminho no resultado da leitura. Funciona em qualquer hospedeiro, sem depender de variável de ambiente de nenhum agente específico:

~/.claude/plugins/cache/cannonball/cannonball/<v>/skills/<nome>/SKILL.md
~/.codex/skills/<nome>/SKILL.md
~/.gemini/skills/<nome>/SKILL.md
~/.agents/skills/<nome>/SKILL.md

Em todos, SKILL_DIR é a pasta do SKILL.md, e SKILL_DIR/scripts/ está ao lado.

A regra que governa esta skill: o acervo vem primeiro. Gerar do zero é o último recurso, não o primeiro — o que está no acervo já rodou, código novo é aposta.

0. Veja o que o acervo tem hoje

O acervo é do usuário e muda a cada ingestão. Antes de qualquer pergunta:

python "${SKILL_DIR}/scripts/perfil.py"

Ele diz quantas peças existem, de que famílias, em que stacks, que setores cobre e onde estão as lacunas. É o que decide se esta conversa é uma montagem a partir do acervo ou uma construção do zero.

Ele termina com um bloco POR ONDE SEGUIR que muda conforme o acervo. Numa instalação nova ele manda vincular a pasta antes de qualquer ingestão — repasse ao usuário, porque esquecer isso deixa o material dele no lugar errado:

python "${SKILL_DIR}/scripts/vincular.py" --para "<pasta do usuário>"

Acervo vazio não invalida a skill. O fluxo continua igual — briefing, cor, tipografia, hero, plano, construção — só que sem peça para reaproveitar. No fim, ofereça guardar com /kit-ingerir: a próxima montagem do mesmo setor já começa adiantada. É assim que o acervo cresce, e cada peça guardada melhora todas as skills de uma vez.

0.1. Pergunte a stack — sempre, e antes de escolher peça

A stack decide quais peças são elegíveis e se haverá conversão. Perguntar depois de escolher significa refazer o trabalho.

Read the full file on GitHub · 960 lines

Files

What ships with it

52 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.

3d ago Changed · +37 lines · -19 tokens per session 5306601e5de1
8d ago First seen · 923 lines · 264 tokens per session scan A ffab415fd7b5

Subscribe to this mod's changes

kit-montar is a skill published in the GitHub repository harebeats/cannonball (9 stars, last pushed 5d ago), licensed MIT. It adds 245 tokens to every session and 12,292 once invoked, about $0.0012 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 2026-08-31.

Claude Code Design and UX Frontend agent-skills ai-agent claude-code-plugin design-system nextjs

designlang-tokens

Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.

Manavarya09/design-extract · 30 tokens

design-to-code-check

Check alignment between a specific design specification and its code implementation — a focused, single-component or single-screen comparison. Trigger when someone says: does this match the design, check implementation, design code alignment, what's different between the design and the build, spec check…

murphytrueman/design-system-ops · 95 tokens

stitch-design-system

Extracts a Stitch design and generates production code artifacts — CSS custom properties with dark mode tokens, a Tailwind v4 @theme block, and a semantic design system document. Run this before framework conversion skills.

gabelul/stitch-kit · 47 tokens

stitch-orchestrator

Master entry point for all Stitch design workflows. Routes from user request → design spec → prompt assembly → screen generation → iteration (edit, variants, design systems) → design system extraction → framework conversion (Next.js, Svelte, HTML, React Native, or SwiftUI) → optional quality pass.

gabelul/stitch-kit · 66 tokens

stitch-a11y

Audits Stitch-generated components for WCAG 2.1 AA accessibility issues and applies fixes — semantic HTML, ARIA attributes, keyboard navigation, focus management, and screen reader support.

gabelul/stitch-kit · 43 tokens

stitch-animate

Adds a purposeful animation layer to Stitch-generated components — CSS transitions, Framer Motion (React/Next.js), or Svelte transitions. Always respects prefers-reduced-motion.

gabelul/stitch-kit · 39 tokens