mainbranch: Skill for Claude Code

.claude/skills/mb-skill-concept/SKILL.md

mb-skill-concept is a skill for Claude Code from noontide-co/mainbranch. It costs 45 tokens per session (427 once invoked), scanned A, original, MIT.

A tool for creating several different website or asset concepts locally at the same time. Each concept is a runnable HTML version that can be previewed before one is chosen.

In plain words
What is it for?
Generating concept variations, comparing their visual style and wording, checking basic preview requirements, and promoting the selected version to the project root.
Why use it?
It makes it easier to compare genuinely different design directions before publishing one. It also keeps the alternatives available for reference.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents.

This is noontide-co/mainbranch's own configuration. It tells Claude Code how to work on mainbranch itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mainbranch configures →

Part of the mainbranch plugin — 21 skills shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to noontide-co/mainbranch. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/noontide-co/mainbranch/main/.claude/skills/mb-skill-concept/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/noontide-co/mainbranch

Made for: Claude Code.

Or install mainbranch, the plugin that ships this one along with the rest of its 21 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.

agentmods badge for mb-skill-concept

README.md
[![agentmods](https://agentmods.dev/badge/skills/noontide-co/mainbranch/mb-skill-concept/github.svg)](https://agentmods.dev/skills/noontide-co/mainbranch/mb-skill-concept)
Your own site
<a href="https://agentmods.dev/skills/noontide-co/mainbranch/mb-skill-concept"><img src="https://agentmods.dev/badge/skills/noontide-co/mainbranch/mb-skill-concept/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.

agentmods 80×15 button for mb-skill-concept

Your own site · 80×15
<a href="https://agentmods.dev/skills/noontide-co/mainbranch/mb-skill-concept"><img src="https://agentmods.dev/badge/skills/noontide-co/mainbranch/mb-skill-concept.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 427 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00045 $0.00427
Opus 5 $0.00023 $0.00214
Sonnet 5 $0.00009 $0.00085
Haiku 4.5 $0.00005 $0.00043

Measured 10d ago against content hash b42e99104ca0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mb-skill-concept 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 10d 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.

.claude/skills/mb-skill-concept/SKILL.md · 41 lines

What it actually says

skill-concept

A composable skill for generating concept variations. /mb-site calls this after the brief is locked, before the first publish.

Inputs

  • The locked brief (path provided in the user message)
  • Reference URLs (taste anchors, not templates)
  • Conversion endpoint config (.mainbranch/conversion.json)

Outputs

  • N localhost-runnable HTML variations, each in its own subdir of the project repo (e.g., concepts/v1/, concepts/v2/)
  • A short comparison summary for the operator: hero artifact, palette, voice variant for each
  • Operator picks one; that variation is promoted to the project root

Flow

  1. Spawn N foreground subagents (default 2). Each gets the same brief + reference URLs but is asked to make different decisions.
  2. Each subagent writes its variation. Foreground only — background writes are known to silently fail.
  3. Validate each variation: footer present, OG.svg under 1200×630, no AI tells in the copy.
  4. Render preview. python3 -m http.server from each subdir; open in browser.
  5. Operator picks. One concept → promoted to repo root; others archived under concepts/.

Foreground rule

Subagents MUST be foreground. The known background-subagent file-write bug means files appear written but don't persist. Foreground only. See references/concept-variations.md for the spawn pattern.

Cross-references

Files

What ships with it

3 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.

  1. 10d ago First seen · 41 lines · 45 tokens per session scan A b42e99104ca0

Subscribe to this mod's changes

mb-skill-concept is a skill published in the GitHub repository noontide-co/mainbranch (39 stars, last pushed 26d ago), licensed MIT. It adds 45 tokens to every session and 427 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.

Related

Other skills, from other repositories

theme-builder

Create or customize a site theme interactively. Walks through site purpose, audience, visual direction, and design specifics before generating a complete base.html template with all SEO, accessibility, search, pagination, and i18n requirements.

seite-sh/seite · 49 tokens

UI Design

Skill "UI Design" from OpenLabor/openlabor, covering ui design, objective and guidelines.

OpenLabor/openlabor · 6 tokens

frontend-design

Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Use whenever the task produces or modifies anything a user will see rendered — websites, landing pages, web apps, dashboards, React/HTML/Vue components, artifacts with visual output, style overhauls, or "make this…

XiaomiMiMo/MiMo-Code · 111 tokens

frontend-design

Produce intentional, responsive, accessible UI work and perform visual QA instead of generic component assembly.

Hmbown/CodeWhale · 21 tokens

image-to-code

Implement a selected image, screenshot, mockup, generated concept, or design frame as a faithful, responsive, interactive frontend in the target codebase.

XiaomiMiMo/MiMo-Code · 34 tokens

frontend

MUST USE for frontend/web UI/UX/visual work: building, styling, redesigning pages/components, React setup, performance audits, visual QA, taste, and polish. Routes four rulesets: design taste router and brand references; perfection for Playwright/Chromium Lighthouse/Core Web Vitals; ui-ux-db palettes/fonts/guidelines…

code-yeongyu/lazycodex · 183 tokens