hive_studio CLAUDE.md

hive_studio CLAUDE.md is an instructions file for Claude Code from aivansoul/hive_studio. It costs 3,291 tokens per session, scanned A, original, MIT.

A project instruction file that guides an AI coding agent through a fixed seven-stage web-design process, from intake to delivery. It also describes parallel agents, a critic, and quality checks.

In plain words
What is it for?
Planning, designing, building, optimizing, testing, and delivering websites in the hive_studio project.
Why use it?
It gives the agent a consistent way to organize web-design work and review results against stated requirements.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

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.

agentmods
npx agentmods add instructions/aivansoul/hive_studio/claude-md
Clone the repo
git clone --depth 1 https://github.com/aivansoul/hive_studio

Made for: Claude Code.

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 hive_studio CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/aivansoul/hive_studio/claude-md.svg)](https://agentmods.dev/instructions/aivansoul/hive_studio/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/aivansoul/hive_studio/claude-md"><img src="https://agentmods.dev/badge/instructions/aivansoul/hive_studio/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,291 This file is loaded in full into every session.
When invoked 3,291 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.03291 $0.03291
Opus 5 $0.01646 $0.01646
Sonnet 5 $0.00658 $0.00658
Haiku 4.5 $0.00329 $0.00329

Measured 6d ago against content hash 7a2cbee86b19, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

hive_studio CLAUDE.md 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 6d 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.md · 253 lines

How it starts

The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.

hive_studio — Constitution

You are operating inside hive_studio, a premium web design system owned by Svetlana Totolina (AI Automation Specialist, Antwerp). This file is loaded automatically into every conversation in this directory and overrides generic defaults.

Read this file first. Then read the phase you're in. Then act.


0. North Star

Every site we ship is judged on five non-negotiables:

  1. Original — no generic AI layouts. If the hero looks like a Vercel template, kill it.
  2. Emotionally strong — first scroll must produce a felt reaction (curiosity, desire, awe, calm).
  3. Conversion-engineered — every section has a job. Decorative-only sections are deleted.
  4. SEO + GEO optimized — ranks on Google AND gets cited by ChatGPT/Perplexity/Claude.
  5. Mobile-first, Lighthouse 95+ mobile — non-negotiable. Desktop is a derivative.

If any of these five fails the Creative Director review, the work does not ship.


1. The Workflow (always the same 7 phases)

01_INTAKE   →  02_STRATEGY  →  03_DESIGN  →  04_BUILD  →  05_SEO_GEO  →  06_QA  →  07_DELIVERY

Each phase has:

  • a template folder (/01_INTAKE, /02_STRATEGY, etc.)
  • a required output file that lives in _projects/[client-slug]/
  • a quality gate the Creative Director must pass before next phase starts

Never skip a phase. Even for "small" jobs. The intake takes 10 minutes and saves 10 hours.


2. The Hive Mind (parallel agents + a critic)

Work is dispatched to a team of specialized agents that run in parallel wherever possible, then synthesized and critiqued by the Creative Director before progressing.

The team

Agent Role Phase Runs parallel with
brand-strategist DNA, positioning, audience 02 (alone)
ux-architect IA, flows, mobile-first wireframes 03 art-director, content-architect
art-director Visual direction, moodboard, refs 03 ux-architect, content-architect
content-architect Page structure, narrative 03 ux-architect, art-director
copywriter Headlines, body, microcopy, CTAs 03 visual-producer (after content-architect)
visual-producer Higgsfield / NanoBanana / imagegen heroes 03 copywriter (after art-director)
frontend-designer Component design, layouts, tokens 04 motion-designer
motion-designer Subtle motion, transitions, scroll 04 frontend-designer
seo-geo-strategist Technical SEO + GEO + schema 05 performance-engineer
performance-engineer Lighthouse 95+, Core Web Vitals 05 seo-geo-strategist
creative-director CRITIC. Reviews every phase output. every gate (alone — judges last)

Read the full file on GitHub · 253 lines

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. 6d ago First seen · 253 lines · 3,291 tokens per session scan A 7a2cbee86b19

Subscribe to this mod's changes

hive_studio CLAUDE.md is an instructions file published in the GitHub repository aivansoul/hive_studio (3 stars, last pushed 3mo ago), licensed MIT. It adds 3,291 tokens to every session, about $0.0165 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.

Related

Other instructions, from other repositories