Borrowing it
Nothing to install: this file belongs to aivansoul/hive_studio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/aivansoul/hive_studio/main/CLAUDE.mdgit clone --depth 1 https://github.com/aivansoul/hive_studioWrote 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.
[](https://agentmods.dev/instructions/aivansoul/hive_studio/claude-md)<a href="https://agentmods.dev/instructions/aivansoul/hive_studio/claude-md"><img src="https://agentmods.dev/badge/instructions/aivansoul/hive_studio/claude-md/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.
<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="Reviewed on agentmods" width="80" height="20"></a>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 | $0.03291 | $0.03291 |
| Opus 5.5 | $0.01316 | $0.01316 |
| Sonnet 5.5 | $0.00658 | $0.00658 |
| Haiku 4.5 | $0.00329 | $0.00329 |
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 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.
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:
- Original — no generic AI layouts. If the hero looks like a Vercel template, kill it.
- Emotionally strong — first scroll must produce a felt reaction (curiosity, desire, awe, calm).
- Conversion-engineered — every section has a job. Decorative-only sections are deleted.
- SEO + GEO optimized — ranks on Google AND gets cited by ChatGPT/Perplexity/Claude.
- 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) |
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 · 253 lines · 3,291 tokens per session scan A 7a2cbee86b19
hive_studio CLAUDE.md is an instructions file published in the GitHub repository aivansoul/hive_studio (3 stars, last pushed 5mo ago), licensed MIT. It adds 3,291 tokens to every session, about $0.0132 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.