horror-style

horror-style is a skill for Claude Code from arjun988/blender-skills. It costs 49 tokens per session (1,161 once invoked), scanned A, original, MIT.

Psychological-horror art direction for Blender scenes and assets, focused on tension, sparse detail, industrial decay, analog equipment, and unsettling lighting.

In plain words
What is it for?
Use it for horror-game environments and props, abandoned industrial spaces, CRT and analog settings, liminal scenes, decayed materials, and compositions built around obscurity and tension.
Why use it?
It helps create unease through familiar places made subtly wrong, limited visibility, and environmental clues instead of relying only on jump scares. It also gives materials, colors, architecture, and lighting a consistent direction.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Part of the blender-skills plugin — 58 skills shipped together

Good fit Use it for horror-game environments and props, abandoned industrial spaces, CRT and analog settings, liminal scenes, decayed materials, and compositions built around obscurity and tension.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/arjun988/blender-skills/horror-style
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 arjun988/blender-skills --skill horror-style
Clone the repo
git clone --depth 1 https://github.com/arjun988/blender-skills

Made for: Claude Code.

Or install blender-skills, the plugin that ships this one along with the rest of its 58 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 horror-style

README.md
[![agentmods](https://agentmods.dev/badge/skills/arjun988/blender-skills/horror-style/github.svg)](https://agentmods.dev/skills/arjun988/blender-skills/horror-style)
Your own site
<a href="https://agentmods.dev/skills/arjun988/blender-skills/horror-style"><img src="https://agentmods.dev/badge/skills/arjun988/blender-skills/horror-style/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 horror-style

Your own site · 80×15
<a href="https://agentmods.dev/skills/arjun988/blender-skills/horror-style"><img src="https://agentmods.dev/badge/skills/arjun988/blender-skills/horror-style.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,161 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 pass 7 Sept 2026
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00049 $0.01161
Opus 5 $0.00024 $0.00580
Sonnet 5 $0.00010 $0.00232
Haiku 4.5 $0.00005 $0.00116

Measured 11d ago against content hash ba007d86309d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

horror-style 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 11d 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/horror-style/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Horror Style Specialist

Psychological tension over jump scares. Environmental storytelling. Sparse detail. Industrial decay.

When to Use

  • Horror game environments and props
  • Psychological tension scenes
  • Analog/liminal aesthetic assets
  • Industrial decay settings
  • Limited visibility compositions

Design Philosophy

Inspired by: Fear to Fathom, Chilla's Art, Puppet Combo, Silent Hill, Resident Evil, Iron Lung

Core tenets:

  1. Less is more — Absence creates tension
  2. Familiar made wrong — Recognizable spaces with subtle wrongness
  3. Light as enemy — Darkness hides; light reveals uncomfortably
  4. Industrial analog — CRT screens, fluorescent hum, concrete, rust
  5. Environmental narrative — Story told through objects, not exposition

Visual Language

Element Horror Treatment
Architecture Brutalist, institutional, repetitive
Materials Stained concrete, peeling paint, rust, yellowed plastic
Lighting Single source, flickering, cold fluorescent
Detail density Sparse foreground, empty midground, obscured background
Color Desaturated, sickly greens, cold blues, blood accent sparingly
Scale Slightly wrong proportions (low ceilings, narrow corridors)

Modeling Guidelines

  • Corridors: Narrow (1.2–1.5m) for claustrophobia
  • Ceilings: Low (2.2–2.4m institutional)
  • Doors: Slightly oversized or undersized — uncanny
  • Detail: Concentrate on hero interactive objects; walls mostly bare
  • Damage: Water stains > bullet holes; neglect > destruction
  • Technology: 80s–90s analog — CRT monitors, tape recorders, rotary phones

Sparse Detail Rule

Foreground: 1–2 narrative objects (key, note, blood stain)
Midground: Architectural structure only
Background: Fog/darkness obscures incomplete geometry

Do not over-model backgrounds visible only in darkness.

Lighting (Horror)

Coordinate with lighting skill:

  • High contrast ratio (8:1 minimum key:fill)
  • Visible light source meshes (bare bulb, fluorescent tube)
  • Volumetric fog mandatory for depth
  • Color temperature clash: warm interior vs cold exterior
  • Flicker animation on 1–2 lights only

Read the full file on GitHub · 146 lines

Files

What ships with it

2 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. 11d ago First seen · 146 lines · 49 tokens per session scan A ba007d86309d

Subscribe to this mod's changes

horror-style is a skill published in the GitHub repository arjun988/blender-skills (182 stars, last pushed 2mo ago), licensed MIT. It adds 49 tokens to every session and 1,161 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.