Scenario Agent Skills is a collection of instructions that teaches AI coding agents to create images, video, audio, textures, skyboxes, and 3D assets through the Scenario MCP server, an interface to Scenario’s generation tools and custom-trained models. It serves game, entertainment, marketing, and other creative work, and also includes workflows for digital content creation software and game engines. The catalogue entries are these skills, along with plugins, commands, agents, instructions, settings, and hooks for using Scenario or driving supported creative applications.
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.
npx skills add scenario-labs/skills --skill scenario-blender-hard-surfacegit clone --depth 1 https://github.com/scenario-labs/skillsWrote 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/skills/scenario-labs/skills/scenario-blender-hard-surface)<a href="https://agentmods.dev/skills/scenario-labs/skills/scenario-blender-hard-surface"><img src="https://agentmods.dev/badge/skills/scenario-labs/skills/scenario-blender-hard-surface/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/skills/scenario-labs/skills/scenario-blender-hard-surface"><img src="https://agentmods.dev/badge/skills/scenario-labs/skills/scenario-blender-hard-surface.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 | $0.00115 | $0.04127 |
| Opus 5.5 | $0.00046 | $0.01651 |
| Sonnet 5.5 | $0.00023 | $0.00825 |
| Haiku 4.5 | $0.00012 | $0.00413 |
Grade A, and why
scenario-blender-hard-surface 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 20d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blender hard surface
Expert hard surface is controlled light on edges: every edge catches a highlight from a bevel or a support loop, flat faces read perfectly flat, and cuts stay editable until the design is settled. The experts disagree on method (n-gons and booleans vs quad cages and subdivision), not on the checks: order of operations, cutter hygiene, planar faces, a shiny matcap orbit. The agent builds the stack with the toolkit and lets the measurable gates find what a human finds by orbiting. If a sibling skill named here is missing from your available skills, ask the user to install it (npx skills add scenario-labs/skills --skill <name>); unattended, proceed from tool schemas and flag the gap.
REQUIRED BACKGROUND: scenario-blender-expert (execution channel, review loop, 5.2 API changes). Toolkit: scripts/bx_hardsurface.py (import sys; sys.path.append("<skills>/scenario-blender-hard-surface/scripts"); import bx_hardsurface as HS), world-space meters, stock Blender only.
Stance (the expert delta)
- Cut first, bevel after, normals last. Booleans above the angle-limited micro bevel, Weighted Normal at the very bottom, a late Mirror above it (Ryuu [00:26:26], [00:28:37]; du Mont [00:19:46]). In 5.2 a pinned modifier keeps its relative order inside the pinned group and new modifiers land above it, so pin bottom-up:
HS.order_stackdoes it andHS.add_booleanalways lands above the tail (verified). - Two bevels, two jobs (du Mont [00:12:25] to [00:15:15]): a weight-limited design bevel (8 to 12 segments) on chosen silhouette edges before the cuts, and an angle-limited micro bevel (30 degrees, Harden Normals, Miter Outer Arc) after every cut, because no real edge is perfectly sharp (Gambrell, du Mont, Ryuu).
- A bevel that shrinks after a boolean is geometry, not a setting (du Mont [00:20:18], [00:30:20]). Move the cutter well away from target edges or make it exactly coincident; keep Clamp Overlap on. Clamp Overlap limits the bevel over the whole object: a slot running 0.7 degrees off a facet edge (clamp ratio 3.8) wiped out the 3 mm bevel on a port elsewhere on the part [verified in 5.2.1].
HS.clamp_culpritsnames the cut. - Every wall, step, gap and rounding facet must be wider than 2x the micro bevel width [added, verified]: a 1 mm pocket floor, a 1.5 mm wall, a 2 mm groove with 1.5 mm bevels (a 3.1 mm one was clean) and a slot rounded in 30-degree facets all clamped the whole object's bevel.
- If Harden Normals or Weighted Normal changes nothing, the face is not flat (Gambrell [00:01:06]). Flatten it; more normal modifiers will not help.
- Pick the school by the part, not by taste. Planar machined parts with many cuts: n-gons + booleans + bevel + custom normals, about a quarter of the time and stays editable (Gambrell [00:18:01]). Continuous curvature, non-uniform roundness, a sculpt or bake high: quad cage + subdivision (rileyb3d, PzThree). Sharpen subD edges with support loops, not creases: 36,800 vs 3,600 triangles at equal quality (Lampel [00:05:28]).
- EXACT is the solver. Gambrell's 2021 "switch to Fast" predates 5.x: Float left 16 non-manifold edges on a coplanar cutter where Exact and Manifold were clean [verified]. When Exact misbehaves the operand is broken (Ryuu [00:15:13]): an open cutter gave Exact 19 non-manifold edges and Manifold silently skipped the cut [verified].
- Judge in a shiny matcap and close up on every cut (Gambrell [00:00:33], rileyb3d [00:06:32]). Whole-object sheets hide smears and shrunken bevels.
What ships with it
5 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.
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.
- 20d ago First seen · 109 lines · 115 tokens per session scan A f14733f37d3f
scenario-blender-hard-surface is a skill published in the GitHub repository scenario-labs/skills (1,034 stars, last pushed today), licensed MIT. It adds 115 tokens to every session and 4,127 once invoked, about $0.0005 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 2026-09-27.
Other skills, from other repositories
baoyu-diagram
Create professional, dark-themed SVG diagrams of any type — architecture diagrams, flowcharts, sequence diagrams, structural diagrams, mind maps, timelines, illustrative/conceptual diagrams, and more. Use this skill whenever the user asks for any kind of technical or conceptual diagram, visualization of a system…
customer-journey-map
Construye un mapa de recorrido del cliente para un producto, servicio o experiencia. Úsalo cuando se te pida mapear un recorrido del cliente, crear un viaje del usuario, documentar puntos de contacto y puntos de fricción, o diseñar un mapa de experiencia. Produce un mapa de recorrido completo con etapas, puntos de…
create-chatgpt-mockup
Render pixel-accurate ChatGPT mobile (iOS) screen mockups in light mode from a thread JSON. Supports user text bubbles, user image attachments, assistant markdown prose, citation chips, the OpenAI spiral logo, the Apps-SDK GPT chip in the composer, and three header styles (model-tag, plain title, "Get Plus"). Fixed…
design-handoff-brief
Transform feature briefs into structured design briefs that give designers the context they need before opening Figma. Use when asked to write a design brief, create a design handoff, brief a designer on a new feature, or translate a PRD into design requirements. Produces a brief with user goal, emotional context…
wordpress-elementor
Edit Elementor pages and manage templates on WordPress sites via browser automation (for visual / structural changes) or WP-CLI (for safe text replacements). Use whenever the user wants to edit an Elementor page, update text in Elementor widgets, apply or manage Elementor templates, or make content changes to pages…
journey-mapping
Build customer journey maps and service blueprints that visualize the end-to-end user experience including touchpoints, emotions, friction, and underlying systems. Use this skill whenever the user wants to map a customer journey, build a service blueprint, identify friction across an experience, align teams on the…