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 akaieuan/Hologram --skill blender-simgit clone --depth 1 https://github.com/akaieuan/HologramWrote 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/akaieuan/hologram/blender-sim)<a href="https://agentmods.dev/skills/akaieuan/hologram/blender-sim"><img src="https://agentmods.dev/badge/skills/akaieuan/hologram/blender-sim/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/akaieuan/hologram/blender-sim"><img src="https://agentmods.dev/badge/skills/akaieuan/hologram/blender-sim.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 | $0.00105 | $0.01138 |
| Opus 5 | $0.00053 | $0.00569 |
| Sonnet 5 | $0.00021 | $0.00228 |
| Haiku 4.5 | $0.00011 | $0.00114 |
Grade A, and why
Blender 5.2 simulation cheat sheet 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 12d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blender 5.2 physics & simulation — cheat sheet
When invoked, print the reference below. Quick lookup — do not read files or
run tools. (Digest of the 5.2 LTS release notes and community testing, July 2026;
the long-form version lives in docs/research/blender-52-simulation.md of the
Hologram repo.)
The new system (5.2, experimental)
XPBD Solver node — Geometry-Nodes-native, constraint-based (the solver family modern game/film cloth uses). ~2–4× faster than legacy cloth in reference tests. Two ready-made assets sit on top of it:
| Asset | Use | Notes |
|---|---|---|
| Cloth Dynamics | modifier + node group on any mesh | pinning, stretch/bend, tearing. NO self-collision or pressure yet. |
| Hair Dynamics | Add > Curves > Empty Hair auto-wires it |
needs an attach surface + Capture Rest Geometry modifier; each curve sims as a Cosserat rod |
Effectors — collisions and forces are explicit, nothing is auto-detected:
- Collider — any closed mesh, via the Collider modifier, collected into the collection you assign as the cloth's effectors
- Custom Force — per-point force vectors. Only gravity is built in; wind / turbulence / drag = build a Custom Force on an Empty (Empties host GN modifiers now)
- Custom Effector — a closure injected at a solver stage (e.g. Post Solve)
Working values: stretch/bend stiffness above ~0.25 goes rubbery — stay under it. Meshes need density for collisions to register — subdivide at least once. Pin the attachment edge (pole edge, rim, hem).
It is experimental. The node design may change; don't build load-bearing tooling against node-group internals — wrap your recipe in one script or skill so there's a single place to fix.
Bake-to-GLB pathways (per sim type)
glTF has no runtime physics — sim at authoring time, export baked geometry.
| Sim | Export-safe route |
|---|---|
| XPBD Cloth/Hair, Simulation Zone | Bake node (Mode = Still for a frozen pose) → evaluated mesh exports like any modifier result; or scrub to the good frame and apply the modifier |
| Classic cloth / soft body | scrub to frame → bpy.ops.object.modifier_apply freezes the drape |
| Rigid body | bpy.ops.rigidbody.bake_to_keyframes(frame_start, frame_end, step) → real object keyframes, glTF exports them natively — the only rigid-body path that survives export |
| Fluid | cache bake → mesh sequence; no keyframe path |
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.
- 12d ago First seen · 82 lines · 105 tokens per session scan A 88cc83e30081
Blender 5.2 simulation cheat sheet is a skill published in the GitHub repository akaieuan/Hologram (2 stars, last pushed 1mo ago), licensed MIT. It adds 105 tokens to every session and 1,138 once invoked, about $0.0005 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.
Other skills, from other repositories
3d_object
Judge whether a generated mesh is fit to ship in a browser game, from the same rendered sheet the orientation review uses.
3d_scene
Choose how to build a 3dscene asset. Do not default to one pipeline for every task: what the user specified about the scene's appearance matters more than the scene type, and generative reconstruction is the least stable route here.
motion
How an agent turns a character mesh into a usable animated FBX — and how to judge whether the result is shippable.
audio
Use this Skill when a game plan requires dialogue, voice lines, sound effects, foley, ambience, or other offline WAV assets. This is asset generation, not a runtime audio-playback contract; use the selected engine context after an asset has passed review.
image
Use this Skill when a game plan needs a single-subject concept image, a character reference cleaned for image-to-3D, or a front-facing transparent T-pose image for downstream character reconstruction. T-pose generation is an image-generation and image-editing task; it is not a separate asset category.
game-cg-director
Convert game CG intent and optional media references into validated, model-specific directing envelopes for opening, cutscene, ultimate, or promo clips. Use for standalone CG prompt direction or as a child capability of a game-generation Harness. Supports T2VA/text-only, I2VA/first-frame image…