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 inspectgit 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/inspect)<a href="https://agentmods.dev/skills/akaieuan/hologram/inspect"><img src="https://agentmods.dev/badge/skills/akaieuan/hologram/inspect/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/inspect"><img src="https://agentmods.dev/badge/skills/akaieuan/hologram/inspect.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 | $0.00103 | $0.00577 |
| Opus 5 | $0.00051 | $0.00289 |
| Sonnet 5 | $0.00021 | $0.00115 |
| Haiku 4.5 | $0.00010 | $0.00058 |
Grade A, and why
Inspect a Hologram asset 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 9d 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.
What it actually says
Inspect a Hologram asset
Bridge the two ways of understanding an export: its structure (what's in the file) and its picture (what it looks like).
What to do
-
Resolve the asset. If they named it loosely ("the hero", "that sword"), call
list_assetsto find the matching.glband its path. If they gave a path, use it directly. -
Read the structure with
inspect_asset(path). It returns the flat Asset: node hierarchy (parent / children / mesh / skin / transform), root nodes, top-level nodes, materials, mesh names, animations, skins, and counts. Don't dump the raw JSON — summarize it like a person would: "12 nodes under one root, 3 materials (body, eyes, metal), one idle animation, rigged with a 28-bone skin." Call out anything that looks off (no materials, dozens of roots, empty meshes). -
Show it, if useful. Call
render_asset(path)for a PNG preview from the live Blender — the agent's version of the visual the dashboard gives a human.- On success you get an image back — describe what you actually see.
- If it returns
{"error", "hint"}, Blender isn't reachable. Say so plainly and pass on the hint (start Blender with the MCP add-on on:9876). Don't treat it as a hard failure — the structure read still stands on its own.
-
Answer the actual question. If they asked "how many materials", lead with the number. Inspect and render are the means, not the deliverable.
Notes
render_assetis non-destructive: it renders in a throwaway scene and restores the user's working scene. Safe against a live Blender session.- Paths resolve relative to the project root or
export_root, and must stay inside the project.
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.
- 9d ago First seen · 43 lines · 103 tokens per session scan A ac8fd5c49c6f
Inspect a Hologram asset is a skill published in the GitHub repository akaieuan/Hologram (2 stars, last pushed 1mo ago), licensed MIT. It adds 103 tokens to every session and 577 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
kiln
3D asset production pipeline via Blender MCP — sourcing, AI generation, cleanup, texturing, optimization, export. Batch mode for autonomous multi-asset production.
using-blender
General Blender workflow skill for AI agents working with .blend, .fbx, .obj, .glb, glTF, materials, scene inspection, bpy automation, headless Blender batch runs, export/reimport validation, previews, and optional Blender MCP control. Use when a task asks to open, inspect, create, automate, convert, optimize, render…
ikea-model-collector
Collect user-observed IKEA product GLB models into verified local research collections with provenance, dimensions, optional Blender previews, a Three.js gallery, indexes, and handoff. Use when Codex is asked to find an IKEA product's available 3D model, process a user-specified product list, import browser-captured…
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.
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.
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.