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 startgit 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/start)<a href="https://agentmods.dev/skills/akaieuan/hologram/start"><img src="https://agentmods.dev/badge/skills/akaieuan/hologram/start/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/start"><img src="https://agentmods.dev/badge/skills/akaieuan/hologram/start.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 | $0.00095 | $0.00710 |
| Opus 5 | $0.00048 | $0.00355 |
| Sonnet 5 | $0.00019 | $0.00142 |
| Haiku 4.5 | $0.00010 | $0.00071 |
Grade B, and why
Get started with Hologram scanned grade B with 1 finding 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
1. **If they're new, explain the two ways above in a sentence or two.** Don't lecture — get them to something working fast. How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Get started with Hologram
Hologram gives you eyes on an AI-driven Blender → glTF pipeline. It works two ways at once, and most people use both:
- Watch — a local dashboard in the browser (default
http://127.0.0.1:7870) that streams what the agent is doing and flags failures as they happen. Keeps a human in the loop, visually. - Drive — read-only MCP tools and these skills, so the agent can inspect, render, validate, and report on assets through natural language.
Both surfaces share one event log, so whatever happens in one shows up in the other.
What to do
-
If they're new, explain the two ways above in a sentence or two. Don't lecture — get them to something working fast.
-
Check the project is initialized. Look for
hologram.tomlat the repo root (Glob). If it's missing, runhologram init— it writeshologram.toml(paths + dashboard config) and.mcp.json(wires the read-only MCP tools into Claude Code viauvx, no install step). Tell them what landed, and that the MCP tools become available once Claude Code picks up.mcp.json— a reload/restart if it was just created. -
Point
export_rootat their GLBs. Openhologram.tomland confirm[paths] export_rootmatches where their.glbfiles actually live. This is the one setting everything else depends on. -
Launch the dashboard. Run
hologram dashboardin the background so it keeps running, then give them the URL (http://127.0.0.1:7870unless they set a different port). Mentionhologram watchas the terminal-only alternative if they'd rather not open a browser. -
Hand off. Point them at what's next:
/hologram:inspect— look at an asset (structure + a rendered preview)/hologram:check— validate exports and read the failures/hologram:status— catch up on what's wrong or what changed/hologram:create-skill— capture one of their workflows as a new skill
Notes
- Don't start a second dashboard if one is already running on the port — check first.
- Everything Hologram's MCP server does is read-only. The one tool that touches
Blender (
render_asset) renders in a throwaway scene and restores the user's working scene — it never modifies their work.
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 · 56 lines · 95 tokens per session scan B 97f0dd564780
Get started with Hologram is a skill published in the GitHub repository akaieuan/Hologram (2 stars, last pushed 1mo ago), licensed MIT. It adds 95 tokens to every session and 710 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). 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.
motion
How an agent turns a character mesh into a usable animated FBX — and how to judge whether the result is shippable.
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.
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…