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.
git 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/plugins/akaieuan/hologram/plugin)<a href="https://agentmods.dev/plugins/akaieuan/hologram/plugin"><img src="https://agentmods.dev/badge/plugins/akaieuan/hologram/plugin/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/plugins/akaieuan/hologram/plugin"><img src="https://agentmods.dev/badge/plugins/akaieuan/hologram/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
hologram 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 1mo 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
{
"name": "hologram",
"version": "0.6.0",
"description": "Live observability + an agent (MCP) surface for Blender -> glTF pipelines. Streams Claude Code activity to the hologram dashboard, exposes four read-only asset tools (list_assets, inspect_asset, tail_events, pipeline_status) plus a non-destructive render_asset, and bundles guided skills (start, inspect, check, status, create-skill) to get going fast.",
"author": {
"name": "Ieuan King"
},
"homepage": "https://github.com/akaieuan/Hologram",
"repository": "https://github.com/akaieuan/Hologram",
"license": "MIT",
"keywords": ["blender", "gltf", "glb", "mcp", "observability", "pipeline", "skills"],
"hooks": "./hooks/hooks.json",
"mcpServers": "./.mcp.json"
}
What it installs
The manifest is a name and a version. 10 skills, 6 hooks, 1 MCP server travel with it, and installing the plugin installs all of them — 891 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill GLB authoring standards A 86 tokens
- Skill Create a Hologram skill A 87 tokens
- Skill Audit the asset catalogue A 79 tokens
- Skill Check the Hologram pipeline A 87 tokens
- Skill Gate assets for review A 76 tokens
- Skill Author a pose via IK and bake A 86 tokens
- Skill Blender 5.2 simulation cheat sheet A 105 tokens
- Skill Inspect a Hologram asset A 103 tokens
- Skill Hologram pipeline status A 87 tokens
- Skill Get started with Hologram B 95 tokens
- Hook UserPromptSubmit A not measured
- Hook SessionEnd A not measured
- Hook SessionStart A not measured
- Hook PostToolUse A not measured
- Hook PostToolUseFailure A not measured
- Hook PreToolUse A not measured
- MCP server hologram A not measured
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.
- 1mo ago First seen · 15 lines scan A 5e8cd16e47a7
hologram is a plugin published in the GitHub repository akaieuan/Hologram (2 stars, last pushed 3mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
blender-kiln
3D asset production pipeline for Claude Code — from a text brief or a photo to an optimized, validated GLB, rigged and animated when asked. Scripted modeling measured against the photo, textures from CC0 scans (Poly Haven), optional AI generation (free TRELLIS.2 Spaces first, Hunyuan3D on request, local TRELLIS.2…
04.-game-art-and-3d
Sprites, icons, tilesets, textures, skyboxes, 3D models, and walkable spaces for games, the web, and interactive scenes.
blender-mcp
Blender 3D automation via MCP.
skills-gamedev
26 game dev skills. Game development across Unity, Unreal, and Blender, plus art and audio pipelines.
remakebench-skills
Evidence-driven Claude Code skills for playable 3D production, image-to-3D reconstruction, quality gates, gameplay verification, and cross-model subagents.
alpha-scene-gen
Generate 3D models with Alpha3D and build them into your open Blender scene, scaled, grounded, and placed from a plain-language description.