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 guinacio/claude-image-gen --skill image-to-3dgit clone --depth 1 https://github.com/guinacio/claude-image-genWrote 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/guinacio/claude-image-gen/image-to-3d)<a href="https://agentmods.dev/skills/guinacio/claude-image-gen/image-to-3d"><img src="https://agentmods.dev/badge/skills/guinacio/claude-image-gen/image-to-3d/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/guinacio/claude-image-gen/image-to-3d"><img src="https://agentmods.dev/badge/skills/guinacio/claude-image-gen/image-to-3d.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 | $0.00112 | $0.03317 |
| Opus 5 | $0.00056 | $0.01658 |
| Sonnet 5 | $0.00022 | $0.00663 |
| Haiku 4.5 | $0.00011 | $0.00332 |
Grade A, and why
image-to-3d 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 2d 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 — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image to 3D with Tripo
One image of one isolated object goes in, a GLB comes out. The script in
scripts/tripo.py handles upload, submission, polling and download.
Cost rule, before anything else
Never submit a Tripo job without asking first. Every run spends the user's
credits. The script enforces this: without --yes it prints the plan, the cost
and the account balance, and stops. Show that dry run, then wait for an explicit
go-ahead before adding --yes.
Usage
python scripts/tripo.py piece.png --name sneaker --output-dir ./models
python scripts/tripo.py piece.png --name sneaker --output-dir ./models --yes
Needs TRIPO_API_KEY in the environment. Standard library only, no install.
| Flag | Effect |
|---|---|
--yes |
actually submit and spend |
--left, --back, --right |
supply your own views instead of letting Tripo invent them |
--direct |
single-image path, skips multiview: cheaper, least accurate geometry |
--model-version |
v3.1-20260211 (default) or v3.0-20250812 |
--name, --output-dir |
naming and destination |
Texture — all inert unless --texture is passed:
| Flag | Effect |
|---|---|
--texture |
also generate texture maps, 10 more credits (default: geometry only) |
--texture-quality detailed |
+10 credits |
--texture-alignment |
original_image (default) favours visual fidelity, geometry favours structure |
--texture-seed N |
repeatable texture |
Mesh:
| Flag | Effect |
|---|---|
--face-limit N |
cap the polygon count |
--geometry-quality detailed |
Tripo's Ultra mode, +20 credits |
--smart-low-poly |
the Smart Mesh of the web UI: built topology instead of a collapsed dense mesh, +10 credits |
--quad |
quads instead of triangles, +5 credits |
--generate-parts |
model split into parts, +20 credits; refuses to combine with textures or --quad |
--no-export-uv |
faster, but the mesh arrives with no UVs |
--compress geometry |
geometry compression instead of the default meshopt |
What ships with it
3 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.
- 2d ago First seen · 281 lines · 112 tokens per session scan A 749064ae67db
image-to-3d is a skill published in the GitHub repository guinacio/claude-image-gen (63 stars, last pushed 2d ago), licensed MIT. It adds 112 tokens to every session and 3,317 once invoked, about $0.0006 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 2026-09-08.
Other skills, from other repositories
image-to-3d-pipeline
Transformez une image 2D en modèle 3D animé prêt pour le web ou le jeu en moins de 30 minutes, en utilisant le workflow Dilum Sanjaya (Hunyuan3D + Mixamo). Use when: Créer un personnage 3D pour un site web - Mascotte, avatar, illustration interactive; Prototyper un asset de jeu - Character design, props…
screenshot-isolated
Render a target GameObject from a chosen camera angle with optional layer-based isolation, configurable background (solid/skybox/transparent), multi-light setup via JSON, and Composite (2x2 Front/Right/Back/Top) mode. Returns a PNG image. When isolated=true, inactive children may briefly fire OnEnable — see the body…
screenshot-camera
Capture a screenshot from a Unity Camera and return it as a PNG image for direct LLM inspection. Falls back to Camera.main (then any active camera) when cameraRef is null. Width and height are capped to keep response size manageable.
screenshot-game-view
Capture a screenshot of the Unity Editor's Game View by reading its internal render texture directly. Image size matches the current Game View resolution; the tool corrects Y-flip on DirectX / Metal so the output is always upright. Requires an open Game View window.
screenshot-scene-view
Capture a screenshot from the Unity Editor Scene View at the requested size. Renders via the Scene View's active camera onto a temporary RenderTexture. Requires an open Scene View.
sound-cues
Create and modify SoundCue assets — add/connect nodes (mixer, random, delay, attenuation, modulator, etc.) and set audio properties (SoundCueService). Use when the user asks to create a Sound Cue, build a SoundCue node graph, or wire audio playback logic.