A set of workflows for creating and processing 3D assets with Meshy, an AI service for generating models from text or images. It covers models, textures, rigs, animations, and files prepared for 3D printing.

Use it to generate, texture, rig, animate, inspect, and download 3D assets through Meshy.

It explains how to run Meshy’s asynchronous jobs, monitor them, account for credits, and save results before download links expire.

meshy — Skill for Claude Code by shoyu-ramen

Install

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.

Any agent

npx skills add shoyu-ramen/meshy-claude-plugin --skill meshy

Clone the repo

git clone --depth 1 https://github.com/shoyu-ramen/meshy-claude-plugin

Made for: Claude Code.

Or install meshy, the plugin that ships this one along with the rest of its 1 skill, 2 commands.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/shoyu-ramen/meshy-claude-plugin/meshy/github.svg)](https://agentmods.dev/skills/shoyu-ramen/meshy-claude-plugin/meshy)

Your own site

<a href="https://agentmods.dev/skills/shoyu-ramen/meshy-claude-plugin/meshy"><img src="https://agentmods.dev/badge/skills/shoyu-ramen/meshy-claude-plugin/meshy/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/shoyu-ramen/meshy-claude-plugin/meshy"><img src="https://agentmods.dev/badge/skills/shoyu-ramen/meshy-claude-plugin/meshy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,204 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00065	$0.01204
Opus 5	$0.00032	$0.00602
Sonnet 5	$0.00013	$0.00241
Haiku 4.5	$0.00006	$0.00120

Measured 11d ago against content hash a863b6f6a68e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

meshy 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 11d 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.

skills/meshy/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Meshy 3D generation workflows

All Meshy operations are async tasks: a create tool returns a task_id instantly; generation takes seconds to minutes. Standard loop for every task:

Create (text_to_3d, image_to_3d, rig, …) → get task_id + task_type.
wait_for_task {task_type, task_id} — blocks with progress, default 300s timeout. On timeout it returns current progress without error; call it again to keep waiting.
download_assets {task_type, task_id, dest_dir} — always do this promptly after SUCCEEDED: Meshy file URLs expire ~3 days (non-Enterprise), then the outputs are gone. Pass an explicit dest_dir inside the user's project.

Check get_balance before expensive runs (free call). Task records are queryable with get_task / list_tasks; both return compact summaries — pass raw: true only if you truly need signed URLs.

Text → 3D (two stages)

text_to_3d {mode: "preview", prompt} → untextured mesh. 20 credits (meshy-6/lowpoly; 5 on older models).
Inspect result (thumbnail), then text_to_3d {mode: "refine", preview_task_id} → textured. 10 credits (2k/4k), 15 (8k). enable_pbr: true for metallic/roughness/normal maps.
Preview prompt ≤600 chars. Refine only textures the geometry — bad shape? Fix the preview prompt, not refine.
Fewer target_formats = faster completion.

Image → 3D

image_to_3d {image_url} — public URL or base64 data URI (jpg/png). 30 credits with texture on meshy-6; should_texture: false → 20.
Multiple angles of one object → multi_image_to_3d {image_urls: [1–4]}.
No local file URL support — encode local files as data:image/png;base64,....
Chain from generated images: text_to_image {generate_multi_view: true} (3 angles) → multi_image_to_3d {input_task_id}.

Character pipeline (generate → rig → animate)

Generate a humanoid model: use pose_mode: "a-pose" or "t-pose" in the create call — rigging needs clear limbs.
rig {input_task_id, height_meters} — 5 credits. Constraints: bipedal humanoid only, ≤300k faces, textured, facing +Z. Output includes basic walk/run.
search_animations {query} → pick action_id from ~680-action catalog (free).
animate {rig_task_id, action_id} — 3 credits each. post_process for fps change / USDZ / armature extraction.
Download rigged + animated FBX/GLB.

Read the full file on GitHub · 60 lines

Changes

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.

11d ago First seen · 60 lines · 65 tokens per session scan A a863b6f6a68e

Subscribe to this mod's changes

meshy is a skill published in the GitHub repository shoyu-ramen/meshy-claude-plugin (0 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 1,204 once invoked, about $0.0003 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.

Creative and media Game development

gameobject-component-destroy

Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.

IvanMurzak/Unity-MCP · 49 tokens

unity-version-split

Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).

IvanMurzak/Unity-MCP · 59 tokens

godot-signals-groups

Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…

gamedev-skills/awesome-gamedev-agent-skills · 95 tokens

meshy