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 calesthio/generative-media-skills --skill meshy-3dgit clone --depth 1 https://github.com/calesthio/generative-media-skillsWrote 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/calesthio/generative-media-skills/meshy-3d)<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/meshy-3d"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/meshy-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/calesthio/generative-media-skills/meshy-3d"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/meshy-3d.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 8 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 108 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 399 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 413 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 434 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 441 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 447 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 461 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 399 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00199 | $0.07024 |
| Opus 5 | $0.00100 | $0.03512 |
| Sonnet 5 | $0.00040 | $0.01405 |
| Haiku 4.5 | $0.00020 | $0.00702 |
Grade A, and why
meshy-3d scanned grade A 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s https://api.meshy.ai/openapi/v2/text-to-3d \ How it starts
The opening of the file, as written. The whole thing — 491 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meshy 3D generation
Meshy is a hosted generative-3D service. You give it text or images; it returns
a textured mesh (GLB/FBX/OBJ/USDZ/STL/3MF), with optional PBR maps, remeshing,
UV, auto-rigging, and library animations. Everything runs as asynchronous
jobs: you POST a task, get a task ID, then poll, stream (SSE), or receive a
webhook until SUCCEEDED.
This skill covers driving Meshy well: choosing the right generation mode, writing prompts that separate geometry from texture, controlling topology and poly count, texturing and re-texturing, rigging and animating, exporting into a game/film/print pipeline, and judging whether the output is usable.
Evidence labels used below
- [Doc] — stated in official Meshy documentation, API reference, or help center (URLs in Sources). Volatile items carry a verification date.
- [1P-claim] — a first-party Meshy claim (marketing/blog/help) not independently verified. Treat as a claim, not a guarantee.
- [Heuristic] — production judgment from how generative-3D pipelines behave; verify against your own output.
Volatile facts (model IDs, credit costs, limits, formats) were verified 2026-07-10 against docs.meshy.ai. Re-check the changelog and pricing pages before quoting numbers to a user, because Meshy ships model versions and adjusts credit costs and promotions frequently.
When to use Meshy — and when not to
Use Meshy when you need:
- A single, coherent prop, character, or creature fast from a prompt or a reference image (concept-to-asset, game jam, previz, background dressing, crowd fillers, marketplace assets, 3D-print blanks). [Heuristic]
- A textured starting mesh you will clean up downstream rather than a final production hero asset. [Heuristic]
- Bulk asset generation where throughput and cost per asset matter more than authored topology. [Heuristic]
Do not reach for Meshy when:
- You need exact real-world dimensions or CAD tolerances (mechanical parts, enclosures, mounting brackets). Generative meshes are approximate; use CAD. [Heuristic]
- You need guaranteed-watertight, manifold geometry for manufacturing. Meshy offers printability analysis/repair and remesh, but does not guarantee a manifold result; validate in a slicer/mesh-repair tool. [Heuristic]
- You must edit the geometry of an existing hand-authored asset — Meshy regenerates, it does not surgically edit your mesh.
- The subject is a full scene (room, environment, multiple interacting objects). Text-to-3D and image-to-3D reconstruct one subject best; build the scene from separately generated parts in your engine. [Doc/Heuristic]
- You require clean animation-ready quad topology with edge loops around
deformation areas authored to spec. Meshy's
quadremesh is quad-dominant reconstruction, not artist-placed edge flow. [Heuristic] - Licensing forbids AI-generated assets, or your reference images are copyrighted in a way that would taint ownership (see Rights & licensing).
What ships with it
1 file 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.
- 8d ago First seen · 491 lines · 199 tokens per session scan A 734252124afd
meshy-3d is a skill published in the GitHub repository calesthio/generative-media-skills (170 stars, last pushed 1mo ago), licensed MIT. It adds 199 tokens to every session and 7,024 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
threejs-world-generation
Build deterministic, editable, free-viewpoint Three.js worlds from text or structured briefs. Use for cinematic 3D terrain, semantic regions, procedural biomes, explicit landmarks, environmental scattering, camera fly-throughs, world diagnostics, or requests for a real 3D environment rather than generated 2D footage.…
3d-asset-generation
Generate, reconstruct, inspect, and route production 3D assets for OpenMontage worlds using Atlas Cloud, fal.ai, licensed catalogs, and Blender.
sound-effects
Generate sound effects from text descriptions using ElevenLabs. Use when creating sound effects, generating audio textures, producing ambient sounds, cinematic impacts, UI sounds, or any audio that isn't speech. Supports looping, duration control, and prompt influence tuning.
character-rigging
Build data-driven 2D character rigs for local animation: parts, pivots, layers, constraints, views, and reusable rig packages.
pose-library-design
Design reusable 2D character pose libraries, action cycles, and expression states for data-driven animation.
rockstar-agent
Helps users create GTA V-style videos in the Rockstar Games aesthetic — from concept to camera-ready.