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 abrahamADSK/fpt-mcp --skill asset-creationgit clone --depth 1 https://github.com/abrahamADSK/fpt-mcpWrote 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/abrahamadsk/fpt-mcp/asset-creation)<a href="https://agentmods.dev/skills/abrahamadsk/fpt-mcp/asset-creation"><img src="https://agentmods.dev/badge/skills/abrahamadsk/fpt-mcp/asset-creation/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/abrahamadsk/fpt-mcp/asset-creation"><img src="https://agentmods.dev/badge/skills/abrahamadsk/fpt-mcp/asset-creation.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 | $0.00144 | $0.01986 |
| Opus 5 | $0.00072 | $0.00993 |
| Sonnet 5 | $0.00029 | $0.00397 |
| Haiku 4.5 | $0.00014 | $0.00199 |
Grade B, and why
asset-creation 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
- **Use MCP tools.** Never tell the user to do something manually if How it starts
The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Asset Creation Workflow
This skill defines the complete flow for creating 3D models from assets registered in ShotGrid. The goal is that the user never has to manually search for references or decide technical paths — the assistant does it for them, presenting clear options.
Context
The system has two MCP servers:
- fpt-mcp: ShotGrid API (sg_find, sg_download, etc.)
- maya-mcp: Maya + remote GPU (shape_generate_remote, shape_generate_text, maya_create_primitive, etc.)
Main Flow
Step 1: Identify the entity
Check if there is ShotGrid context in the message (it comes as JSON at the end of the prompt
when launched from the Qt console via AMI). Look for fields like entity_type, entity_id,
project_id.
If there is AMI context (entity_type + entity_id present):
- You already have the entity. Skip to Step 2.
If there is NO context (the user wrote something like "create the dragon model"):
- Extract from the user's text which asset to search for (name, type, description)
- Use
sg_findto search for matching Assets:sg_find(entity_type="Asset", filters=[["code", "contains", "<term>"]], fields=["id", "code", "sg_asset_type", "description", "image", "sg_status_list"]) - If there are multiple results, present the list and ask the user to choose:
Found these assets: 1. Dragon_Hero (Character) — ID #1478 2. Dragon_BG (Environment) — ID #1502 3. Dragon_Prop (Prop) — ID #1489 Which one? - If there is exactly one, confirm: "Found Asset 'Dragon_Hero' (#1478). Is this the one?"
- If there are no results, inform and ask if they want to search differently or create a new one.
Step 2: Discover visual reference material
Once the entity is identified, search ALL available visual material. This is crucial because the quality of the 3D model directly depends on the reference used.
Execute these searches in parallel (or sequentially if not possible):
2a. Asset's own thumbnail:
sg_find(entity_type="Asset",
filters=[["id", "is", <asset_id>]],
fields=["image", "code", "description"])
The image field is the asset's main thumbnail.
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 · 198 lines · 144 tokens per session scan B 6c1d299d90e7
asset-creation is a skill published in the GitHub repository abrahamADSK/fpt-mcp (1 stars, last pushed 23d ago), licensed MIT. It adds 144 tokens to every session and 1,986 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.