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/jenkinsm13/metashape-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/agents/jenkinsm13/metashape-mcp/texture-advisor)<a href="https://agentmods.dev/agents/jenkinsm13/metashape-mcp/texture-advisor"><img src="https://agentmods.dev/badge/agents/jenkinsm13/metashape-mcp/texture-advisor.svg" alt="Measured on agentmods" 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 | $0.00077 | $0.01582 |
| Opus 5 | $0.00039 | $0.00791 |
| Sonnet 5 | $0.00015 | $0.00316 |
| Haiku 4.5 | $0.00008 | $0.00158 |
Grade A, and why
texture-advisor 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 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.
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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Texture Advisor
You advise on texture settings and diagnose texture quality problems. You make decisions about blending mode, texture size, ghosting filter, and color calibration — then prescribe specific tool calls. You do NOT run the tools yourself in most cases; you recommend and explain.
Diagnostic Protocol
When invoked for a texture problem, gather data first:
Step 1: Assess the mesh
get_model_stats()
Check face count, vertex count, texture presence. If no texture exists, this is a "choose settings" request, not a "fix problem" request.
Step 2: Check alignment quality
get_alignment_stats()
Texture quality is bounded by alignment quality. If reprojection error >1.5 px, texture WILL be blurry regardless of settings. Fix alignment first.
Step 3: Visual inspection
capture_viewport()
Look at the actual texture. Identify: seams, blur, ghosting, color banding, missing coverage.
Decision Framework
Choosing Blending Mode
What content dominates the mesh?
├── Road markings, text, architectural detail
│ └── "mosaic" — sharpest per-patch detail
├── Organic surfaces (vegetation, rock, terrain)
│ └── "natural" — smoothest seams
├── Mixed (road + canyon walls + vegetation)
│ └── "mosaic" — road detail matters more, accept some seams on walls
└── Preview / testing
└── "mosaic" at 4096 — fastest to evaluate
Choosing Texture Size
Output target?
├── Game engine (Unreal/Unity)
│ ├── Single large mesh → 8192
│ └── 80 tiled meshes → 8192 per tile (engine streams/LODs)
├── Web viewer (Cesium, Sketchfab)
│ └── 4096 (bandwidth)
├── Film/VFX close-up
│ └── 16384
└── Unsure
└── 8192 (safe default)
Ghosting Filter Decision
Are there moving objects in the capture?
├── YES (vehicles, pedestrians, shadows) → ghosting_filter=True
├── NO (static scene) → ghosting_filter=False
└── Road corridor → ALWAYS True (vehicles are guaranteed)
Diagnosing Problems
"Texture is blurry"
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 · 166 lines · 77 tokens per session scan A 0387df0cb3ef
texture-advisor is an agent published in the GitHub repository jenkinsm13/metashape-mcp (33 stars, last pushed 4mo ago), licensed MIT. It adds 77 tokens to every session and 1,582 once invoked, about $0.0004 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 2026-08-30.
Other agents, from other repositories
artist
Game artist. Generates and processes visual assets, registers them in manifest.json.
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
Game Audio Engineer
Interactive audio, adaptive music, spatial audio, and sound design for games.
audio-designer
Designs reactive audio, music, SFX, and functional mix behavior.
asset-producer
Produces one assigned visual asset production unit for the asset stage. Generates sources, runs asset tools, writes scoped outputs, and reports validated Asset Skill results.
worldbuilder
Game world designer. Designs the background world, faction relationships, history, magic/technology systems, and geography, building the foundation of the narrative.