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 qfoldit/Protein-Design-MCP --skill scene-exportgit clone --depth 1 https://github.com/qfoldit/Protein-Design-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/qfoldit/protein-design-mcp/scene-export)<a href="https://agentmods.dev/skills/qfoldit/protein-design-mcp/scene-export"><img src="https://agentmods.dev/badge/skills/qfoldit/protein-design-mcp/scene-export/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/qfoldit/protein-design-mcp/scene-export"><img src="https://agentmods.dev/badge/skills/qfoldit/protein-design-mcp/scene-export.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 | $0.00187 | $0.01196 |
| Opus 5.5 | $0.00075 | $0.00478 |
| Sonnet 5.5 | $0.00037 | $0.00239 |
| Haiku 4.5 | $0.00019 | $0.00120 |
Grade A, and why
qfoldit-scene-export 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 2mo 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
qFoldIT Scene Export
Converts a universal ScenePlan (nodes = primitives with position/
rotation/scale/material, edges = bonds/connections, optional lights and
camera) into real output files. Built specifically so it needs no live
engine — the honest fallback tier below qfoldit-engine-bridge's
live-control integrations (Unreal/Unity), for when those aren't
connected, or for engines where only knowledge-search tools exist
(Unigine, Omniverse) and a human needs an actual file to import.
What's implemented, and how thoroughly each was verified
| Exporter | Format | Verification depth |
|---|---|---|
export_obj.py |
Wavefront OBJ + MTL | Strong: structural validity (indices in range, materials cross-referenced) AND real geometric correctness (decoded vertex positions checked against known atom coordinates) |
export_gltf.py |
glTF 2.0 (self-contained, base64-embedded) | Strong: full manual spec-conformance check (buffer/bufferView/accessor cross-referencing, decoded binary geometry) — no pygltflib available in this sandbox, so this was written by hand against the spec, not rubber-stamped by an existing validator |
export_threejs.py |
Standalone interactive HTML | Strong but different kind: JS syntax verified (node --check), AND the actual rendering logic was visually confirmed correct by rendering a real methane molecule in a live browser widget during this skill's development — genuine visual proof, not just a syntax check |
export_godot_gdscript.py |
Godot 4.x GDScript | Weak, disclosed as such: only brace-balance/known-class-name checks. No live Godot instance was available to actually run this. Treat as "written to the documented API," not "tested." |
When to use which exporter
- OBJ: broadest compatibility (every engine and DCC tool imports it). No animation, no native hierarchy — geometry is baked to world space. Good default when you don't know the target tool yet.
- glTF: the modern standard for web/AR/most game engines; better material fidelity (PBR metallic/roughness) than OBJ; self-contained single file (no separate texture/bin files to lose track of).
- Three.js HTML: when the user wants something viewable RIGHT NOW with zero installs — just open the file in a browser. Needs internet access to load Three.js from a CDN (not offline-capable, unlike the OBJ/glTF output files).
- Godot GDScript: only if the user is specifically targeting Godot AND understands this hasn't been run against a real Godot instance — say this explicitly every time this exporter is used.
What ships with it
16 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.
- evals/__pycache__/run_tests.cpython-312.pyc 11 KB
- evals/eval_set.json 3.7 KB
- evals/run_tests.py 6.2 KB runs code
- README.md 3.5 KB
- references/engine_notes.md 5.2 KB
- references/scene_plan_reference.md 3.6 KB
- scripts/__pycache__/export_gltf.cpython-312.pyc 11 KB
- scripts/__pycache__/export_godot_gdscript.cpython-312.pyc 11 KB
- scripts/__pycache__/export_obj.cpython-312.pyc 15 KB
- scripts/__pycache__/export_threejs.cpython-312.pyc 10 KB
- scripts/__pycache__/scene_plan.cpython-312.pyc 16 KB
- scripts/export_gltf.py 7.3 KB runs code
- scripts/export_godot_gdscript.py 6.7 KB runs code
- scripts/export_obj.py 8.4 KB runs code
- scripts/export_threejs.py 5.7 KB runs code
- scripts/scene_plan.py 11 KB runs code
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.
- 2mo ago First seen · 75 lines · 187 tokens per session scan A f85a69a5467d
qfoldit-scene-export is a skill published in the GitHub repository qfoldit/Protein-Design-MCP (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 187 tokens to every session and 1,196 once invoked, about $0.0007 per session on Opus 5.5. 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.
qfoldit-scene-export compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| qfoldit-scene-exportqfoldit/Protein-Design-MCP | Skill | 1 | 2mo ago | Apache-2.0 | A | 187 | Claude Code |
| playtest-reportDonchitos/Claude-Code-Game-Studios | Skill | 36k | 19d ago | MIT | A | 20 | Claude Code |
| godot-signals-groupsgamedev-skills/awesome-gamedev-agent-skills | Skill | 6.9k | 10d ago | Apache-2.0 | A | 95 | Claude Code |
| scenario-unreal-gameplayscenario-labs/skills | Skill | 3.2k | yesterday | MIT | A | 121 | Claude Code |
| motionOpenDCAI/GameFactory-3A | Skill | 1.0k | 9d ago | Apache-2.0 | A | 0 | Claude Code, Codex |
| unity-addressablesBesty0728/Unity-Skills | Skill | 1.9k | yesterday | MIT | A | 25 | Claude Code, Codex |
| unity-manual-componentBesty0728/Unity-Skills | Skill | 1.9k | yesterday | MIT | A | 36 | Claude Code, Codex |