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 dcc-mcp/dcc-mcp-marmoset --skill marmoset-lookdevgit clone --depth 1 https://github.com/dcc-mcp/dcc-mcp-marmosetWrote 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/dcc-mcp/dcc-mcp-marmoset/marmoset-lookdev)<a href="https://agentmods.dev/skills/dcc-mcp/dcc-mcp-marmoset/marmoset-lookdev"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-marmoset/marmoset-lookdev/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/dcc-mcp/dcc-mcp-marmoset/marmoset-lookdev"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-marmoset/marmoset-lookdev.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 | $0.00046 | $0.00295 |
| Opus 5.5 | $0.00018 | $0.00118 |
| Sonnet 5.5 | $0.00009 | $0.00059 |
| Haiku 4.5 | $0.00005 | $0.00030 |
Grade A, and why
marmoset-lookdev 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 16d 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.
What it actually says
Marmoset Toolbag Lookdev
Inspect material bindings first. Frame by exact object UID when preparing a hero asset; omit the UID only when the full scene should determine the camera.
configure_color_output can select Toolbag's ACES tone mapper for visual
comparison. Toolbag does not expose an OCIO/ACEScg transform API, so this is
an output-boundary check rather than an OCIO-managed production workflow.
What ships with it
4 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.
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.
- 16d ago Changed dfbd002fff57
- 1mo ago First seen · 29 lines · 46 tokens per session scan A 4645013a2ef2
marmoset-lookdev is a skill published in the GitHub repository dcc-mcp/dcc-mcp-marmoset (3 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 295 once invoked, about $0.0002 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.
Other skills, from other repositories
godot-build-optimization
Analyze a Godot project and generate a version-aware SCons export-template profile, optional .gdbuild feature profile, and reproducible artifact-size report. Use when reducing packaged engine size before export; keep runtime validation and risky binary post-processing explicit.
designer-session
Host skill - inspect, author, save, and export a Substance 3D Designer graph. Use when an Agent needs bounded node, connection, parameter, gradient, output, package, resource, map, or SBSAR operations instead of arbitrary Python execution.
designer-offline
Offline artifact skill - cook hash-pinned SBS sources and render compiled SBSAR maps and bake pinned UV0 mesh positions and FBX colour IDs with installed official Substance tools without a Designer GUI.
godot-export
Domain skill — Inspect export presets and templates, package Godot projects for desktop EXE/standalone, Web, and mobile targets, and validate packaged-only resource, font, signing, and hosting failures. Use for export planning and release preflight, not for editing gameplay or scene content.
designer-effects
Host skill - apply discoverable procedural effect recipes (blur, warp, levels, sharpen, edge detect, blend, mask) to a Substance 3D Designer graph. Use when an Agent needs bounded effect-chain authoring instead of arbitrary node surgery.
godot-editor
Domain skill — Return errors captured by the DCC-MCP editor plugin. Capture the selected editor viewport to a PNG. Render a scene offscreen to a PNG and report the rendering method and unique-color count you judge a frame by. Both are diagnostics, not proof. Requires a windowed host. The call is refused under…