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-substance3d-designer --skill designer-effectsgit clone --depth 1 https://github.com/dcc-mcp/dcc-mcp-substance3d-designerWrote 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-substance3d-designer/designer-effects)<a href="https://agentmods.dev/skills/dcc-mcp/dcc-mcp-substance3d-designer/designer-effects"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-substance3d-designer/designer-effects/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-substance3d-designer/designer-effects"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-substance3d-designer/designer-effects.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 | $0.00053 | $0.00780 |
| Opus 5.5 | $0.00021 | $0.00312 |
| Sonnet 5.5 | $0.00011 | $0.00156 |
| Haiku 4.5 | $0.00005 | $0.00078 |
Grade A, and why
designer-effects 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 1mo 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Designer Effects
Apply procedural effect recipes on top of an existing Designer graph.
Honest capability boundary
Substance 3D Designer has no scene-level effect stack. An "effect" here is a
compositing or filter node inserted into the graph topology, created and wired
through the adapter's verified create_node and connect_nodes primitives.
There is no viewport effect, no post-process pass, and no shader authoring.
This skill is experimental: recipe availability is a runtime property, not a
documented guarantee. The 7 effect recipes resolve against the live
node-definition inventory at call time, so treat the available flag reported
by list_effect_recipes as the only source of truth for whether a recipe exists
in the running Designer build. Never assume a recipe name implies a node type.
Recipe discovery instead of hardcoded node types
Node type URLs differ between Designer builds. Each recipe declares an ordered list of candidate URLs and resolves the first one the live node-definition inventory actually advertises.
- Run
list_effect_recipesfirst. It reports every recipe with its resolvedtype_urland anavailableflag. - A recipe that resolves to nothing fails closed with
RECIPE_UNAVAILABLEand lists the candidates it tried. Nothing is created in that case. apply_effect_chainresolves every step before creating any node, so a missing type cannot leave a partial chain behind. Port lookup, every intermediate connection, the final target connection, and export are all inside one rollback unit: if any of them fails, the nodes created by that call are removed. The same guarantee applies toapply_effect.
Tool notes
apply_effectinserts one recipe node. Passtarget_nodeandtarget_propertyto wire its output onward; omit them to leave the node unwired for manual inspection.apply_effect_chainwiressource_node.source_propertyinto step 1, then each step into the next, then the last step into the optional target. Ports are resolved by discovery, not by a fixed name: texture-typed ports win, then conventionally named ports (input/output,source,result), then the first available port. Do not assume a literalinputoroutputid.- Chain length is bounded to 12 steps.
spacingspaces nodes horizontally in native graph coordinates fromorigin. - Use
export_graph_statefromdesigner-sessionafter a chain to verify the resulting topology.
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.
- 1mo ago Changed 89f2afc48f04
- 1mo ago Changed · +6 lines d592b17efcd5
- 1mo ago First seen · 67 lines · 53 tokens per session scan A cd49fb0371b0
designer-effects is a skill published in the GitHub repository dcc-mcp/dcc-mcp-substance3d-designer (3 stars, last pushed yesterday), licensed MIT. It adds 53 tokens to every session and 780 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 2026-09-20.
Other skills, from other repositories
painter-project
Host skill - inspect and author the current Substance 3D Painter project. Use when creating or checking projects, building uniform or texture-driven PBR layers, masks and generators, baking mesh maps, importing resources, or exporting. Not for arbitrary JavaScript execution.
painter-lighting
Inspect and control Substance 3D Painter scene lighting. Painter has no light objects, so lighting is the environment map and its exposure and rotation. Use when setting up an HDRI, matching a look-dev environment, or reading the current lighting configuration. Not for lamps, shadows, or light rigs.
painter-material
Inspect and author the channel-level material surface of a Substance 3D Painter layer stack. Use when reading which channels a stack carries, enabling or disabling the channels a layer contributes, or setting uniform channel values. Not for creating layers, importing textures, or painting strokes.
painter-compositing
Inspect and control how a Substance 3D Painter layer composites with the layers beneath it - visibility, opacity, blending mode, and mask state. Use when stacking layers non-destructively or tuning how one layer combines with another. Not for creating or deleting layers, and not for painting strokes.
painter-diagnostics
Read-only readiness diagnostics for a running Substance 3D Painter adapter.
photoshop-layers
Adobe Photoshop layer operations — create, delete, reorder, duplicate, rename, set opacity/visibility, fill, blend modes.