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 jasonjgardner/blockbench-mcp-project --skill blockbench-substancegit clone --depth 1 https://github.com/jasonjgardner/blockbench-mcp-projectWrote 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/jasonjgardner/blockbench-mcp-project/blockbench-substance)<a href="https://agentmods.dev/skills/jasonjgardner/blockbench-mcp-project/blockbench-substance"><img src="https://agentmods.dev/badge/skills/jasonjgardner/blockbench-mcp-project/blockbench-substance/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/jasonjgardner/blockbench-mcp-project/blockbench-substance"><img src="https://agentmods.dev/badge/skills/jasonjgardner/blockbench-mcp-project/blockbench-substance.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 | $0.00220 | $0.01977 |
| Opus 5.5 | $0.00088 | $0.00791 |
| Sonnet 5.5 | $0.00044 | $0.00395 |
| Haiku 4.5 | $0.00022 | $0.00198 |
Grade A, and why
blockbench-substance 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blockbench + Adobe Substance 3D
Optional and advanced. Most Blockbench work never needs this: paint with blockbench-texturing, generate with blockbench-gpt-image-textures, derive normal/MER with blockbench-albedo-to-pbr. Use this skill only when the user asks for Substance or already has .sbsar/.sbs/Painter assets. It needs a licensed Adobe Substance 3D install. Load blockbench-use first and blockbench-pbr-materials to assign results.
Substance produces image files. Blockbench stays the source of geometry and UVs. Every path ends with files imported through create_texture (data, pbr_channel) or import_texture_set.
0. Locate the tools
python scripts/sat_locate.py
Designer bundles sbsrender, sbscooker, sbsupdater and substance3d_baker, off PATH, in C:\Program Files\Adobe\Adobe Substance 3D Designer\. sbsmutator and the pysbs Python API come only with the standalone Substance Automation Toolkit. Painter is a GUI app driven over HTTP. If nothing is found, stop and tell the user; do not install Adobe software.
Pick the path
| Goal | Tool | Reference |
|---|---|---|
| Procedural material (bricks, rust, leaves) as Blockbench textures | sat_render.py → sbsrender |
sat-cli.md |
Have a .sbs graph, need an .sbsar |
sbscooker (sbsupdater first if old) |
sat-cli.md |
Edit/specialise a .sbs headlessly |
sbsmutator (SAT only) |
sat-cli.md |
| AO / curvature / ID / position masks from the model | substance3d_baker |
baker.md |
| Hand-paint the model with smart materials | Painter + painter_remote.py |
painter.md |
| Pack Bedrock MER, convert bit depth, flip normal green, shrink | prep_maps.py |
below |
What ships with it
9 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.
- references/baker.md 7.4 KB
- references/painter.md 5.6 KB
- references/sat-cli.md 8.4 KB
- scripts/painter_bedrock_export.py 3.6 KB runs code
- scripts/painter_new_project.py 2.0 KB runs code
- scripts/painter_remote.py 5.2 KB runs code
- scripts/prep_maps.py 8.1 KB runs code
- scripts/sat_locate.py 4.5 KB runs code
- scripts/sat_render.py 7.4 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.
- 1mo ago First seen · 88 lines · 220 tokens per session scan A 4895083926f0
blockbench-substance is a skill published in the GitHub repository jasonjgardner/blockbench-mcp-project (27 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 220 tokens to every session and 1,977 once invoked, about $0.0009 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 2026-09-25.
blockbench-substance compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| blockbench-substancejasonjgardner/blockbench-mcp-project | Skill | 27 | 1mo ago | Apache-2.0 | A | 220 | Claude Code |
| ux-reviewDonchitos/Claude-Code-Game-Studios | Skill | 36k | 18d ago | MIT | A | 42 | Claude Code |
| ux-designDonchitos/Claude-Code-Game-Studios | Skill | 36k | 18d ago | MIT | A | 31 | Claude Code |
| game-ui-uxgamedev-skills/awesome-gamedev-agent-skills | Skill | 6.9k | 9d ago | Apache-2.0 | A | 123 | Claude Code |
| roblox-uigamedev-skills/awesome-gamedev-agent-skills | Skill | 6.9k | 9d ago | Apache-2.0 | A | 101 | Claude Code, Codex |
| scenario-roblox-uiscenario-labs/skills | Skill | 3.2k | yesterday | MIT | A | 153 | Claude Code |
| scenario-unity-uiscenario-labs/skills | Skill | 3.2k | yesterday | MIT | A | 124 | Claude Code |