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 CheshireJCat/blender --skill create-3d-modelgit clone --depth 1 https://github.com/CheshireJCat/blenderWrote 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/cheshirejcat/blender/create-3d-model)<a href="https://agentmods.dev/skills/cheshirejcat/blender/create-3d-model"><img src="https://agentmods.dev/badge/skills/cheshirejcat/blender/create-3d-model/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/cheshirejcat/blender/create-3d-model"><img src="https://agentmods.dev/badge/skills/cheshirejcat/blender/create-3d-model.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 | $0.00144 | $0.02582 |
| Opus 5.5 | $0.00058 | $0.01033 |
| Sonnet 5.5 | $0.00029 | $0.00516 |
| Haiku 4.5 | $0.00014 | $0.00258 |
Grade A, and why
create-3d-model 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create 3D Model
Turn text, images, wireframes, multiview references, or existing assets into validated 3D models. Use Blender as the production backend and editable source environment, not as the definition of the product. Inspect the inputs and open scene, route the request to the smallest relevant module set, execute controlled bpy changes, inspect visual evidence, iterate, export the model, and preserve the engineering source.
This DeepSeek Harness plugin registers the complete 30-part capability stack: this top-level orchestrator plus 29 independently loadable domain skills. Load only the domain skills required by the request.
Start here
- Read references/dsh-integration.md before the first Blender tool call in a task.
- Read references/capability-map.md and select only the skills needed for the request.
- Load a selected module with the DSH
skilltool using its kebab-case name, such asblender-modeling,reference-to-3d, orwireframe-to-3d. Resolve its resources from the directory reported by the skill loader. - Treat this file and
dsh-integration.mdas higher priority than a vendored module when tool naming, scene safety, output paths, or runtime guidance differs.
Do not read every module preemptively. Load the orchestrator or domain module first, then follow a dependency only when its gate is reached.
Discover Blender capabilities
- Call
blender_statusbefore the first modeling operation. It reports Blender, the analysis runtime, registered skills, helpers, and workspace. - Use
blender_scene_infoandblender_object_infofor structural inspection. Useblender_importbefore editing a non-Blend asset. - Use
blender_pythonfor controlledbpychanges,blender_previewfor camera-free blockout evidence,blender_renderorblender_render_framesfor presentation/animation evidence, andblender_exportfor portable deliverables. - Run
blender_validate_scenebefore export andblender_validate_exportafter export. For reference, wireframe, contour, multiview, UV, texture, look, repair, or animation QA, discover and run deterministic helpers throughblender_helper_catalogandblender_helper_run. - If
blender_status.availableis false, stop and report the executable/configuration error. Do not claim Blender work completed while the backend is unavailable. - Every file path must stay inside the current dsh workspace unless the plugin was explicitly configured otherwise. Keep Poly Haven, Sketchfab, Hyper3D, Hunyuan3D, and other network asset or generation features disabled unless the user explicitly requests them.
What ships with it
60 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.
- LICENSE 1.0 KB
- references/blender-5-compat.md 3.3 KB
- references/capability-map.md 6.4 KB
- references/core/assembly-order.md 4.8 KB
- references/core/blender-version-compat.md 3.9 KB
- references/core/common-object-dimensions.md 12 KB
- references/dsh-integration.md 8.0 KB
- references/modeling-patterns.md 7.2 KB
- references/modules/animation-quality-gate/scripts/animation_contact_sheet.py 1.9 KB runs code
- references/modules/animation-quality-gate/SKILL.md 2.1 KB
- references/modules/atlas-uv-fitting/scripts/atlas_region_detector.py 2.3 KB runs code
- references/modules/atlas-uv-fitting/scripts/atlas_region_mapper.py 2.2 KB runs code
- references/modules/atlas-uv-fitting/SKILL.md 3.2 KB
- references/modules/blender-animation/references/overview.md 9.6 KB
- references/modules/blender-animation/SKILL.md 9.9 KB
- references/modules/blender-cameras/references/overview.md 9.0 KB
- references/modules/blender-cameras/SKILL.md 10 KB
- references/modules/blender-export/references/overview.md 10 KB
- references/modules/blender-export/SKILL.md 8.5 KB
- references/modules/blender-lighting/references/overview.md 9.9 KB
- references/modules/blender-lighting/SKILL.md 21 KB
- references/modules/blender-materials/references/overview.md 12 KB
- references/modules/blender-materials/SKILL.md 21 KB
- references/modules/blender-modeling/references/overview.md 9.9 KB
- references/modules/blender-modeling/SKILL.md 14 KB
- references/modules/blender-pro-workflow/references/overview.md 10 KB
- references/modules/blender-pro-workflow/SKILL.md 9.3 KB
- references/modules/blender-rendering/references/overview.md 10 KB
- references/modules/blender-rendering/SKILL.md 9.8 KB
- references/modules/blender-skill-harmonizer/references/handoff-contracts.md 1.5 KB
- references/modules/blender-skill-harmonizer/scripts/skill_graph_audit.py 2.9 KB runs code
- references/modules/blender-skill-harmonizer/SKILL.md 7.0 KB
- references/modules/blender-uv-texturing/references/overview.md 1.1 KB
- references/modules/blender-uv-texturing/SKILL.md 6.6 KB
- references/modules/closed-surface-uv-coverage/scripts/surface_texture_coverage_audit.py 2.9 KB runs code
- references/modules/closed-surface-uv-coverage/SKILL.md 3.8 KB
- references/modules/contour-to-mesh/scripts/mask_to_mesh_recipe.py 4.4 KB runs code
- references/modules/contour-to-mesh/scripts/source_locked_skin_recipe.py 5.7 KB runs code
- references/modules/contour-to-mesh/SKILL.md 4.5 KB
- references/modules/fit-repair-optimizer/scripts/fit_repair_queue.py 5.2 KB runs code
- references/modules/fit-repair-optimizer/SKILL.md 3.2 KB
- references/modules/landmark-fit-repair/scripts/landmark_fit_report.py 1.5 KB runs code
- references/modules/landmark-fit-repair/SKILL.md 2.0 KB
- references/modules/mascot-logo-reconstruction/SKILL.md 3.6 KB
- references/modules/multiview-constraint-solver/scripts/view_constraint_report.py 3.5 KB runs code
- references/modules/multiview-constraint-solver/SKILL.md 2.1 KB
- references/modules/multiview-fit-loop/scripts/multiview_fit_report.py 5.3 KB runs code
- references/modules/multiview-fit-loop/SKILL.md 2.7 KB
- references/modules/orbital-hud-motion/scripts/orbit_layout_manifest.py 1.3 KB runs code
- references/modules/orbital-hud-motion/SKILL.md 2.3 KB
- references/modules/orthographic-registration/scripts/register_views.py 2.2 KB runs code
- references/modules/orthographic-registration/SKILL.md 2.0 KB
- references/modules/quality-refinement-autoloop/scripts/ralph_autoloop_plan.py 2.7 KB runs code
- references/modules/quality-refinement-autoloop/scripts/release_readiness_check.py 2.1 KB runs code
- references/modules/quality-refinement-autoloop/scripts/sanitize_skill_contributions.py 1.3 KB runs code
- references/modules/quality-refinement-autoloop/SKILL.md 5.0 KB
- references/modules/reference-analysis-validator/references/metrics-and-thresholds.md 1.5 KB
- references/modules/reference-analysis-validator/scripts/reference_manifest_compiler.py 5.2 KB runs code
- references/modules/reference-analysis-validator/scripts/render_overlay_validator.py 4.0 KB runs code
- references/modules/reference-analysis-validator/SKILL.md 3.3 KB
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 · 118 lines · 144 tokens per session scan A 3ea560aaf604
create-3d-model is a skill published in the GitHub repository CheshireJCat/blender (55 stars, last pushed 11d ago), licensed MIT. It adds 144 tokens to every session and 2,582 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
dsh-tui-guide
Use when the user asks about dsh-tui itself (usage, shortcuts, config, themes, migration, VS Code). Load before answering; skip for normal coding tasks.
video-recap
A workflow that turns a supplied video into a Chinese narrated recap by combining video understanding, story planning, editing, voiceover, and final assembly.
video-assemble
A video post-production skill for combining narration, source audio, and subtitles into a final video. It can mix voice-over with the original sound, create SRT and ASS subtitle files, optionally burn subtitles into the picture, and standardize loudness.
workflow-manager
A writing workflow tracker for chapter-based projects. It records whether each chapter is being assembled, drafted, reviewed, confirmed, polished, or archived.
dog-import-query
Query a smart-import DoG graph after a novel has been split into chapters. Use to inspect import completeness, AI precheck errors, and pending outline/asset/canonical setup.
review-chapter
A six-part review of a manuscript chapter. It compares the chapter with the outline and reports quality, coverage, review status, and problems supported by evidence from the text.