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-blender --skill blender-devgit clone --depth 1 https://github.com/dcc-mcp/dcc-mcp-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/dcc-mcp/dcc-mcp-blender/blender-dev)<a href="https://agentmods.dev/skills/dcc-mcp/dcc-mcp-blender/blender-dev"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-blender/blender-dev/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-blender/blender-dev"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-blender/blender-dev.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 | $0.00020 | $0.00753 |
| Opus 5.5 | $0.00008 | $0.00301 |
| Sonnet 5.5 | $0.00004 | $0.00151 |
| Haiku 4.5 | $0.00002 | $0.00075 |
Grade A, and why
blender-dev 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
blender-dev
Development-only diagnostics for Blender add-ons and adapter debugging.
Prefer typed domain skills for scene authoring. Use this skill when you need to
inspect add-on state, attach a checkout to sys.path, reload development
modules, run a named diagnostic check, inspect structured UI metadata, or start
an optional debugpy listener. Code execution helpers can run arbitrary Python
inside Blender and should be used only for explicit development or test flows.
Add-on lifecycle
list_addons / get_addon_status / enable_addon / disable_addon cover
add-ons Blender already knows about. These three cover the rest:
| Tool | Description |
|---|---|
install_addon |
Install a .py single-file add-on or a .zip bundle, then optionally enable it |
remove_addon |
Disable and uninstall an add-on (works in background mode) |
refresh_addons |
Rescan the add-on paths and report the count change |
Two things that otherwise surprise callers:
- Installing does not refresh the module list.
install_addonrunsaddon_refreshitself, but if you drop a file into an add-on directory by other means, callrefresh_addonsbeforelist_addonswill show it. - Give
addon_modulefor archives. Blender derives a module name from the file name, which does not always match the package inside a zip, so the install can succeed while the module never appears. Passingaddon_modulelets the tool confirm it; if the name is wrong you get an error naming it instead of a silent success. remove_addondoes not use Blender'saddon_removeoperator. That operator callscontext.area.tag_redraw(), which isNoneunderblender --background, so it raises there. Removal instead disables through the operator, deletes the module files directly, refreshes, and then confirms the add-on is gone — if it is still registered the call fails rather than reporting success. Single-file add-ons delete the.py; packages delete the whole directory.
What ships with it
17 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.
- scripts/attach_project.py 388 B runs code
- scripts/capture_ui_snapshot.py 391 B runs code
- scripts/disable_addon.py 382 B runs code
- scripts/enable_addon.py 378 B runs code
- scripts/find_ui_elements.py 387 B runs code
- scripts/get_addon_status.py 380 B runs code
- scripts/get_python_environment.py 404 B runs code
- scripts/install_addon.py 427 B runs code
- scripts/list_addons.py 372 B runs code
- scripts/refresh_addons.py 426 B runs code
- scripts/reload_modules.py 393 B runs code
- scripts/remove_addon.py 405 B runs code
- scripts/run_check.py 371 B runs code
- scripts/run_entrypoint.py 399 B runs code
- scripts/run_script.py 381 B runs code
- scripts/start_debug_server.py 406 B runs code
- tools.yaml 13 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 Changed · +29 lines 83035ce1d958
- 1mo ago Changed · +2 lines db1be1c24cfa
- 1mo ago First seen · 41 lines · 20 tokens per session scan A 9429171cdcb9
blender-dev is a skill published in the GitHub repository dcc-mcp/dcc-mcp-blender (50 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 753 once invoked, about $0.0001 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
blender-reference-modeling
Build, compare, review, or repair a Blender model against an actual supplied image, photograph, concept, or visual reference using adaptive decomposition, measurable proportions, evidence scoring, and bounded repair. Use only when the request explicitly concerns model creation or quality against visual form criteria…
blender-retopology
Improve Meshy, Tripo or other existing Blender meshes with deliberate editable topology, source-preserving cleanup, reduction, remeshing or reference-derived reconstruction, followed by geometry and appearance checks. Use for dense generated meshes, human-style edge flow, hard-surface rebuilding or character…
blender-bridge
Operate Blender Agent Bridge through its stable five-tool MCP gateway for scene inspection, modeling, materials, rigging, animation, simulation, rendering, external assets, trusted scripts, and preview decisions. Use whenever an agent must work in a live Blender scene through Blender Bridge, especially when only…
dcc-diagnostics
Infrastructure skill — DCC-agnostic observability primitives: capture screenshots, query audit logs, inspect tool performance metrics, and monitor process health. Works in any DCC environment (Maya, Blender, Houdini, Unreal, etc.) or standalone Python. Use for debugging any skill failure or verifying DCC state. Not…
qt-ui-inspector
Infrastructure skill — DCC-agnostic Qt UI introspection: list top-level windows, find widgets by name/class, describe widget properties, walk the widget tree, and poll for availability. Works in any DCC with a Qt binding (Maya, Blender, Houdini, Unreal, etc.). All tools are read-only and lazy-loaded.
3dsmax-scripting
Domain skill - run explicit 3ds Max scripting checks and inspect host-side developer surfaces. Use for debugging automation, resolving nodes, and inspecting runtime symbols when typed tools are not enough.