blender-managed
Skill4 starsChanged 21 days agoApache-2.0View on GitHub
Start a non-invasive Blender design session from Codex without installing a Blender Add-on. Use for new projects or when the user wants Codex to launch Blender.
In this repository44 other files it gives its agents.
- AGENTS.mdAGENTS.md
- openspec-apply-changeSkill
- openspec-archive-changeSkill
- openspec-exploreSkill
- openspec-proposeSkill
- openspec-sync-specsSkill
- openspec-update-changeSkill
- blender-ai-replicationSkill
- blender-asset-librarySkill
- blender-background-jobsSkill
- blender-character-animationSkill
- blender-character-riggingSkill
- blender-cinematographySkill
- blender-connectorSkill
- blender-curvesSkill
- blender-design-loopSkill
- blender-designSkill
- blender-exportSkill
- blender-grease-pencilSkill
- blender-hairSkill
- blender-hard-surfaceSkill
- blender-harness-drivingSkill
- blender-harnessSkill
- blender-inspectSkill
- blender-mcp-setupSkill
- blender-previewSkill
- blender-previsSkill
- blender-procedural-modelingSkill
- blender-quality-validationSkill
- blender-recoverSkill
- blender-render-compositingSkill
- blender-retopologySkill
- blender-scene-assemblySkill
- blender-sculpt-surfaceSkill
- blender-seedance-pipelineSkill
- blender-sequence-editingSkill
- blender-simulationSkill
- blender-to-dreaminaSkill
- blender-trackingSkill
- blender-useSkill
- blender-uv-materialSkill
- blender-video-originalSkill
- blender-video-recreateSkill
- blender-visual-loopSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 1 is distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
Use --execution-mode review_only for a read-only session.
- Very specific: line 17
Wait for the private 0600 session descriptor, then communicate through harness_cli.py.
- Very specific: line 18
Keep Blender alive until the user closes it or authorizes session.close.
- Very specific: line 21
Verify session.status reports the requested mode.
- Distinctive: line 24
If no foreground viewport exists, report that specific condition.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Managed Blender Session
Use python3 scripts/launch_harness.py --session-id <unique-id> --output-root <approved-root>.
For an authorized automatic task add --execution-mode auto_with_budget and repeated
--export-format blend --export-format mp4 for its requested formats; add
--allow-designed-proxies only when the user permitted original substitute assets.
Use --execution-mode review_only for a read-only session. Omission remains interactive.
The launcher starts scripts/managed_bootstrap.py in foreground mode with
--disable-autoexec. Do not change Blender preferences. A project path must be an authorized
regular .blend; omit it for a new design.
Wait for the private 0600 session descriptor, then communicate through harness_cli.py.
Keep Blender alive until the user closes it or authorizes session.close. Never fall back to
unreviewed arbitrary Python when the Harness fails to start.
Verify session.status reports the requested mode. The temporary Codex Live Session panel and
viewport header expose progress and takeover controls. Use view.set, view.focus,
playback.set_frame and playback.set rather than an expert script for UI review.
If no foreground viewport exists, report that specific condition; do not claim the user can
see operations. Read command reference.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

