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 agentmods add commands/choxos/mathvizagent/render-previewgit clone --depth 1 https://github.com/choxos/MathVizAgentWhat 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 | $0.00013 | $0.01507 |
| Opus 5 | $0.00006 | $0.00754 |
| Sonnet 5 | $0.00003 | $0.00301 |
| Haiku 4.5 | $0.00001 | $0.00151 |
Grade A, and why
render-preview 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 yesterday.
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 — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/render-preview - Rendering Commands Reference
Quick reference for rendering Manim animations at various quality levels.
Basic Render Commands
Quality Presets
# Low quality (480p15) - Quick preview
manim -pql scene_file.py SceneName
# Medium quality (720p30) - Testing
manim -pqm scene_file.py SceneName
# High quality (1080p60) - Production
manim -pqh scene_file.py SceneName
# 4K quality (2160p60) - Highest quality
manim -pqk scene_file.py SceneName
Quality Preset Details
| Flag | Resolution | FPS | Use Case |
|---|---|---|---|
-ql |
480p | 15 | Quick preview |
-qm |
720p | 30 | Testing, review |
-qh |
1080p | 60 | Production |
-qk |
2160p | 60 | 4K displays |
Common Options
Preview Options
# -p: Preview after render (opens video player)
manim -pql scene.py MyScene
# Without preview (just render)
manim -ql scene.py MyScene
# Preview specific section
manim -pql --from_animation_number 5 scene.py MyScene
Output Options
# Custom output file name
manim -pqm -o custom_name.mp4 scene.py MyScene
# Specify output directory
manim -pqm --media_dir ./output scene.py MyScene
# Transparent background (for compositing)
manim -pqm -t scene.py MyScene # Creates .mov with alpha
# GIF output
manim -pqm --format gif scene.py MyScene
Performance Options
# Disable caching (when debugging)
manim -pql --disable_caching scene.py MyScene
# Force re-render
manim -pql --flush_cache scene.py MyScene
# Verbose output (debugging)
manim -pql -v DEBUG scene.py MyScene
# Quiet output
manim -pql -v WARNING scene.py MyScene
Render All Scenes
# Render all scenes in a file
manim -qm scene_file.py -a
# Render all scenes with preview
manim -pqm scene_file.py -a
# Render specific scenes
manim -qm scene_file.py Scene1 Scene2 Scene3
Section-Based Rendering
If scenes use next_section():
# Save each section as separate file
manim -pql --save_sections scene.py MyScene
# Skip to specific section
manim -pql -n 0,2 scene.py MyScene # Render animations 0 through 2
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.
- yesterday First seen · 253 lines · 13 tokens per session scan A d65822c28ce5
render-preview is a command published in the GitHub repository choxos/MathVizAgent (1 stars, last pushed 3mo ago), licensed MIT. It adds 13 tokens to every session and 1,507 once invoked, about $0.0001 per session on Opus 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 2026-08-31.
Other commands, from other repositories
stt
Transcribe a local audio file or remote audio URL into text.
audition-voices
Generate voice audition samples for a character using Venice TTS.
status
Show 3d-design team status and recent activity.
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.
develop-image-prompt.eval
Generates a detailed image generation prompt from a document or content description. Good output: a prompt that is specific, visual, non-abstract, includes style/composition/lighting guidance, and is calibrated to the specified dimensions and style options.
diagram-create
Generate a diagram. Pass a prompt describing what to visualize.