Borrowing it
Nothing to install: this file belongs to LinHao-city/StoryMind. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/LinHao-city/StoryMind/main/.agents/skills/manimgl-best-practices/SKILL.mdgit clone --depth 1 https://github.com/LinHao-city/StoryMindWrote 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/linhao-city/storymind/manimgl-best-practices)<a href="https://agentmods.dev/skills/linhao-city/storymind/manimgl-best-practices"><img src="https://agentmods.dev/badge/skills/linhao-city/storymind/manimgl-best-practices/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/linhao-city/storymind/manimgl-best-practices"><img src="https://agentmods.dev/badge/skills/linhao-city/storymind/manimgl-best-practices.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 | $0.00167 | $0.02005 |
| Opus 5 | $0.00084 | $0.01002 |
| Sonnet 5 | $0.00033 | $0.00401 |
| Haiku 4.5 | $0.00017 | $0.00200 |
Grade A, and why
manimgl-best-practices 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 12d 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.
The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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.
- examples/attention_arcs_animation.py 8.1 KB runs code
- examples/attention_pattern_dots.py 4.3 KB runs code
- examples/attention_scenes.py 34 KB runs code
- examples/attention_softmax_masking.py 3.7 KB runs code
- examples/autoregressive_flow.py 7.0 KB runs code
- examples/basic_multihead.py 5.0 KB runs code
- examples/bloch_sphere_3d.py 6.9 KB runs code
- examples/block_collision_basic.py 5.4 KB runs code
- examples/blocks_3d.py 7.2 KB runs code
- examples/collision_phase_space.py 10 KB runs code
- examples/complex_s_plane.py 9.8 KB runs code
- examples/cost_function.py 3.9 KB runs code
- examples/cube_projection_3d.py 6.3 KB runs code
- examples/damped_solutions_splane.py 9.2 KB runs code
- examples/dot_product_visualization.py 5.5 KB runs code
- examples/double_slit_interference.py 11 KB runs code
- examples/eigenvalue_equations.py 7.2 KB runs code
- examples/eigenvector_flow_field.py 6.5 KB runs code
- examples/eigenvector_matrix_transformation.py 6.2 KB runs code
- examples/elastic_collision_vectors.py 10 KB runs code
- examples/embedding_matrix.py 5.5 KB runs code
- examples/equation_transforms.py 10.0 KB runs code
- examples/exponential_derivative.py 8.2 KB runs code
- examples/fibonacci_eigenvalues.py 5.9 KB runs code
- examples/gradient_descent_basic.py 6.8 KB runs code
- examples/hexagon_cube_correspondence.py 2.8 KB runs code
- examples/integration_visualization.py 6.9 KB runs code
- examples/laplace_integral.py 9.3 KB runs code
- examples/light_polarization.py 11 KB runs code
- examples/linear_regression.py 3.8 KB runs code
- examples/llm_prediction_pipeline.py 9.3 KB runs code
- examples/lorenz_attractor.py 5.3 KB runs code
- examples/lozenge_tiling.py 3.2 KB runs code
- examples/max_random_process.py 5.8 KB runs code
- examples/mlp_forward_pass.py 8.7 KB runs code
- examples/mlp_network_icon.py 3.2 KB runs code
- examples/mlp_neuron_activation.py 7.7 KB runs code
- examples/mlp_neurons_flow.py 10 KB runs code
- examples/mlp_relu_visualization.py 5.3 KB runs code
- examples/mlp_vector_space.py 8.6 KB runs code
- examples/mlp_weight_matrix.py 8.5 KB runs code
- examples/multi_head_attention.py 8.3 KB runs code
- examples/network_block_flow.py 8.4 KB runs code
- examples/neural_network_basic.py 4.3 KB runs code
- examples/parallax_starfield.py 6.3 KB runs code
- examples/probability_distribution.py 12 KB runs code
- examples/probability_output.py 12 KB runs code
- examples/quantum_gates.py 8.7 KB runs code
- examples/qubit_state_vector.py 6.0 KB runs code
- examples/query_key_dot_products.py 4.2 KB runs code
- examples/query_key_space_mapping.py 6.3 KB runs code
- examples/radial_wave_visualization.py 7.6 KB runs code
- examples/rotating_exponentials.py 9.3 KB runs code
- examples/semantic_similarity.py 5.8 KB runs code
- examples/simple_test.py 1.8 KB runs code
- examples/softmax_visualization.py 4.8 KB runs code
- examples/solve_damped_ode.py 9.1 KB runs code
- examples/spring_mass_system.py 9.6 KB runs code
- examples/sqrt_random_process.py 4.8 KB runs code
- examples/superposition_effect.py 9.0 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.
- 12d ago First seen · 216 lines · 167 tokens per session scan A acb89023c69f
manimgl-best-practices is a skill published in the GitHub repository LinHao-city/StoryMind (7 stars, last pushed 2mo ago), licensed AGPL-3.0. It adds 167 tokens to every session and 2,005 once invoked, about $0.0008 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 skills, from other repositories
manimce-best-practices
Trigger when: (1) User mentions "manim" or "Manim Community" or "ManimCE", (2) Code contains from manim import , (3) User runs manim CLI commands, (4) Working with Scene, MathTex, Create(), or ManimCE-specific classes. Best practices for Manim Community Edition - the community-maintained Python animation engine.…
figure
Hybrid figure pipeline (Nano Banana raster + rembg background removal + TikZ vector assembly). Includes a TikZ template library covering quantum circuits (quantikz), Feynman diagrams (tikz-feynman), circuits (circuitikz), molecules (chemfig), 2D/3D plots (pgfplots), energy-level diagrams, phase-space trajectories…
ai-media
Use when a creative goal must become a finished media file: pick and order generative-media models per modality — AI voiceover, image-to-video clips, score — then glue them with ffmpeg (mux, duck, loudnorm, concat). NOT still-image generation/editing (that is replicate-images); NOT code-rendered React compositing…
remotion-video
Use when you need to render an actual video file with Remotion — React compositions, the Composition/Sequence/TransitionSeries graph, transitions, burned-in word-by-word captions from a transcript, automatic silence removal, b-roll overlays, headless CI renders, and a final MP4 or MOV. NOT writing the script, hook…
minimax-video
Generate and edit videos using MiniMax H3, the state-of-the-art open multimodal generation model. Supports text-to-video, image-to-video (first/last frame), reference-to-video with multimodal context (images, video clips, audio references), native stereo sound, up to 15 seconds at 2K resolution, in-context…
minimax-music
Generate professional-quality music using the MiniMax CLOUD Music API (music-3.0). Supports full songs with vocals, purely instrumental tracks, AI lyrics writing, and cover generation from reference audio. Typical output is 2-3 minutes of finished stereo audio. Use when the user asks to create music, generate a song…