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 ronak-create/FableCut --skill motion-graphicsgit clone --depth 1 https://github.com/ronak-create/FableCutWrote 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/ronak-create/fablecut/motion-graphics)<a href="https://agentmods.dev/skills/ronak-create/fablecut/motion-graphics"><img src="https://agentmods.dev/badge/skills/ronak-create/fablecut/motion-graphics/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/ronak-create/fablecut/motion-graphics"><img src="https://agentmods.dev/badge/skills/ronak-create/fablecut/motion-graphics.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 | $0.00164 | $0.03972 |
| Opus 5.5 | $0.00066 | $0.01589 |
| Sonnet 5.5 | $0.00033 | $0.00794 |
| Haiku 4.5 | $0.00016 | $0.00397 |
Grade A, and why
motion-graphics 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 15d 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Motion graphics with FableCut
Motion graphics in FableCut are ordinary clips on the timeline, so everything you know about clips (tracks, keyframes, transitions, masks, blend) still applies. Three pieces do the work:
- Shape layer: a clip with
kind:"shape"that draws vector items fromprops.shapes. It stays sharp at any scale and needs no media. - Null: a clip with
kind:"null"that never renders. It exists to be a parent. - Parent:
"parent":"<clip id>"makes a clip move, turn and scale with another one. Every visual clip also has an anchor point (anchorX,anchorY) that it turns and scales around.
For the full key table, read fablecut_docs {section:"schema"} once and see
its "Shapes, nulls and parenting", "Motion paths, motion blur and text on a
path", "Compositions (nested sequences)" and "Presets and templates" parts. The notes below cover how to use it well.
Coordinates (get these right first)
- A clip's
x/yare px from the canvas centre. When it has a parent, they are px from the parent's centre, in the parent's turned and scaled space. - A shape item's
x/yare px from the layer's origin (the layer clip'sx/y). Path and linepointsare px around the item's ownx/y. rotationis in degrees, clockwise, and y points down.- Item
keys[].tand clipkeyframes[].tare seconds from the clip's start, not from the timeline.
Workflow
fablecut_get_project {compact:true}to see the tracks and what is free. Shapes usually go on V2/V3 above the footage.- Add the layer with its items in one
addClip, or add an empty layer and thensetShapeitems into it by name. Name every item you plan to touch again (name:"Bar"), so later edits sayshape:"Bar"and not an index. - Animate the items with
keys, and the whole layer with clipkeyframes(x,y,scale,rotation,opacity,trimEnd, and so on). - Group things that move as one: put shapes in a
groupitem inside a layer, or parent whole clips (titles, images, other layers) to a null withsetParent. - Check it:
fablecut_get_project {compact:true}shows each layer as[3 shapes: rect #ffd166 2 keys, …]and each child asparent:c_….
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.
- 15d ago Changed · +71 lines · +52 tokens per session de97683f3bd6
- 16d ago First seen · 156 lines · 112 tokens per session scan A f8603f50d307
motion-graphics is a skill published in the GitHub repository ronak-create/FableCut (766 stars, last pushed today), licensed MIT. It adds 164 tokens to every session and 3,972 once invoked, about $0.0007 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 2026-10-12.
Other skills, from other repositories
ax-ai
This skill helps an LLM generate correct AI provider setup and configuration code using @ax-llm/ax. Use when the user asks about ai(), providers, models, routing, adaptive balancing, presets, embeddings, batch audio with ai.transcribe() or ai.speak(), extended thinking, context caching, or mentions…
ax-cpp-gen
Use when writing C++ code with axllm for AxGen programs, forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output parsing.
ax-go-gen
Use when writing Go code with github.com/ax-llm/ax/packages/go for AxGen programs, forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output parsing.
ax-java-gen
Use when writing Java code with dev.axllm:ax for AxGen programs, forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output parsing.
ax-agent-rlm
This skill helps an LLM generate correct AxAgent RLM/runtime code using @ax-llm/ax. Use when the user asks about RLM code execution, AxJSRuntime, contextFields, contextPolicy, liveRuntimeState, promptLevel, stage prompt controls, executorModelPolicy, maxRuntimeChars, agent.test(...), llmQuery(...), recursionOptions…
ax-gen
This skill helps an LLM generate correct AxGen code using @ax-llm/ax. Use when the user asks about ax(), AxGen, generators, forward(), streamingForward(), validation, assertions, streaming assertions, field processors, step hooks, self-tuning, or structured outputs. For MCP clients, transports, prompts, resources…