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 remake-reelgit 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/remake-reel)<a href="https://agentmods.dev/skills/ronak-create/fablecut/remake-reel"><img src="https://agentmods.dev/badge/skills/ronak-create/fablecut/remake-reel/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/remake-reel"><img src="https://agentmods.dev/badge/skills/ronak-create/fablecut/remake-reel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00074 | $0.00831 |
| Opus 5.5 | $0.00030 | $0.00332 |
| Sonnet 5.5 | $0.00015 | $0.00166 |
| Haiku 4.5 | $0.00007 | $0.00083 |
Grade A, and why
remake-reel 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 today.
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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Remaking a reference edit
Given a video the user likes, FableCut extracts what is measurable about the edit — where the cuts land, where the beats are, how energy moves — and hands it back as a blueprint. The structure is deterministic; the creative mapping onto new footage is yours.
Get the blueprint
fablecut_analyze_reference {path:"C:\\…\\ref.mp4"}
Needs ffmpeg on PATH. It returns shot boundaries (cuts, shots[] with a
per-shot energy 0–100), music beats[] and bpm, a loudness energy curve,
and drop — the biggest musical rise. It also extracts the reference's music
track into the project and registers it as media, so the rebuild can sit on the
same song.
If obvious cuts were missed, lower threshold; if camera motion is being read
as cuts, raise it.
Rebuild
- Match the canvas: copy the reference's
width/height/fpsonto the project. Writebeatsintomarkersso the user can see the grid and the UI snaps drags to it. - Music on A1,
in: 0, running the full reference duration. - One clip per
shots[]entry on V1 at the samestartandduration. Match footage to each shot'senergy— calm material under ~40, motion over ~70 — and choose each clip'sinso something actually happens inside the window. - Land the hero shot on
drop. The standard garnish is a speed ramp settling into it, anadjustlayer withshake+rgbSplitfor one impact frame, or a whip transition on the way in. - Pace to taste: shots under ~0.6 s read as beat-flashes.
avgShotLentells you the reference's overall rhythm. - With the user's own music instead of the reference's,
fablecut_beats {clipId}finds its tempo, beat and drop;snap:truerolls the cuts onto the beat,retime:{every:2}re-cuts V1 so each shot lasts 2 beats. - Posting it vertically:
fablecut_reframe {aspect:"9:16"}makes a copy whose shots follow their subject.
No reference, just long footage? fablecut_highlights {duration:30} picks its
best moments (movement, sound, a clear picture) into a new sequence; then
steps 6 and 7. Look at the picks with fablecut_frame {time} and swap any
that miss.
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.
- today Changed · +10 lines c6b12de99768
- 1mo ago First seen · 56 lines · 74 tokens per session scan A 84e48b484850
remake-reel is a skill published in the GitHub repository ronak-create/FableCut (766 stars, last pushed today), licensed MIT. It adds 74 tokens to every session and 831 once invoked, about $0.0003 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
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-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-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-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…