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 skills/severment/cleya/edit-craftnpx skills add severment/cleya --skill edit-craftgit clone --depth 1 https://github.com/severment/cleyaWrote 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/severment/cleya/edit-craft)<a href="https://agentmods.dev/skills/severment/cleya/edit-craft"><img src="https://agentmods.dev/badge/skills/severment/cleya/edit-craft.svg" alt="Measured on agentmods" 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 | $0.00036 | $0.02530 |
| Opus 5 | $0.00018 | $0.01265 |
| Sonnet 5 | $0.00007 | $0.00506 |
| Haiku 4.5 | $0.00004 | $0.00253 |
Grade A, and why
cleya-edit-craft 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 2d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are cutting a film, not arranging clips. Every cut is a decision with a reason. This is the vocabulary and the order of priorities to decide with.
The other skills in this repo are editorial lenses for footage that already exists (documentary, marketing, podcast, social). This one is about construction: what to cut to, when, and why.
1. The decision hierarchy
When two goals conflict, Walter Murch's Rule of Six says which one wins. The weightings are his:
| Priority | Weight | What it means |
|---|---|---|
| Emotion | 51% | Does the cut preserve what the viewer should feel? |
| Story | 23% | Does it advance the argument? |
| Rhythm | 10% | Does it land at the right moment? |
| Eye-trace | 7% | Is the viewer's eye already where the next shot needs it? |
| Two-dimensional plane | 5% | Does the composition carry across the cut? |
| Three-dimensional space | 4% | Is screen geography preserved? |
The rank is the point: never sacrifice emotion to protect continuity. Emotion outweighs the bottom three combined by five to one. A technically perfect cut that kills the feeling is a bad cut; an "incorrect" cut that lands emotionally is a good one. Murch's summary — don't give up emotion before story, story before rhythm, rhythm before eye-trace, eye-trace before planarity, planarity before spatial continuity.
2. When to cut
- Cut on motion. A cut placed mid-gesture hides itself, because the viewer is tracking the movement, not the join. This is the single most useful habit in the list.
- Cut when the thought completes. Murch's "blink" principle: people blink at the end of a thought. Cut where the viewer would blink, not where the shot runs out.
- Cut for a reason. If you cannot say what the next shot gives that this one cannot, do not cut. Boredom is not fixed by more cuts; it is fixed by shots that earn their place.
- Do not cut on a static frame unless the stillness is the point. Cutting from stillness to stillness is where "slideshow" comes from.
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.
- 2d ago First seen · 160 lines · 36 tokens per session scan A b759bf055ca0
cleya-edit-craft is a skill published in the GitHub repository severment/cleya (0 stars, last pushed 29d ago), licensed Apache-2.0. It adds 36 tokens to every session and 2,530 once invoked, about $0.0002 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
talking-head-recut
Package an existing talking-head / interview / podcast video with timed, designed GRAPHIC OVERLAY cards — kinetic titles, lower-thirds, data callouts, quotes, side panels, picture-in-picture — synced to the transcript, on a 16:9 / 9:16 / 4:5 canvas of your choice; the clip plays untouched underneath. Trigger on…
embedded-captions
Add captions or subtitles to an existing single-subject talking-head video without editing the footage. Use for plain verbatim captions, cinematic captions embedded behind the subject, VFX captions, “炸/特效/酷炫字幕,” or a named identity from the 35-style catalog. Route by visual identity, not by backend engine. The quiet…
faceless-explainer
Turn arbitrary text — an article, notes, a topic, a brief — into a faceless explainer video: there is no site or footage to capture, so the visuals are invented per scene (typography, abstract graphics, diagrams, data-viz). Use for topic explainers, concept breakdowns, how-tos, listicles. Not a video built from a…
pr-to-video
Turn a GitHub pull request (a PR URL, owner/repo#N, or 'this PR' in a checked-out repo) into a code-change explainer video — changelog, feature reveal, fix, or refactor walkthrough built from the diff, commits, and files: the input is a code change, not a website. Not a product promo (/product-launch-video) or a no-PR…
slideshow
Author a HyperFrames slideshow — a presentation, pitch deck, or interactive deck with discrete slides, fragment reveals, branching, hotspot navigation, and built-in presenter mode with speaker notes; also converts an existing page into a deck. Output is a navigable deck, not a rendered MP4. If the user didn't…
hyperframes-audio
Use when audio already placed in a HyperFrames composition needs to be mixed: fade-in/fade-out, crossfade, track gain or volume, volume automation, ducking, a music bed that fights a voiceover (voiceover carve), effects on a track (EQ, compressor, limiter, gate, saturation, delay, reverb, chorus, phaser, bitcrush)…