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 alivirgo/Major-AI-Skills --skill losslesscutgit clone --depth 1 https://github.com/alivirgo/Major-AI-SkillsWrote 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/alivirgo/major-ai-skills/losslesscut)<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/losslesscut"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/losslesscut/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/alivirgo/major-ai-skills/losslesscut"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/losslesscut.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 | $0.00038 | $0.02038 |
| Opus 5.5 | $0.00015 | $0.00815 |
| Sonnet 5.5 | $0.00008 | $0.00408 |
| Haiku 4.5 | $0.00004 | $0.00204 |
Grade A, and why
losslesscut scanned grade A with 1 finding 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 6d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
proc = subprocess.run(cmd, capture_output=True, text=True) How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LosslessCut Stream Editor AI Skill Guide (Claude)
Overview & Engine Architecture
LosslessCut (mifi/lossless-cut) is an Electron UI over FFmpeg stream copy (-c copy). Lossless cuts must start on decoder keyframes (IDR/I). Keyframe cut snaps start to a nearby keyframe (often earlier). Experimental Smart Cut re-encodes only from the desired start to the next keyframe, then copies the rest — unsupported for many files/codecs/multi-video-track cases.
Projects use .llc JSON5, schema version 2: mediaFileName, cutSegments[{ start, end?, name, tags?, selected? }].
┌─────────────────────────────────────────────────────────────┐
│ LosslessCut cut → export │
│ │
│ Analysis │
│ ├── ffprobe packets/flags → keyframes ('K') │
│ └── GOP spacing drives how “early” cuts start │
│ │
│ Cut modes │
│ ├── Keyframe cut (default, -ss before -i style) │
│ ├── Exact/frame modes with caveats │
│ └── Smart Cut (experimental hybrid re-encode bridge) │
│ │
│ Interchange │
│ ├── .llc v2 segments / CSV / YouTube chapters │
│ └── ffmpeg concat demuxer for merge │
└─────────────────────────────────────────────────────────────┘
When to use / when not to
Use when
- Rough selects, removing intros/outros, splitting recordings, preserving codecs.
- Generating
.llcmanifests or keyframe-aligned FFmpeg-c copyslices. - Extracting/keeping secondary audio or subtitle tracks during remux.
Do not use when
- Frame-accurate creative edit with effects → NLE skills (
@adobe-premiere-pro,@final-cut-pro, …). - Guaranteed frame-exact cut on arbitrary codecs without re-encode → full re-encode via
@ffmpeg(or Smart Cut only if it works for that file). - DRM / encrypted media circumvention → refuse.
What ships with it
2 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.
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.
- 6d ago Changed · +39 lines · +10 tokens per session b30c50d135dd
- 1mo ago Changed · -14 tokens per session 392e748cf37e
- 2mo ago First seen · 160 lines · 42 tokens per session scan A 009f4739650d
losslesscut is a skill published in the GitHub repository alivirgo/Major-AI-Skills (2 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 2,038 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
flutter-developer
Build beautiful, performant Flutter applications for iOS, Android, and web. Covers state management, navigation, animations, platform channels, and deployment.
accessibility-mobile
Professional Accessibility Mobile Expert skill. Build performance-tuned, secure, and intuitive mobile applications for iOS and Android.
app-store-optimizer
Professional App Store Optimizer Expert skill. Build performance-tuned, secure, and intuitive mobile applications for iOS and Android.
biometric-auth
Professional Biometric Auth Expert skill. Build performance-tuned, secure, and intuitive mobile applications for iOS and Android.
camera-integration
Professional Camera Integration Expert skill. Build performance-tuned, secure, and intuitive mobile applications for iOS and Android.
deep-link-specialist
Professional Deep Link Specialist Expert skill. Build performance-tuned, secure, and intuitive mobile applications for iOS and Android.