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 Mark-Life/agent-skills --skill clean-cutgit clone --depth 1 https://github.com/Mark-Life/agent-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/mark-life/agent-skills/clean-cut)<a href="https://agentmods.dev/skills/mark-life/agent-skills/clean-cut"><img src="https://agentmods.dev/badge/skills/mark-life/agent-skills/clean-cut/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/mark-life/agent-skills/clean-cut"><img src="https://agentmods.dev/badge/skills/mark-life/agent-skills/clean-cut.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 | $0.00100 | $0.02222 |
| Opus 5.5 | $0.00040 | $0.00889 |
| Sonnet 5.5 | $0.00020 | $0.00444 |
| Haiku 4.5 | $0.00010 | $0.00222 |
Grade A, and why
clean-cut 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 27d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clean Cut
A clean cut keeps every spoken word and removes only the non-content between words: hesitation sounds, audio events, and dead air. The viewer should not notice an edit happened, only that the video is shorter and tighter.
This skill is a style layer on top of video-use (~/.agents/skills/video-use/SKILL.md, source: browser-use/video-use). Read its SKILL.md first: its Hard Rules apply here unchanged. video-use provides transcription and visual checks. This skill decides what to cut and ships its own cut builder and renderer.
Defaults
| Setting | Value |
|---|---|
| Content | every word kept, no sections removed, no reordering |
| Cut | fillers, audio events, silences ≥ 0.4s |
| Pause left after a cut | ~0.27s source (≈0.25s at 1.1x) |
| Pause when the screen changes during silence | ~0.8s, so the viewer sees the change |
Word parasites (like, you know, как бы, вот) |
kept: removing them risks changing meaning. Offer as an option in the report |
| Speed | 1.1x, pitch preserved (atempo) |
| Frame rate | 30 fps |
| Loudness | two-pass loudnorm to -14 LUFS (screen recordings are often ~-29 LUFS) |
| Grade, subtitles, overlays | none |
| Iteration | 1080p30 preview first → user approves → 4K30 final with the same EDL |
| Source file | never modified; all output in <videos_dir>/edit/ |
The user already stated this strategy by invoking the skill. Confirm only the unknowns: content type (screen recording or talking head) and language if unclear. Then execute without a separate strategy round.
Setup
VU= the video-use repo root:$(dirname "$(readlink -f ~/.agents/skills/video-use/SKILL.md)").H=$VU/helpers.PY= video-use's Python with its deps ($VU/.venv/bin/pythonafteruv sync). This skill's own scripts are stdlib-only and run with anypython3.CC= this skill's folder.E=<videos_dir>/edit.SRC= the source video.- ElevenLabs key:
ELEVENLABS_API_KEYin the environment or$VU/.env. The key needs the Speech to Text permission. A 401 withmissing_permissionsmeans the key exists but that toggle is off: the user enables it in ElevenLabs → Developers → API Keys.
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.
- 27d ago First seen · 120 lines · 100 tokens per session scan A 279c456b9b6a
clean-cut is a skill published in the GitHub repository Mark-Life/agent-skills (3 stars, last pushed 2d ago), licensed MIT. It adds 100 tokens to every session and 2,222 once invoked, about $0.0004 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 2026-09-25.
Other skills, from other repositories
ralplan
Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution.
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
remember
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.
moai-lane-watchdog
One lane stall watchdog iteration: measure lane progress on three channels, classify the stall cause, apply the remedy or resolve the judgment through the decision ladder — instead of waiting on a reply — then record the outcome and report. Reads the unified --auto doctrine at…
moai-ref-ui-polish
UI polish and interface-completion reference: the small visual details — concentric border radius, optical alignment, shadow-vs-border, motion easing, typography smoothing, tabular numbers, icon stroke weight, hit areas — that separate polished interfaces from generic ones. Agent-extending skill that amplifies…
blueprint-cloudflare-scaffold
Lay out a Worker with D1 and static Vue assets, with tests that run inside the Workers runtime.