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 instructions/lucyfengcl-art/video-prep/agents-mdgit clone --depth 1 https://github.com/lucyfengcl-art/video-prepWrote 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/instructions/lucyfengcl-art/video-prep/agents-md)<a href="https://agentmods.dev/instructions/lucyfengcl-art/video-prep/agents-md"><img src="https://agentmods.dev/badge/instructions/lucyfengcl-art/video-prep/agents-md.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 5.1 | $0.00304 | $0.00304 |
| Opus 5 | $0.00152 | $0.00152 |
| Sonnet 5 | $0.00061 | $0.00061 |
| Haiku 4.5 | $0.00030 | $0.00030 |
Grade A, and why
video-prep AGENTS.md 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 5d 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.
What it actually says
video-prep
This repo provides the video-prep skill and the video-prep-edit CLI
for prepping raw video clips before the real edit: cut silent gaps, transcribe
subtitles (any language, Mandarin by default), normalize speed, and stitch clips
in natural numeric order — outputting clean per-clip .mp4 + .srt plus an
optional merged, subtitle-burned preview. Pre-processing, not the creative edit.
When the user asks to "clean up / prep / edit my clips" (usually in ./raw/),
process the whole folder in one run — never merge clips pairwise yourself:
video-prep-edit ./raw # Mandarin (default); add --language en / auto
video-prep-edit ./raw -j 3 # parallelize many clips on a multi-core CPU
Full, authoritative guidance lives in the skill — read it before running:
- Skill (source of truth):
skills/video-prep/SKILL.md - CLI install:
uv tool install git+https://github.com/lucyfengcl-art/video-prep - Human docs:
README.md·BLOCKS.md(lower-level building blocks)
Requires ffmpeg (and ffmpeg-full to burn subtitles) on the machine.
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.
- 5d ago First seen · 24 lines · 304 tokens per session scan A 9337d8b24fa0
video-prep AGENTS.md is an instructions file published in the GitHub repository lucyfengcl-art/video-prep (1 stars, last pushed 1mo ago), licensed MIT. It adds 304 tokens to every session, about $0.0015 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 instructions, from other repositories
video-captions AGENTS.md
Instructions for katareayush/video-captions, covering repo guide, layout and working on this repo.
video-captions GEMINI.md
Instructions for katareayush/video-captions: Two skills ship with this extension. Load a skill's SKILL.md only when its trigger fires — they are written to be read on demand, not up front.
claude-code-youtube-extract CLAUDE.md
Claude Code instructions for muckybuzzwoo/claude-code-youtube-extract, covering claude.md — yt-extract plugin, what this plugin is, components, architectural conventions and script cli (internal, skill-facing).
living-manual CLAUDE.md
Instructions for dougstanford/living-manual, covering living-manual, start of every session, how work lands — non-negotiable, user's manual (living-manual) and releasing.
ship-it open-pr.instructions.md
Instructions for khrichtchatyi/ship-it: When the user asks to open, create, or submit a pull request, follow the skill in skills/open-pr/SKILL.md in full: verify gh is authenticated, resolve the target repository and default branch, push the current branch, open one pull request with a title and body derived from the…
agent-skills CLAUDE.md
Instructions for mindbox-cloud/agent-skills, covering agent-skills — developer guide for claude code, repository purpose, repository structure, how to add a new plugin and step 1 — create the directory structure.