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 commands/ivanlutsenko/awac-ai-agent-plugins/clip-makergit clone --depth 1 https://github.com/IvanLutsenko/awac-ai-agent-pluginsWrote 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/commands/ivanlutsenko/awac-ai-agent-plugins/clip-maker)<a href="https://agentmods.dev/commands/ivanlutsenko/awac-ai-agent-plugins/clip-maker"><img src="https://agentmods.dev/badge/commands/ivanlutsenko/awac-ai-agent-plugins/clip-maker.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 | $0.00023 | $0.01251 |
| Opus 5 | $0.00012 | $0.00626 |
| Sonnet 5 | $0.00005 | $0.00250 |
| Haiku 4.5 | $0.00002 | $0.00125 |
Grade A, and why
clip-maker 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 3d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clip Maker — Full Pipeline
Create vertical (9:16) clips from a horizontal video, optimized for Reels/Shorts/TikTok.
Arguments
Parse $ARGUMENTS for:
<video_path_or_url>— required, path to source video OR YouTube/web URL--duration N— target clip duration in seconds (default: 60)--auto— skip manual moment selection, use all found moments--no-subtitles— don't burn subtitles into clips--api— use OpenAI Whisper API instead of local whisper--no-copy— skip social media copy generation--language LANG— transcription language (default: ru)--prompt "terms"— domain-specific terms for whisper (improves recognition of jargon, names, abbreviations)
Pipeline
Execute steps sequentially. Report progress to the user after each step.
Step 1: Check dependencies
bash ${CLAUDE_PLUGIN_ROOT}/scripts/install-deps.sh [--api if user passed --api]
If it fails, stop and report what's missing.
Step 2: Download if URL
If <video_path> looks like a URL (starts with http://, https://, or youtube.com, youtu.be):
VIDEO_PATH=$(bash ${CLAUDE_PLUGIN_ROOT}/scripts/download-video.sh "<url>" ~/Downloads)
The script outputs the downloaded file path. Use it as <video_path> for subsequent steps.
Step 3: Setup output directory
Create output directory next to the video: {video_dir}/{video_name}_clips/
Step 4: Transcribe
bash ${CLAUDE_PLUGIN_ROOT}/scripts/transcribe.sh "<video_path>" "<output_dir>" [--api] [--language LANG] [--prompt "terms"]
This produces <output_dir>/transcript.json.
Step 5: Find interesting moments
Launch the moment-finder agent:
Agent(subagent_type="clip-maker:moment-finder", model="opus", prompt="
Analyze the transcript and find the most engaging moments for vertical clips.
- Transcript path: <output_dir>/transcript.json
- Target clip duration: <duration> seconds
- Output path: <output_dir>/moments.json
Read the transcript, find the best moments, and write moments.json.
")
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.
- 3d ago First seen · 165 lines · 23 tokens per session scan A e22f854438be
clip-maker is a command published in the GitHub repository IvanLutsenko/awac-ai-agent-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 1,251 once invoked, about $0.0001 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 commands, from other repositories
brand-generate
Generate an on-brand document from a saved Brand Profile.
stt
Transcribe a local audio file or remote audio URL into text.
audition-voices
Generate voice audition samples for a character using Venice TTS.
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.
tag
Add or remove free-form tags on photos, then find them with search --tag.
develop-image-prompt.eval
Generates a detailed image generation prompt from a document or content description. Good output: a prompt that is specific, visual, non-abstract, includes style/composition/lighting guidance, and is calibrated to the specified dimensions and style options.