Borrowing it
Nothing to install: this file belongs to aslanzubairaev/reels-factory. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/aslanzubairaev/reels-factory/master/.claude/commands/finish.mdgit clone --depth 1 https://github.com/aslanzubairaev/reels-factoryWrote 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/aslanzubairaev/reels-factory/finish)<a href="https://agentmods.dev/commands/aslanzubairaev/reels-factory/finish"><img src="https://agentmods.dev/badge/commands/aslanzubairaev/reels-factory/finish/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/commands/aslanzubairaev/reels-factory/finish"><img src="https://agentmods.dev/badge/commands/aslanzubairaev/reels-factory/finish.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 | $0.00000 | $0.01259 |
| Opus 5 | $0.00000 | $0.00629 |
| Sonnet 5 | $0.00000 | $0.00252 |
| Haiku 4.5 | $0.00000 | $0.00126 |
Grade A, and why
finish 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 11d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/finish — Быстрый пост-продакшн
После записи в Studio /finish собирает финальный пакет для Instagram за ~2 минуты (без субтитров) или за ~8 минут с флагом --with-subs.
Вход
- Аргумент 1 (опционально): имя проекта. Если не задан — последний проект с файлами записи.
- Флаг
--with-subs— включает субтитры (Transcribe + Subtitle). По умолчанию выключено.
Шаги (4, плюс 2 опциональных)
0. Подготовка видео (ВСЕГДА)
0a. Если есть recording_full.webm и нет recording_full.mp4:
ffmpeg -y -i recording_full.webm -c:v libx264 -preset medium -crf 20 -pix_fmt yuv420p -vsync cfr -r 30 -c:a aac -b:a 192k -ar 48000 -af aresample=async=1:first_pts=0 -movflags +faststart recording_full.mp4
(CFR + async-resample — иначе видео отстаёт от аудио.)
0b. Если в output/ есть несколько recording_NNN.mp4 и нет recording_full.mp4 — обязательно запустить skill:
python .claude/skills/concat-segments/concat.py projects/{name}/output/
Самостоятельно ffmpeg -filter_complex "fps=30,setpts=..." не использовать — ломает синхрон. Skill сам выбирает stream-copy или re-encode с CFR.
0c. После успеха — не удалять сегменты вручную, их уберёт cleanup на шаге 4.
[опционально при --with-subs] 1a. Transcribe
python .claude/skills/transcribe/transcribe.py projects/{name}/output/recording_full.mp4
Сверяет transcript_raw.txt со скриптом (02_script.json), исправляет ослышки → transcript.txt + transcript_corrections.md.
[опционально при --with-subs] 1b. Subtitle
python .claude/skills/subtitle/analyze_frame.py projects/{name}/output/recording_full.mp4
Читает subtitle_placement.json:
- Если зона чистая →
generate_subs.py+render_video.py→final_video_subs.mp4 - Если грязно → пропускает вшивание (не портит визуал)
2. Copywriter
Запустить агента из .claude/agents/copywriter-agent.md. Source — 02_script.json (не transcript, не analysis.json).
Выход в projects/{name}/output/:
cover_text.json—{line1, line2}(цепляющий хук)caption.txt— пост с hook + польза + CTA + 15-20 хэштеговshort_caption.txt— до 150 символовfirst_comment.txt— провокация обсужденияhashtags.txt— теги через пробел
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.
- 11d ago First seen · 101 lines · 0 tokens per session scan A 3c736237b245
finish is a command published in the GitHub repository aslanzubairaev/reels-factory (2 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,259 tokens. 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
review-video
Make a " Reviews" video — a fast, faceless VO montage of REAL, verified competitor reviews that names the recurring complaints and positions YOUR business as the alternative, then hands off to your own customer testimonials.
avatar-vo-reel
Build a fullscreen voiceover-over-b-roll reel — talking-head avatar hook, then fullscreen screen-capture b-roll while the VO continues, lower-third captions, badge swap, SFX.
genimage
Generate, edit, or create any image — photos, illustrations, website visuals, placeholders, icons, thumbnails, banners, or any graphic asset.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.