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.
git clone --depth 1 https://github.com/Belagum/promptcutWrote 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/belagum/promptcut/video)<a href="https://agentmods.dev/commands/belagum/promptcut/video"><img src="https://agentmods.dev/badge/commands/belagum/promptcut/video/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/belagum/promptcut/video"><img src="https://agentmods.dev/badge/commands/belagum/promptcut/video.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 | $0.00023 | $0.00250 |
| Opus 5.5 | $0.00009 | $0.00100 |
| Sonnet 5.5 | $0.00005 | $0.00050 |
| Haiku 4.5 | $0.00002 | $0.00025 |
Grade A, and why
video 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 1mo 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
Use the video-toolbox skill. The person wants a finished video from: $ARGUMENTS
Steps, in order:
- If the request is thin, ask at most two questions that actually change the output: language and voice of the narration, aspect (16:9 or 9:16), and whether images should be generated or pulled from stock. Then stop asking and work.
- If they pasted a script, keep their wording. If they gave a topic, write the narration yourself, then show it as plain text for approval before spending anything.
- Write
plan.jsonnext to their working directory, runplan-check, thenbuild --fakeand report duration and shot count. - On approval run the real
build. Report the mp4 path, duration andspend_usd. - Offer
capcut-from-planornle-from-plan --target premiere|resolve|vegasif they may want to hand-tweak in their editor.
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.
- 1mo ago First seen · 22 lines · 23 tokens per session scan A 2af82993b2b3
video is a command published in the GitHub repository Belagum/promptcut (1 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 250 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
create-topic
Research and generate a complete topic plan with keyword mapping, audience, angle, and competitive positioning.
brand-setup
Create or update a brand profile: colors, fonts, logo, voice, platforms. "set up a new client brand".
negative-keyword-sweep
Find wasted spend in Google Ads search terms and add negatives at the right scope (account list, campaign, or ad group). Use when the user says "find junk keywords", "stop wasting on bad searches", or wants a search-terms cleanup.
launch-meta-campaign
Launch a complete Meta Ads campaign — campaign, ad set, and ad(s) — built paused and ready to review. Use when the user wants a new Facebook/Instagram campaign.
new-month
Start a new month for a brand: folder and settings; a calendar to load -> parse-calendar; ideas -> ideate-month. "start a new month for this brand".
change-plan
Create a comprehensive change management plan for a transformation initiative.