Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add ahmedawan-oracle/fde_demo_builder/plugin install fde-demo-builderWrote 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/ahmedawan-oracle/fde_demo_builder/new-broll)<a href="https://agentmods.dev/commands/ahmedawan-oracle/fde_demo_builder/new-broll"><img src="https://agentmods.dev/badge/commands/ahmedawan-oracle/fde_demo_builder/new-broll/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/ahmedawan-oracle/fde_demo_builder/new-broll"><img src="https://agentmods.dev/badge/commands/ahmedawan-oracle/fde_demo_builder/new-broll.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 | $0.00029 | $0.00618 |
| Opus 5 | $0.00015 | $0.00309 |
| Sonnet 5 | $0.00006 | $0.00124 |
| Haiku 4.5 | $0.00003 | $0.00062 |
Grade A, and why
new-broll 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 4d 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
Scaffold a new story-rebuild demo project named $1 using the FDE Demo Builder v2 templates.
Do the following:
- Create
$1/in the current working directory (error out politely if it already exists). - Copy from
${CLAUDE_PLUGIN_ROOT}/skills/demo-video-builder/scripts/into$1/:vo_script.example.py→$1/vo_script.pygen_vo_multivoice.py→$1/gen_vo_multivoice.pyrender_scene.js→$1/render_scene.jsshot.js→$1/shot.jsassemble.example.sh→$1/assemble.shrequirements.txt→$1/requirements.txt- create
$1/scenes/and copyscenes/broll_opener.example.html→$1/scenes/opener.html
- Create empty
$1/vo/,$1/out/,$1/qa/,$1/assets/folders. - Print concise next steps:
- Drop the source demo in as
$1/recording.mp4. - Review first: extract frames (
ffmpeg -i recording.mp4 -vf "fps=1/12,scale=800:-1" qa/f_%02d.jpg) and transcribe (faster-whisper) to map slides-vs-recording stretches and cut boundaries. - Edit
$1/vo_script.py: cast the voices, write the SCENES (animated acts) and PLACED beats (re-voiced recording), thenpython gen_vo_multivoice.py. - Rewrite
$1/scenes/opener.htmlfor the story (it's a working template — keep the boot and loop blocks verbatim, replace the layers). QA withnode shot.js scenes/opener.html 12 qa/op12.png, render withnode render_scene.js scenes/opener.html vo_opener.mp3 out/seg1_opener.mp4. - Cut + mux the recording segments and run
bash assemble.sh(recipes are in the file). - Finish with the
demo-qa-revieweragent on the final MP4. - Method details:
${CLAUDE_PLUGIN_ROOT}/skills/demo-video-builder/references/broll-scenes.mdandreferences/multi-voice.md.
- Drop the source demo in as
Also remind them of the hard rules: no customer names or internal identifiers anywhere (scenes, VO text, examples — use fictional brands and synthetic numbers), and scrub every privacy leak in recorded frames before sharing.
Use forward-slash paths and platform-appropriate copy commands. Do not overwrite an existing $1/.
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.
- 4d ago First seen · 39 lines · 29 tokens per session scan A b72d2642238b
new-broll is a command published in the GitHub repository ahmedawan-oracle/fde_demo_builder (4 stars, last pushed 5d ago), licensed MIT. It adds 29 tokens to every session and 618 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 2026-09-05.
Other commands, from other repositories
brand-generate
Generate an on-brand document from a saved Brand Profile.
list
List available Piper TTS TTS voices with optional filtering.
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.
transcribe
Transcribe the file at $ARGUMENTS into Markdown using the Frenchie MCP server.
varyshop-carousel
Create a Varyshop multi-slide carousel (LIGHT style, hook → CTA).
imperium:create-video
Create startup video content. Supports pitch videos, product demos, social clips, investor updates, and hiring videos. Bridges to Remotion for rendering.