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 skills add erduo1998-cell/erduo-broll-loop-engineering --skill broll-onboardinggit clone --depth 1 https://github.com/erduo1998-cell/erduo-broll-loop-engineeringWrote 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/skills/erduo1998-cell/erduo-broll-loop-engineering/broll-onboarding)<a href="https://agentmods.dev/skills/erduo1998-cell/erduo-broll-loop-engineering/broll-onboarding"><img src="https://agentmods.dev/badge/skills/erduo1998-cell/erduo-broll-loop-engineering/broll-onboarding/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/skills/erduo1998-cell/erduo-broll-loop-engineering/broll-onboarding"><img src="https://agentmods.dev/badge/skills/erduo1998-cell/erduo-broll-loop-engineering/broll-onboarding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00028 | $0.00959 |
| Opus 5 | $0.00014 | $0.00479 |
| Sonnet 5 | $0.00006 | $0.00192 |
| Haiku 4.5 | $0.00003 | $0.00096 |
Grade A, and why
broll-onboarding 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 9d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
B-roll onboarding
Act only as the environment diagnostic and authorized repair coordinator. This is an exception path, not a stage in every production. Do not direct, collect media, write animation source, integrate, render, export, or judge aesthetics.
Dispatch gate
Accept only a compact JSON result from scripts/production-preflight.mjs with
next: run-onboarding-diagnostic. If next is continue, do not run. If it is
fix-production-input, return the input/output issue to Parent without doing
environment inspection. fix-project-runtime also stays out of Onboarding and
belongs to the bounded project-local Remotion bootstrap/repair path.
Valid diagnostic causes are limited to:
- no readiness cache after installation or migration;
- cached release, machine, architecture, Node major, installed Skill set, pinned HyperFrames version, or pinned official-Skills commit changed;
- a requested backend is not recorded ready;
- a production command actually failed and points to a machine/tool problem.
A new production run, SRT, project/output path, runtime-plan identity, command
PATH, free-space value, or Pexels status is not a deep-cache invalidator.
Inputs
- release and Skill roots;
- preflight JSON and failed fact IDs;
- mode:
inspectorrepair; - exact required backend set, if already planned;
- in repair mode only, explicit authorization and the approved repair list;
- previous readiness cache, when present.
Read ../../references/first-run-onboarding.md. Read runtime selection and
capability references only when a failed backend fact requires them. Do not
read film, craft, material, review, or rendering references.
Inspect once
Inspection is read-only. Check only the failed or stale installation facts and their direct prerequisites. Do not rescan production paths, parse the SRT, estimate its delivery size, inspect Pexels, or run both backends when only one failed.
Common installation facts are Node 22.20+, executable FFmpeg/FFprobe, release
Skill discovery, release identity, and host/architecture. For HyperFrames,
load the pinned official hyperframes and hyperframes-cli Skills, then run
the release doctor and inspect its JSON. For Remotion, use only exact
project-local remotion and @remotion/cli dependencies and direct local CLI
evidence; never use global CLI or an npx download as proof.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 106 lines · 28 tokens per session scan A d0fcdac40182
broll-onboarding is a skill published in the GitHub repository erduo1998-cell/erduo-broll-loop-engineering (170 stars, last pushed 2d ago), licensed MIT. It adds 28 tokens to every session and 959 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 2026-08-30.
Other skills, from other repositories
video-hyperframes
Hyperframes / Remotion-compatible continuous frame animation with autoplay support.
paperclip-capsules
Generate, implement, or review Paperclip capsule visuals. Use for capsule art, agent capsules, heartbeat status capsules, identicons, capsule banks, or brand-usage validation.
video-hyperframes
A web-based sequence of video frames designed for Hyperframes or Remotion, with each frame presenting one visual idea.
srt-whiteboard-animation
A workflow that turns SRT subtitle files into whiteboard-style hand-drawn animation videos. It plans scenes from the subtitles, draws them in flowing strokes, and renders an MP4.
create-video
Tạo một video MỚI cho series "so sánh / phân biệt kiến thức" của repo này — clip dọc TikTok/Reels/Shorts 30-40s, layout 3-zone cố định theo DESIGN.md, voiceover tiếng Việt sinh bằng Edge TTS (mặc định, miễn phí) hoặc Vbee TTS, dựng bằng HyperFrames. Dùng skill này khi người dùng nói "làm video so sánh X vs Y", "phân…
hbg-life-simulation
A workflow for producing Chinese narrative videos in a recurring comic style, from source story and characters to a verified MP4 video.