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-directorgit 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-director)<a href="https://agentmods.dev/skills/erduo1998-cell/erduo-broll-loop-engineering/broll-director"><img src="https://agentmods.dev/badge/skills/erduo1998-cell/erduo-broll-loop-engineering/broll-director/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-director"><img src="https://agentmods.dev/badge/skills/erduo1998-cell/erduo-broll-loop-engineering/broll-director.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 | $0.00043 | $0.01773 |
| Opus 5 | $0.00022 | $0.00886 |
| Sonnet 5 | $0.00009 | $0.00355 |
| Haiku 4.5 | $0.00004 | $0.00177 |
Grade A, and why
broll-director 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
B-roll Director
Own meaning, semantic shot boundaries, chapter suggestions, and whole-film direction. Do not collect media, choose runtime APIs, author source, render, or review the finished film.
Read the complete original SRT and original design before dividing the film. Neither may be replaced by a Director summary. Also read the task constraints, optional user-media index, and at most two selected references. Do not reopen the Parent Skill, other stage Skills, generic craft references, schemas, validators, or catalogs. The injected Director charter and this exact contract are complete.
Direct truth and creative freedom
Use SRT integer milliseconds as time truth. Cover zero through the final cue
end, including gaps. Divide by complete meaning, then recommend contiguous
semantic chapters. A normal shot is about 5–12 seconds; a shot over 15 seconds
needs a content-driven durationRationale. Never write authoring.solo or make
the unit decision. Mark only the two closed technical risks when they are true;
the Parent Planner owns grouping.
Write every Recipe in two layers:
truthis immutable downstream: source cues, spoken facts, audience outcome, readable result, exact time, chapter, and incoming/outgoing seam.creativeProposalis a strong proposal, not a locked implementation. The Chapter Builder may revise metaphor, objects, composition, motion, material route, and key states when a better answer preservestruth.
For abstract claims, decide whether a person, recognizable object, real
interface, generated metaphor, or mixed material makes the truth clearer. Do
not default everything to native structure. Select exactly one proposed route:
native, provided, search, generate, or mixed. Select two to four
genuinely relevant craftIntent values; they guide invention and are never a
score, checklist, or backend-routing signal.
Use motion-map.json only to expose adjacent repetition in content relation,
composition, entry, rhythm, and primary action. It must not become a shot
template. Three representative scenes must cover opening, information-dense,
and late positions and three visibly different content relationships.
What ships with it
4 files 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 · 98 lines · 43 tokens per session scan A 2c224aba0e52
broll-director is a skill published in the GitHub repository erduo1998-cell/erduo-broll-loop-engineering (170 stars, last pushed 2d ago), licensed MIT. It adds 43 tokens to every session and 1,773 once invoked, about $0.0002 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…
p5-paint-animation
Turn a text prompt, a photo, or a live video clip into hand-made-looking p5.js animation — pencil handwriting that writes itself, photos repainted as brushstroke art with paint-on animation and camera moves, and short videos (iPhone Live Photos included) repainted frame-by-frame as a living painting. Trigger on…