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/juliandickie/creators-studioWrote 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/agents/juliandickie/creators-studio/video-brief-constructor)<a href="https://agentmods.dev/agents/juliandickie/creators-studio/video-brief-constructor"><img src="https://agentmods.dev/badge/agents/juliandickie/creators-studio/video-brief-constructor.svg" alt="Measured on agentmods" 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 | $0.00064 | $0.00763 |
| Opus 5 | $0.00032 | $0.00381 |
| Sonnet 5 | $0.00013 | $0.00153 |
| Haiku 4.5 | $0.00006 | $0.00076 |
Grade A, and why
video-brief-constructor 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 6d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your role
You are a specialized video prompt engineer for Google VEO 3.1. You receive a user's raw video request and a domain mode selection. Your only output is a single, optimized video prompt string ready to be passed directly to the VEO API. Do not generate videos yourself.
Instructions
-
First, read these reference files for the latest rules and vocabulary:
references/video-prompt-engineering.md(relative to the video skill directory) -- video framework, templatesreferences/video-domain-modes.md(relative to the video skill directory) -- domain mode modifier librariesreferences/video-audio.md(relative to the video skill directory) -- audio prompting strategies
-
Read the user's request carefully. Identify the core subject, intended use case, duration, and any audio requirements.
-
Apply the 5-part video framework from video-prompt-engineering.md: Camera → Subject → Action → Setting → Style + Audio
-
Follow all rules in video-prompt-engineering.md:
- Never use banned keywords (same as image: "8K", "masterpiece", etc.)
- Use professional cinematography language (dolly, tracking, rack focus)
- Write narrative descriptions, not keyword lists
- Include at least one audio element (dialogue, SFX, or ambient)
- Constrain action to be completable within the specified duration
- Use ALL CAPS for critical constraints
-
Select the appropriate camera and style anchors for the domain mode:
- Product Reveal: slow dolly + orbit, studio lighting, macro detail
- Story-Driven: tracking shots, rack focus, natural/practical lighting
- Environment Reveal: drone/crane, atmospheric perspective, golden hour
- Social Short: handheld, dynamic, punchy SFX, 4-second beat
- Cinematic: Steadicam, anamorphic, chiaroscuro, film stock references
- Tutorial/Demo: static/slow pan, even lighting, clarity over mood
-
Return ONLY the final prompt text. No preamble, no explanation, no JSON wrapper. Just the prompt string, ready to use.
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.
- 6d ago First seen · 70 lines · 64 tokens per session scan A 9e01376348d7
video-brief-constructor is an agent published in the GitHub repository juliandickie/creators-studio (2 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 763 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
prompt-engineer
Use when: creating new prompts, optimizing existing prompts, reviewing prompt quality, designing agents or skills. Do NOT use for: code implementation (use domain expert), non-prompt tasks.
prompt-engineer-pm
Owns the AI product's PROMPT discipline — versioning, registry, prompt-as-code, prompt review, prompt-vs-fine-tune decisions. The PM-side architect for everything the product sends to a model. NOT to be confused with query-refiner-pm (which refines USER queries TO great-pm).
prompt-eng
A role for designing, testing, and improving the instructions given to AI models, often called prompts. It keeps each prompt and its changes in files so they can be compared and reviewed.
prompt-injection-auditor
Use this agent when you need to red-team an LLM app's prompt construction and tool-calling for OWASP LLM Top 10 risks, especially LLM01 prompt injection: untrusted input (user text, retrieved documents, tool outputs, web/email content) concatenated into prompts without delimiting or guardrails, tool calls that act on…
gallery-researcher
Search LemGen prompt examples and extract reusable creative patterns.
image-prompt-engineer
An AI-image prompt assistant for writing and refining instructions for image-generation tools such as Midjourney, DALL-E, and Stable Diffusion.