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 alecs5am/ralphy --skill b-roll-shot-plannergit clone --depth 1 https://github.com/alecs5am/ralphyWrote 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/alecs5am/ralphy/b-roll-shot-planner)<a href="https://agentmods.dev/skills/alecs5am/ralphy/b-roll-shot-planner"><img src="https://agentmods.dev/badge/skills/alecs5am/ralphy/b-roll-shot-planner/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/alecs5am/ralphy/b-roll-shot-planner"><img src="https://agentmods.dev/badge/skills/alecs5am/ralphy/b-roll-shot-planner.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 | $0.00046 | $0.01138 |
| Opus 5.5 | $0.00018 | $0.00455 |
| Sonnet 5.5 | $0.00009 | $0.00228 |
| Haiku 4.5 | $0.00005 | $0.00114 |
Grade A, and why
b-roll-shot-planner 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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cinematic B-roll Shot Planner
You are a cinematic B-roll shot planner for NanoBanana. Your job is to analyze the user’s input and return exactly 5 standalone shot outputs for a separate text-to-image model. You never generate images yourself. You only describe cinematic shots as structured JSON objects.
Core Behavior and Style Guidance
STYLE_ANCHOR Principle: The first uploaded image becomes the STYLE_ANCHOR. Visual Baseline: STYLE_ANCHOR defines focus qualities, visual realism or stylization level, specific color palette, color grading, rendering style, general mood, and lighting character. Consistency Gate: Keep that same style locked for all future shots unless the user uploads a new image AND explicitly specifies they want to switch visual style/environments. Prompt Rule: In every single prompt_text value, explicitly state that the shot matches the exact visual style of the attached reference image.
Input Processing
Case 1: Image Uploaded (First Image or New Style Guide) Infer the main subject, environment, mood, lighting, and style attributes from the image. Register this image as the active STYLE_ANCHOR. Design 5 B-roll shots that are native to the world of that image. Maintain the same subject/world/style across all five shots, but vary camera angles, framings, lenses, and shot purposes to provide robust edit coverage. Case 2: User Text Input ONLY (No New Image) Keep using the active STYLE_ANCHOR for style/tonal attributes. Treat the text as the focal scene or action point for this batch of shots. Shot 1 must represent the clearest, most direct match to the text request. Shots 2–5 must stay in the same scene/location and act as supporting B-roll coverage to build edit continuity. Cinematic B-roll Sequencing Logic Think like a seasoned editor building a sequence, not like a prompt writer repeating variations of a single wide shot. Avoid 5 near-duplicate compositions. Every shot must have clear purpose in an edit timeline.
Story-supporting coverage: Integrate details, inserts, tactile close-ups, environmental cutaways, isolated object focus, reaction moments, aftermath, and transition shots. If the user specifies a primary action: Shot 1 = represents the primary action clearly. Shots 2–5 = close-ups, tactile inserts (handles, hinges, moving parts), surrounding elements, secondary frames, aftermath (dust settling, debris, footprint on floor), or nearby contextual objects that enrich the moment. Variety guidelines: Mix low/high angles, macro lens close-ups, wide establishing shots, and point-of-view framings.
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 · 82 lines · 46 tokens per session scan A 0e0f0016754e
b-roll-shot-planner is a skill published in the GitHub repository alecs5am/ralphy (140 stars, last pushed 23d ago), licensed Apache-2.0. It adds 46 tokens to every session and 1,138 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
video-gen
Use when generate videos with AI models — Runway, Kling, Sora, Pika, Seedance 2.0, Grok Imagine, Veo. Text-to-video, image-to-video, video extension, multi-modal references. Use when generating video from text prompts, animating images, or creating AI video content.
clinical-reports
Write comprehensive clinical reports including case reports (CARE guidelines), diagnostic reports (radiology/pathology/lab), clinical trial reports (ICH-E3, SAE, CSR), and patient documentation (SOAP, H&P, discharge summaries). Full support with templates, regulatory compliance (HIPAA, FDA, ICH-GCP), and validation…
imaging-data-commons
Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.
clinical-decision-support
Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading…
immunology-assays
Computational analysis of immunology experimental data. ATAC-seq differential accessibility, immune cell tracking from microscopy, ELISA data processing with 4-parameter logistic fitting, immunohistochemistry quantification, antibody titer analysis, and cell cycle phase duration estimation. For flow cytometry use…
molecular-cloning
Molecular cloning simulation and design. PCR amplicon prediction, restriction enzyme digestion, Golden Gate and Gibson assembly simulation, primer design, CRISPR sgRNA design, and plasmid annotation. For protein-level sequence analysis use biopython or esm; for database lookups use gene-database or ensembl-database.