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 agentmods add skills/whystrohm/shotkit/visual-prompt-forgenpx skills add whystrohm/shotkit --skill visual-prompt-forgegit clone --depth 1 https://github.com/whystrohm/shotkitWhat 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 | $0.00138 | $0.04298 |
| Opus 5 | $0.00069 | $0.02149 |
| Sonnet 5 | $0.00028 | $0.00860 |
| Haiku 4.5 | $0.00014 | $0.00430 |
Grade A, and why
visual-prompt-forge 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 2d 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 — 364 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual Prompt Forge
You are turning structured shot data into prompts that work in production. Each image generator rewards a different prompting style, short and high-signal for Midjourney, natural-language for Flux, paragraph-form for GPT Image, text-aware for Ideogram. A prompt that crushes in one will produce slop in another.
This skill adapts. Same shot, different syntax.
When to use
Trigger when the user:
- Hands over a
shots.json(or any structured shot list) and asks for prompts - Names a specific generator (Midjourney, Flux, Ideogram, GPT Image, Nano Banana, Seedream, Kling, Veo, Seedance, Hailuo)
- Asks for "image prompts," "Midjourney prompts," "AI prompts," "generation prompts" for a storyboard
- Wants the same shot adapted to multiple generators
If the user wants to build a storyboard from scratch (no shots.json yet), use storyboard-architect first, then chain into this skill.
What you produce
For a given shots.json and a list of target generators, produce one file per generator,
inside a directory named for the round:
output/prompts/round-1/
├── midjourney.txt # If targeted
├── flux.txt
├── ideogram.txt
├── gpt-image.txt
├── nano-banana.txt
├── seedream.txt
├── kling.txt # Motion-aware video, default
├── veo.txt # Motion, dialogue/lipsync + native audio
├── seedance.txt # Motion, multi-shot sequences
└── hailuo.txt # Motion, budget iteration
Round 1 is the first pass. Revision mode writes output/prompts/round-2/, and so on.
The round in the path is not decoration: prompt files used to be written to one fixed
path per generator, so round 2 destroyed round 1 and the prompt that actually produced
most of the surviving frames was gone.
Each file is plain text, one prompt per shot, separated by a blank line and a # shot_NN comment. Designed for copy-paste workflows, drop into the generator's UI or pipe into an API.
The five-layer prompt anatomy
Every prompt is composed from these layers. Read references/prompt-anatomy.md for the full theory. Quick version:
What ships with it
23 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.
- adapters/_capabilities.json 6.8 KB
- adapters/capabilities.schema.json 2.4 KB
- adapters/flux.md 5.2 KB
- adapters/gpt-image.md 5.0 KB
- adapters/hailuo.md 3.9 KB
- adapters/ideogram.md 4.7 KB
- adapters/kling.md 5.1 KB
- adapters/midjourney.md 4.9 KB
- adapters/nano-banana.md 5.1 KB
- adapters/seedance.md 4.5 KB
- adapters/seedream.md 4.2 KB
- adapters/veo.md 4.5 KB
- examples/one-shot-all-adapters/flux.txt 1.0 KB
- examples/one-shot-all-adapters/gpt-image.txt 1.5 KB
- examples/one-shot-all-adapters/ideogram.txt 941 B
- examples/one-shot-all-adapters/kling.txt 1023 B
- examples/one-shot-all-adapters/midjourney.txt 684 B
- examples/one-shot-all-adapters/nano-banana.txt 1.3 KB
- examples/one-shot-all-adapters/README.md 2.9 KB
- examples/one-shot-all-adapters/seedream.txt 697 B
- references/consistency-locks.md 5.3 KB
- references/failure-modes.md 6.3 KB
- references/prompt-anatomy.md 4.4 KB
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.
- 2d ago First seen · 364 lines · 138 tokens per session scan A 46760f0ebecf
visual-prompt-forge is a skill published in the GitHub repository whystrohm/shotkit (18 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 138 tokens to every session and 4,298 once invoked, about $0.0007 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
clinpgx-database
Access ClinPGx pharmacogenomics data (successor to PharmGKB). Query gene-drug interactions, CPIC guidelines, allele functions, for precision medicine and genotype-guided dosing decisions.
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
datavis
Comprehensive data visualization toolkit for creating beautiful, mathematically elegant visualizations with D3.js, Chart.js, and custom SVG. Use when (1) building interactive data visualizations, (2) designing color palettes for charts, (3) choosing scales and visual encodings, (4) creating data pipelines from…
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.
vibe-research
Deep research and market validation for app ideas. Use when starting a new project, validating an idea, or when the user says "research my idea", "validate my app", or "help me start a new project".
detecting-data-anomalies
Investigate outliers, rare events, spikes, and suspicious records in datasets. Use as an explicit anomaly-analysis helper when you want concrete anomaly-detection workflow guidance, not generic data validation or end-to-end ML ownership.