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/squadcodercom/squadcoder/image-gen-promptingnpx skills add squadcodercom/squadcoder --skill image-gen-promptinggit clone --depth 1 https://github.com/squadcodercom/squadcoderWhat 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 | $0.00095 | $0.00820 |
| Opus 5 | $0.00048 | $0.00410 |
| Sonnet 5 | $0.00019 | $0.00164 |
| Haiku 4.5 | $0.00010 | $0.00082 |
Grade A, and why
sc:image-gen-prompting 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Image Prompting
Turn a request into a precise, generator-ready prompt. A good prompt is specific and ordered, not a pile of adjectives.
Prompt formula (in this order)
[subject + action] , [environment/context] , [composition/shot] , [style/medium] , [lighting] , [color/mood] , [quality/render] , [params]
Example: "a ceramic coffee mug on a marble countertop, morning kitchen, close-up product shot, soft natural window light from the left, warm muted palette, photorealistic, shallow depth of field --ar 4:5"
Levers (pick deliberately)
- Shot: close-up / macro / medium / wide / aerial / flat-lay / eye-level.
- Lens/feel: 35mm, 85mm portrait, tilt-shift, bokeh, long exposure.
- Style: photorealistic, 3D render, isometric, watercolor, line art, brand-flat, cyberpunk, claymation.
- Lighting: soft natural, golden hour, studio softbox, rim light, neon, chiaroscuro.
- Mood/color: warm/cool, pastel, high-contrast, monochrome, on-brand hex.
Negative prompts (SD/Flux)
List what to avoid: extra fingers, deformed hands, text, watermark, blurry, low-res, jpeg artifacts, duplicate.
Aspect ratios by use
- Square 1:1 (IG feed, avatars) · Portrait 4:5 (IG/FB feed) · 9:16 (Stories/Reels/TikTok) · 16:9 (YouTube/web hero) · 1.91:1 (link previews/ads).
Model-specific notes
- Midjourney: terse, comma-separated; use
--ar,--s(stylize),--c(chaos),--nofor negatives. Quality over sentence grammar. - DALL·E / GPT-Image: full natural-language sentences; great at following instructions + text-in-image; describe layout explicitly.
- Stable Diffusion / Flux: weighted tokens
(keyword:1.3), explicit negative prompt, set steps/CFG; good for control + LoRAs. - Higgsfield: motion/video-oriented — specify camera move (push-in, orbit, pan), duration, and a clear single subject; keep scenes simple.
Product / ad creatives (most common ask)
- Isolate the product, name the surface + background, specify lighting direction, leave negative space for copy if it's an ad.
- Keep brand colors; request a clean composition; generate 3–4 variations and pick.
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 · 49 lines · 95 tokens per session scan A 11c859011b07
sc:image-gen-prompting is a skill published in the GitHub repository squadcodercom/squadcoder (11 stars, last pushed 2mo ago), licensed MIT. It adds 95 tokens to every session and 820 once invoked, about $0.0005 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
remotion-to-hyperframes
Port an existing Remotion (React) composition's source to HyperFrames HTML. Use ONLY on an explicit ask to port/convert/migrate/translate a Remotion source — one-way, Remotion-only. A passing Remotion mention, reference-only code, or "make something like my Remotion video" is a fresh build (/general-video). Unclear →…
apple-design
Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading)…
transformers-js
Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, summarization), computer vision (image classification, object detection), audio (speech recognition, audio classification), and multimodal tasks. Works in browsers and…
gemini-live-api-dev
Use this skill when building real-time, bidirectional streaming applications with the Gemini Live API. Covers WebSocket-based audio/video/text streaming, voice activity detection (VAD), native audio features, function calling, session management, ephemeral tokens for client-side auth, live translation, and all Live…
swiftui-expert-skill
Use when writing, reviewing, or refactoring SwiftUI code for iOS or macOS, including state management and @Observable data flow, view composition and invalidation/performance, lists and ForEach identity, environment usage, localization, animations, Liquid Glass adoption, migrating soft-deprecated APIs, or Instruments…
stage-edit
For the VideoStudio EDIT line, the edit decision list lives in project/plan.json and gate-control owns its Gate B authorization transition. Start/resume execution with production.status; do not run trims, assembly, or localization against a changed or unsigned EDL. Runtime status/producedpath updates do not invalidate…