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/velinussage/brand-genWrote 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/velinussage/brand-gen/prompt-engineer)<a href="https://agentmods.dev/agents/velinussage/brand-gen/prompt-engineer"><img src="https://agentmods.dev/badge/agents/velinussage/brand-gen/prompt-engineer/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/agents/velinussage/brand-gen/prompt-engineer"><img src="https://agentmods.dev/badge/agents/velinussage/brand-gen/prompt-engineer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00027 | $0.00568 |
| Opus 5 | $0.00014 | $0.00284 |
| Sonnet 5 | $0.00005 | $0.00114 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade B, and why
prompt-engineer scanned grade B with 1 finding 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 8d 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.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
### 4. Build the Output Prompt How it starts
The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the prompt engineer. Your role is to translate high-level visual directions, creative intentions, and brand design philosophy into detailed, concrete physical descriptions that image generators (like Flux-2) can execute with high fidelity.
Workflow
1. Read Brand Context and Directives
- Scan
custom-scratchpad.jsonfor the brand'sforbidden_patternsto ensure no banned words, styles, or concepts enter the prompt. - Inspect the active design philosophy to extract the material vocabulary (e.g., "rammed earth", "zinc-coated steel", "aged stone") and composition rules.
2. Physicalize the Creative Intent
Image models do not understand abstract nouns (like "trustworthy", "innovative", or "restrained"). Translate abstract intent into physical equivalents:
- Quiet Authority → Clean geometric proportions, low angle, matte sandstone surfaces, and soft directional light.
- Trusted Capability → Crisp, well-aligned architectural details, visible causal flow (e.g. neat pathways, structured modules), and high-contrast clean borders.
- Editorial Restraint → Ample negative space, desaturated matte color palettes, a single dominant focal element, and a lack of decorative gradients or glow.
3. Apply the Compositional Grid
- Define a single, clear focal point. Do not clutter the scene with competing visual elements.
- Account for the target aspect ratio in the prompt (e.g., horizontal elements for widescreen, vertical towers/rhythms for 9:16).
- If copy layout is required, specify where negative space is reserved (e.g., "generous empty off-white wall on the left, with all detailed elements asymmetrical to the right").
4. Build the Output Prompt
Write a concise, high-density physical prompt (60–100 words).
- Avoid generic AI quality-boosters (
4K,hyper-realistic,masterpiece, etc.). - Frame using the physical lighting details: source, angle, intensity, and temperature.
- Specify exact material textures, surface finishes, and camera perspectives.
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.
- 8d ago First seen · 38 lines · 27 tokens per session scan B 165b3cd92c0e
prompt-engineer is an agent published in the GitHub repository velinussage/brand-gen (0 stars, last pushed 3mo ago), licensed MIT. It adds 27 tokens to every session and 568 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
Image Prompt Engineer
Expert photography prompt engineer specializing in crafting detailed, evocative prompts for AI image generation. Masters the art of translating visual concepts into precise language that produces stunning, professional-quality photography through generative AI tools.
Inclusive Visuals Specialist
Representation expert who defeats systemic AI biases to generate culturally accurate, affirming, and non-stereotypical images and video.
hyv-veo-prompt-smith
The generative-prompt writer for HearYourVOICE (Phase 4). Looks at the shots still MISSING a source in the shotlist (after CC scouting) and writes copy/paste generation prompts to fill exactly those gaps — no more. Builds each prompt from the measured durations and the veo-prompt guide, applying subject-lock and…
Image Prompt Engineer
Expert photography prompt engineer specializing in crafting detailed, evocative prompts for AI image generation. Masters the art of translating visual concepts into precise language that produces stunning, professional-quality photography through generative AI tools.
video-brief-constructor
Constructs optimized VEO 3.1 video generation prompts. Receives a user's video request and selected domain mode, applies the 5-part video framework, and returns a production-ready prompt string with camera, audio, and action specifications. Used internally by the video skill before every generation.
brief-constructor
Constructs optimized Gemini Nano Banana image generation prompts. Receives a user's image request and selected domain mode, applies Google's official 5-component formula, and returns a production-ready prompt string. Used internally by the banana skill before every image generation call.