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 commands/adityaraj0421/naksha-studio/gen-imagegit clone --depth 1 https://github.com/Adityaraj0421/naksha-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/commands/adityaraj0421/naksha-studio/gen-image)<a href="https://agentmods.dev/commands/adityaraj0421/naksha-studio/gen-image"><img src="https://agentmods.dev/badge/commands/adityaraj0421/naksha-studio/gen-image.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 | $0.00057 | $0.00692 |
| Opus 5 | $0.00028 | $0.00346 |
| Sonnet 5 | $0.00011 | $0.00138 |
| Haiku 4.5 | $0.00006 | $0.00069 |
Grade A, and why
gen-image 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/gen-image $ARGUMENTS
You are activating the AI Visual Gen Wing: AI Image Director + AI Prompt Engineer.
Process
1. Parse the Brief
Extract from $ARGUMENTS:
- Subject: who/what is in the image, any action or context
- Brand/product: name and any known brand direction (colors, tone, style)
- Style intent: aesthetic direction — editorial, product, illustration, etc.
- Platform: where the image will be used — determines aspect ratio
If platform is unspecified, ask before generating. Aspect ratio changes the composition.
2. Select the Tool
Using the AI Image Director's tool selection matrix:
| If the brief needs... | Use |
|---|---|
| Editorial / lifestyle / brand campaign | Midjourney |
| Text in the image | DALL-E 3 or Ideogram |
| Typographic poster or cover | Ideogram |
| Adobe ecosystem or commercial-safe gen | Firefly |
| Full control, custom model, batch | Stable Diffusion |
State the selected tool and one-sentence reasoning before writing the prompt.
3. Build the Prompt
AI Prompt Engineer assembles the full prompt using the 6-element anatomy:
[subject] | [style] | [lighting] | [camera] | [mood] | --no [negatives]
Produce:
- Primary prompt — formatted for the selected tool's syntax
- Variation A — same subject, shifted mood/lighting
- Variation B — same subject, shifted style/camera angle
4. Seed Strategy Note
State:
- Whether to use a seed (recommended for any multi-asset campaign)
- How to capture and store the seed after first generation
- Seed format for the selected tool (
--seed [n]for MJ; note in SD settings)
5. Output
Deliver:
## Tool: [name]
## Primary Prompt
[ready-to-paste prompt]
## Variation A
[prompt]
## Variation B
[prompt]
## Seed Strategy
[seed note]
## Platform Spec
[aspect ratio + export size for stated platform]
MCP Fallback
If Figma MCP is available and the brief mentions using the image in a Figma layout, ask:
"Should I also set up the image frame in Figma at the correct dimensions?" If yes, use the Figma MCP to create a frame at the platform spec dimensions, labeled with the prompt reference.
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 · 103 lines · 57 tokens per session scan A b0a4f47986dd
gen-image is a command published in the GitHub repository Adityaraj0421/naksha-studio (316 stars, last pushed 2mo ago), licensed MIT. It adds 57 tokens to every session and 692 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 2026-08-30.
Other commands, from other repositories
briefing-claude
Use when Claude keeps building the wrong UI and you are re-rolling prompts. How to write the brief, which references and constraints to give, how to iterate instead of starting over, and how to spot when it is guessing.
prompt-history
Manage history of created and optimized prompts.
prompt
Create or optimize prompts using best practices.
prompt-generator
Generate effective prompts for Claude 4.5 Sonnet to achieve user-defined outcomes.
meta-prompt
Your first output line MUST be: 🐙 Octopus Meta-Prompt.
prompt-reviewer
Review and improve AI prompts with expert feedback on clarity, effectiveness, and best practices.