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/davistroy/claude-marketplaceWrote 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/davistroy/claude-marketplace/develop-image-prompt.eval)<a href="https://agentmods.dev/commands/davistroy/claude-marketplace/develop-image-prompt.eval"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/develop-image-prompt.eval.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 | $0.00000 | $0.00604 |
| Opus 5 | $0.00000 | $0.00302 |
| Sonnet 5 | $0.00000 | $0.00121 |
| Haiku 4.5 | $0.00000 | $0.00060 |
Grade A, and why
develop-image-prompt.eval 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 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.
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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eval: /develop-image-prompt
Purpose
Generates a detailed image generation prompt from a document or content description. Good output: a prompt that is specific, visual, non-abstract, includes style/composition/lighting guidance, and is calibrated to the specified dimensions and style options.
Fixtures
| Fixture | Purpose |
|---|---|
docs/sample-prd.md |
Source document for a product feature illustration |
docs/meeting-transcript.md |
Source for a team collaboration visual |
Test Scenarios
S1: Happy path — prompt from PRD
Invocation: /develop-image-prompt fixtures/docs/sample-prd.md
Must:
- Generates at least one image prompt
- Prompt is specific and visual (mentions concrete visual elements — not abstract concepts like "productivity")
- Prompt includes style guidance (e.g., illustration style, color palette, mood)
- Prompt is a single coherent paragraph or structured block, not a list of bullet points
Should:
- Prompt references Slack-like interface elements given the PRD's subject matter
- Includes composition guidance (foreground/background, perspective)
- Suggests aspect ratio or dimensions appropriate for the content
Must NOT:
- Generate a prompt that is purely text-based (e.g., "an image showing productivity")
- Include real company names, trademarks, or real people's faces
S2: Custom dimensions
Invocation: /develop-image-prompt fixtures/docs/sample-prd.md --dimensions 16:9
Must:
- Prompt specifies 16:9 landscape orientation
- Composition guidance suits widescreen format
S3: Custom style
Invocation: /develop-image-prompt fixtures/docs/sample-prd.md --style photorealistic
Must:
- Prompt is calibrated for photorealistic output (not cartoon/illustration)
- Style guidance in prompt matches the requested style
S4: Multiple prompt variants
Invocation: /develop-image-prompt fixtures/docs/sample-prd.md --variants 3
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 · 88 lines · 0 tokens per session scan A d1f93e870820
develop-image-prompt.eval is a command published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 604 tokens. 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 2026-08-31.
Other commands, from other repositories
gen-image
Generate a brand-aligned AI image — tool selection, full prompt (subject, style, lighting, camera, mood, negatives), variation prompts, and seed strategy. Works across Midjourney, DALL-E, Ideogram, Firefly, and Stable Diffusion.
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.
start-3-1-3
Module 3.1.3: Consistency & Style - Golden Rules of prompting, reference images, and variants.
stardust-use
A command for retrieving an encrypted prompt template from a service, decrypting it in memory, filling in parameters, and generating content. It requires an authenticated session.
pickle-prompt
Build a model-ready image/video prompt with the macro-pickle Prompt Engine and (on export) save it to your prompt vault.
improve-prompt
Improve any prompt — for LLMs/chat/agents or generative image/video/audio models. Model-agnostic; interviews to fill real gaps, then returns a rewritten prompt plus a short rationale.