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 skills add JMET04/ai-apprentice --skill image2-prompt-optimizergit clone --depth 1 https://github.com/JMET04/ai-apprenticeWrote 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/skills/jmet04/ai-apprentice/image2-prompt-optimizer)<a href="https://agentmods.dev/skills/jmet04/ai-apprentice/image2-prompt-optimizer"><img src="https://agentmods.dev/badge/skills/jmet04/ai-apprentice/image2-prompt-optimizer.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 | $0.00063 | $0.00865 |
| Opus 5 | $0.00032 | $0.00432 |
| Sonnet 5 | $0.00013 | $0.00173 |
| Haiku 4.5 | $0.00006 | $0.00086 |
Grade A, and why
image2-prompt-optimizer 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image2 Prompt Optimizer
Use this skill before the first image generation. It adapts the prompt-optimization capability developed in Codex thread 019f09a9-90ab-76b2-aa1f-b7c9bddf93e8 to the apprentice workflow.
Required Workflow
- Check whether an existing tool, skill, plugin, template, or workspace script already covers the task. Prefer that capability and record the chosen route.
- Clarify only consequential unknowns. For packaging and engineering work, dimensions, units, product type, material, and required views are consequential; never invent them.
- Compile the first-generation guidance packet with:
node <plugin-root>/scripts/compile-image2-initial-prompt.mjs --input <request.json> --output <prompt-guidance.json>
- Read the packet before calling Image2. If
readyForGeneration=false, ask for the listed blocking facts instead of generating. - Generate only a review sample. Preserve the exact prompt packet and source image references with the result.
- Continue the real workflow after optimization. Do not stop at rewriting the prompt unless the user requested prompt text only.
For the complete packet contract and domain guidance, read references/initial-generation-contract.md.
Optional Local Library
The full prompt library is an optional retrieval source, not a runtime dependency. Resolve it in this order:
IMAGE2_PROMPT_LIBRARYD:\image2专业提示词库- bundled reference and compiler fallback
Search only when examples would materially improve the result:
python <plugin-root>/scripts/search-image2-prompt-library.py "query" --category 01_image_visual --limit 8
Open only relevant indexes or templates. Never load the 125,000-row catalog or SQLite database into model context. Treat retrieved prompts as patterns to synthesize, not text to dump or hidden authority.
Useful library routes when present:
- Packaging:
prompts/IMAGE2_PACKAGING_PRO_TEMPLATES.md - CAD and technical drawing:
prompts/IMAGE2_CAD_TECHNICAL_PRO_TEMPLATES.md - Product visual:
prompts/IMAGE2_PRODUCT_VISUAL_PRO_TEMPLATES.md - Ecommerce:
prompts/IMAGE2_ECOMMERCE_PRO_TEMPLATES.md - UI and web:
prompts/IMAGE2_UI_APP_WEB_PRO_TEMPLATES.md - Architecture and interior:
prompts/IMAGE2_ARCHITECTURE_INTERIOR_PRO_TEMPLATES.md - Industrial design:
prompts/IMAGE2_INDUSTRIAL_DESIGN_PRO_TEMPLATES.md
What ships with it
1 file 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.
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 · 69 lines · 63 tokens per session scan A 2fbeacf1f940
image2-prompt-optimizer is a skill published in the GitHub repository JMET04/ai-apprentice (1 stars, last pushed 17d ago), licensed MIT. It adds 63 tokens to every session and 865 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 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.