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 Glad-Labs/poindexter --skill image-generationgit clone --depth 1 https://github.com/Glad-Labs/poindexterWrote 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/glad-labs/poindexter/image-generation)<a href="https://agentmods.dev/skills/glad-labs/poindexter/image-generation"><img src="https://agentmods.dev/badge/skills/glad-labs/poindexter/image-generation/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/skills/glad-labs/poindexter/image-generation"><img src="https://agentmods.dev/badge/skills/glad-labs/poindexter/image-generation.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 | $0.00066 | $0.01357 |
| Opus 5 | $0.00033 | $0.00678 |
| Sonnet 5 | $0.00013 | $0.00271 |
| Haiku 4.5 | $0.00007 | $0.00136 |
Grade A, and why
image-generation 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 10d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image generation skill
The prompts the pipeline uses to direct visuals for a post — a featured
hero prompt, inline-section illustrations, stock search queries, the
image-director reasoning that decides which sections get images, and the
vision alt-text captioner that describes the rendered result. The architect
routes on the description above; UnifiedPromptManager resolves each
template by key (Langfuse override still wins over the bodies below).
Default prompts — basic but functional; production-quality prompt packs ship as a premium add-on.
image.featured_image
Write a single Stable Diffusion XL image prompt for a magazine-style editorial cover illustration.
Image subject: {subject}
Art style: {style} — {style_tags}
Depict a concrete, specific subject or scene that represents the image subject above (a recognizable object, place, or visual metaphor), rendered fully in the "{style}" art style. Commit to that style's medium, palette, and composition. Do NOT default to a generic glowing-circuit board or abstract floating-data backdrop, and do not lock every image to teal/cyan — vary the focal subject, composition, and color treatment so it reads differently from a typical tech illustration. People are welcome when they serve the subject — keep them stylized (never photoreal) and their action simple and specific; one or two figures beat a crowd. No text or words in the image.
Output ONLY the image prompt, 1-2 sentences, nothing else.
image.inline_illustration
Write a single Stable Diffusion XL image prompt for a blog section illustration.
Section subject: {search_query}
Art style: {style}
Depict a specific, concrete scene for the section subject, rendered fully in the "{style}" art style — commit to that style's medium and palette rather than a generic tech render or screenshot. People are fine when the section subject involves them — stylized, never photoreal, doing something concrete. No text or words. Vary the composition so it doesn't look like every other section image.
Output ONLY the image prompt, 1 sentence, nothing else.
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.
- 10d ago First seen · 121 lines · 66 tokens per session scan A 3a367ea2b269
image-generation is a skill published in the GitHub repository Glad-Labs/poindexter (5 stars, last pushed today), licensed Apache-2.0. It adds 66 tokens to every session and 1,357 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
content-pipeline
A Chinese-language workflow for turning collected source material into articles and versions for several publishing platforms, including formatted previews, cover images, social posts, podcasts, and videos.
openai-image-gen
Batch-generate images via OpenAI Images API. Random prompt sampler + index.html gallery.
nano-banana-pro
Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro).
video-frames
Extract frames or short clips from videos using ffmpeg.
sherpa-onnx-tts
Local text-to-speech via sherpa-onnx (offline, no cloud).
sag
ElevenLabs text-to-speech with mac-style say UX.