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 code-yeongyu/senpi --skill skillgit clone --depth 1 https://github.com/code-yeongyu/senpiWrote 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/code-yeongyu/senpi/skill)<a href="https://agentmods.dev/skills/code-yeongyu/senpi/skill"><img src="https://agentmods.dev/badge/skills/code-yeongyu/senpi/skill/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/code-yeongyu/senpi/skill"><img src="https://agentmods.dev/badge/skills/code-yeongyu/senpi/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.02093 |
| Opus 5.5 | $0.00026 | $0.00837 |
| Sonnet 5.5 | $0.00013 | $0.00419 |
| Haiku 4.5 | $0.00007 | $0.00209 |
Grade A, and why
gpt-image-gen 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 1mo 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GPT Image Generation
How to get the image right the first time, and how to fix it fast when it is not. Read this before your first generation call.
Which tool
When image generation tooling is present in your tool set, pick the surface that actually exists right now:
- If a native
image_generationserver tool is available, use it. The provider runs generation server-side and returns the image in the response stream. - Otherwise, call the
generate_imagetool. It sends your prompt and optional reference images to the configured OpenAI-compatible endpoint and saves the result as a png, jpeg, or webp file. The model, quality, size, background, and format controls below apply togenerate_image, not to the native server tool.
Check your current tool set before choosing. Tool state can change mid-session (model switch, credential change), so trust the tools you can see over what this page said at startup. If both surfaces ever appear, prefer the native server tool. When the request is clear, generate directly instead of asking for confirmation; ask only when a required reference image is missing.
Model selection
gpt-image-2.5-sunburst(default): the base model, optimized for quality, above gpt-image-2. Use it for precise edits, fidelity to reference subjects and products, dense text or diagrams, and final production assets.gpt-image-2.5-flare: the small model, optimized for speed, with quality comparable to gpt-image-2. Reach for it when latency or volume matters more than the last increment of quality.gpt-image-2: previous generation; quality tiers stop athigh, transparency is preview-level.
The default is the better model on purpose. When a workflow turns out to be latency-sensitive, run the same prompt and inputs on Flare and switch only if the result still meets the bar.
Prompt crafting
Start from the deliverable, then describe what is visible. Match the prompt's specificity to the user's request:
- A specific request (exact text, a named layout, a product photo brief) is normalized, not padded. Keep every stated requirement; do not add objects, people, brands, slogans, or story beats the user did not ask for.
- A generic request ("a logo for a bakery") gets tasteful concreteness: medium, composition, lighting, palette, materials. Stay within what the request implies.
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.
- 1mo ago Changed · -18 lines · +3 tokens per session 32c29f27c041
- 1mo ago Changed · +43 lines ad0659eb1871
- 1mo ago First seen · 68 lines · 63 tokens per session scan A c17f229c5207
gpt-image-gen is a skill published in the GitHub repository code-yeongyu/senpi (482 stars, last pushed today), licensed MIT. It adds 66 tokens to every session and 2,093 once invoked, about $0.0003 per session on Opus 5.5. 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 skills, from other repositories
transformers
This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning…
segment-anything-model
Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks in an image.
hugging-face-cli
Execute Hugging Face Hub operations using the hf CLI. Use when the user needs to download models/datasets/spaces, upload files to Hub repositories, create repos, manage local cache, or run compute jobs on HF infrastructure. Covers authentication, file transfers, repository creation, cache operations, and cloud compute.
stable-diffusion-image-generation
State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.
autogpt-agents
Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems.
blip-2-vision-language
Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.