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 blueberrycongee/Lumina-Note --skill image-gengit clone --depth 1 https://github.com/blueberrycongee/Lumina-NoteWrote 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/blueberrycongee/lumina-note/image-gen)<a href="https://agentmods.dev/skills/blueberrycongee/lumina-note/image-gen"><img src="https://agentmods.dev/badge/skills/blueberrycongee/lumina-note/image-gen/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/blueberrycongee/lumina-note/image-gen"><img src="https://agentmods.dev/badge/skills/blueberrycongee/lumina-note/image-gen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 109 Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.Fix: Set explicit rate limits, timeouts, and resource quotas for API calls, file operations, and compute. Implement circuit breakers for runaway loops.
- medium Memory Poisoning · line 118 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
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 | $0.00060 | $0.01671 |
| Opus 5 | $0.00030 | $0.00835 |
| Sonnet 5 | $0.00012 | $0.00334 |
| Haiku 4.5 | $0.00006 | $0.00167 |
Grade A, and why
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 9d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image generation playbook
You have one image-generation tool: generate_image. It routes to one of three providers (gpt-image-2, Gemini Nano Banana, Seedream 4.5) and writes a PNG to assets/generated/<YYYY-MM>/<id>.png inside the vault, with a sidecar JSON capturing the prompt and references for reproducibility.
The tool is registered by Lumina's plugin. The provider's API key must already be configured in AI Settings → Image Models — surface that path in your error message if you hit a "no API key" error.
When to invoke
Trigger on intent, not specific words. Plausible signals:
- Direct ask: "draw / generate / paint / create an image of …", "make me a picture of …".
- Note-illustration ask: "give this note a header image", "an icon for this section", "a cover for the chapter".
- Mood / inspiration ask: "what would X look like", "show me a vibe board for …", "imagine …".
- Continuation: "make it more …", "in the style of that other one" — usually means iterate on the most recent generated image.
Don't invoke when:
- The user's intent is a diagram (mermaid, sequence chart, flow). Use markdown / mermaid instead — generation models do diagrams badly.
- The user wants a real photograph of a real subject (a person, an event). Image gen is synthesis, not retrieval.
- The user's request is ambiguous and getting it wrong wastes their time. Ask one clarifying question instead of guessing.
Provider routing
Pick the provider parameter based on what the request is for and what is configured. When Lumina tells you a configured provider in the user message wrapper, use only that provider unless Lumina explicitly lists another configured provider. Never switch to an unconfigured provider.
| Use this provider | When the request is… |
|---|---|
openai-image (gpt-image-2) |
Photorealism is essential, the user explicitly asks for OpenAI / DALL-E / GPT, or Lumina says OpenAI is the configured image provider. |
google-image (Nano Banana) |
General-purpose, iterating with reference images, anything where consistency across multiple frames matters, when Google image generation is configured. |
bytedance-image (Seedream 4.5) |
The image needs to render readable text, dense typography, or poster-style layouts, and Seedream is configured. The language the user typed in is not by itself a visible-text requirement. |
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.
- 9d ago First seen · 119 lines · 60 tokens per session scan A 3bafcffb57c6
image-gen is a skill published in the GitHub repository blueberrycongee/Lumina-Note (911 stars, last pushed 26d ago), licensed Apache-2.0. It adds 60 tokens to every session and 1,671 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 skills, from other repositories
slidev
Create and present web-based slidedecks for developers using Slidev with Markdown, Vue components, code highlighting, animations, and interactive features. Use when building technical presentations, conference talks, code walkthroughs, teaching materials, or developer decks.
[object Object]
Read, search, and open notes in the user's "{{GRAPHNAME}}" Reflect graph via the reflect CLI. Use when the user asks about their notes, daily notes, journal, or anything they may have written down in Reflect.
reflect-design
Use this skill to generate well-branded interfaces and assets for Reflect (reflect.app, the minimalist networked note-taking app), either for production or throwaway prototypes/mocks/etc. Contains essential design guidelines, colors, type, fonts, assets, and UI kit components for prototyping.
release-version
Steps to cut a VNote version release (e.g. v4.3.0) — bump the version with scripts/updateversion.py, refresh and fill zhCN/ja translations via lupdate, write the changes.md changelog, and trigger the CI [Release] build. Use when asked to "release", "cut a release", "bump the version", or "prepare vX.Y.Z".
adv-art
Plan, generate, normalize, validate, and publish visual assets for an ADV.JS game. Use when creating character tachie and expression variants, backgrounds, CG illustrations, thumbnails, or an asset manifest; replacing placeholders with original artwork; preparing immutable CDN/COS object paths; or auditing provenance…
alive:demo
Generate a believable, lived-in ALIVE world from a free-text persona description (custom path) or a deterministic sandbox preset. Routes the create/list/activate/deactivate/delete/status surface and orchestrates the 5-stage subagent generation pipeline.