nexu is an open-source desktop client that connects an OpenClaw AI agent to messaging services such as WeChat, Feishu, Slack, and Discord. It is for people who want to chat with their agent from those channels using their own model credentials while keeping data on their computer, and the catalogue entries support its agent workflows.
Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/nexu-io/nexu/nano-banana)<a href="https://agentmods.dev/skills/nexu-io/nexu/nano-banana"><img src="https://agentmods.dev/badge/skills/nexu-io/nexu/nano-banana/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/nexu-io/nexu/nano-banana"><img src="https://agentmods.dev/badge/skills/nexu-io/nexu/nano-banana.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 | $0.00044 | $0.00824 |
| Opus 5 | $0.00022 | $0.00412 |
| Sonnet 5 | $0.00009 | $0.00165 |
| Haiku 4.5 | $0.00004 | $0.00082 |
Grade A, and why
nano-banana 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 13d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nano Banana — Image Generation
Image generation script supporting three models. Requires sharp for input image compression (auto-installed on first run).
Models
| Flag | Notes |
|---|---|
--model nano-banana |
Default. Fast, good quality. |
--model nano-banana-pro |
Highest quality, slower. |
--model nano-banana-2 |
Legacy model. |
Generate an image
node {baseDir}/scripts/generate-image.js --prompt "a cat sitting on mars" --filename "cat-on-mars.png"
Edit a single image
node {baseDir}/scripts/generate-image.js \
--prompt "make the sky purple" \
--filename "edited.png" \
-i "/path/to/input.png" \
--model nano-banana-pro
Multi-image composition (up to 14 images)
node {baseDir}/scripts/generate-image.js \
--prompt "combine these into a collage" \
--filename "collage.png" \
-i img1.png -i img2.png -i img3.png
Options
| Flag | Short | Default | Description |
|---|---|---|---|
--prompt |
-p |
required | Image description or editing instruction |
--filename |
-f |
required | Output filename |
--input-image |
-i |
— | Input image(s), repeatable, max 14 |
--model |
— | nano-banana |
nano-banana, nano-banana-pro, or nano-banana-2 |
--resolution |
-r |
1K |
1K, 2K, or 4K |
--aspect-ratio |
— | — | e.g. 1:1, 16:9, 4:3, 3:4, 9:16 |
API key
The API key is pre-configured on this machine. No flags or environment variables needed.
Input image handling
All input images are sent as inline base64. Images over 500 KB are automatically compressed to JPEG and resized to fit under the limit. This keeps requests fast and avoids File API auth issues with the enterprise endpoint.
Output
Relative filenames are saved to $OPENCLAW_STATE_DIR/media/outbound/{slugid}/nano-banana/{filename}. Absolute paths are used as-is. Absolute paths are used as-is. Use timestamps in filenames to avoid overwrites: cat-on-mars-20260304-165000.png.
What ships with it
2 files 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.
- 13d ago First seen · 90 lines · 44 tokens per session scan A 63f51ca819d2
nano-banana is a skill published in the GitHub repository nexu-io/nexu (3,268 stars, last pushed 4mo ago), licensed MIT. It adds 44 tokens to every session and 824 once invoked, about $0.0002 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
clip-hand-skill
Expert knowledge for AI video clipping — yt-dlp downloading, whisper transcription, SRT generation, and ffmpeg processing.
twitter-hand-skill
Expert knowledge for AI Twitter/X management — API v2 reference, content strategy, engagement playbook, safety, and performance tracking.
collector-hand-skill
Expert knowledge for AI intelligence collection — OSINT methodology, entity extraction, knowledge graphs, change detection, and sentiment analysis.
predictor-hand-skill
Expert knowledge for AI forecasting — superforecasting principles, signal taxonomy, confidence calibration, reasoning chains, and accuracy tracking.
researcher-hand-skill
Expert knowledge for AI deep research — methodology, source evaluation, search optimization, cross-referencing, synthesis, and citation formats.
lead-hand-skill
Expert knowledge for AI lead generation — web research, enrichment, scoring, deduplication, and report generation.