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 feiskyer/codex-settings --skill nanobanana-skillgit clone --depth 1 https://github.com/feiskyer/codex-settingsWrote 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/feiskyer/codex-settings/nanobanana-skill)<a href="https://agentmods.dev/skills/feiskyer/codex-settings/nanobanana-skill"><img src="https://agentmods.dev/badge/skills/feiskyer/codex-settings/nanobanana-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/feiskyer/codex-settings/nanobanana-skill"><img src="https://agentmods.dev/badge/skills/feiskyer/codex-settings/nanobanana-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Rogue Agent · line 79 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00039 | $0.01033 |
| Opus 5.5 | $0.00016 | $0.00413 |
| Sonnet 5.5 | $0.00008 | $0.00207 |
| Haiku 4.5 | $0.00004 | $0.00103 |
Grade A, and why
nanobanana-skill 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 26d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nanobanana Image Skill
Use the bundled nanobanana.py to generate or edit images with Gemini image models. The default path targets Nano Banana 2 (gemini-3.1-flash-image-preview) with thinking summaries and Google Search grounding on, because those defaults are the main reason to use this skill instead of a generic image prompt.
Requirements
GEMINI_API_KEYin~/.nanobanana.env(GEMINI_API_KEY=sk-dummy) or the shell environment.- Python dependencies from
requirements.txt. - The executable is
nanobanana.pyin this same skill directory. Resolve its absolute path once before running it.
The CLI can print --help without credentials. It validates local input files before creating an API client and exits non-zero when the API returns no image.
Defaults
Model gemini-3.1-flash-image-preview, search grounding on, thinking summaries on at level high, resolution 1K, and no aspect ratio unless the request implies a shape. Do not make the user choose a model, search mode, or thinking mode unless they asked for that level of control.
Leaving aspect ratio unspecified is usually better for edits, because Gemini can match the input image shape. For text-only generation, set one only when the user implies a format such as poster, square post, banner, phone wallpaper, or ultrawide hero.
Worth overriding: --model gemini-3-pro-image-preview for very detail-heavy or typography-sensitive work (slower); --resolution 512px for quick ideation (Nanobanana 2 models only), 2K/4K for polished deliverables; --thinking-level low when latency beats refinement; search off when the user wants a purely imaginative result. Run python3 /absolute/path/to/nanobanana.py --help for the exact accepted values, including the full aspect-ratio and model lists.
Run it
Generate from text:
python3 /absolute/path/to/nanobanana.py \
--prompt "Create a high-end coffee bag package design with tactile paper texture and clear typography" \
--output /absolute/path/to/output/package.png
What ships with it
4 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.
- 26d ago Changed · -11 tokens per session b38fed047466
- 1mo ago Changed · -166 lines · -57 tokens per session 60ed128dea4d
- 1mo ago First seen · 241 lines · 107 tokens per session scan A 0b4870a685e1
nanobanana-skill is a skill published in the GitHub repository feiskyer/codex-settings (247 stars, last pushed 27d ago), licensed MIT. It adds 39 tokens to every session and 1,033 once invoked, about $0.0002 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
github-review-pr
Review GitHub pull requests with detailed, multi-perspective code analysis using parallel subagents. Use this skill whenever the user wants to review a PR, asks for code review on a pull request, mentions "review PR", "check this PR", "look at pull request", or references a PR number or GitHub PR URL. Do NOT use for…
skill-creator
Create, refine, and benchmark agent skills. Use when building a new skill, updating an existing one, running evals, checking trigger quality, or improving a skill description.
deep-research
Multi-agent research orchestration: split a research goal into parallel sub-goals, run each via headless claude -p subprocesses, aggregate results into a polished report file. Use for systematic web/document research, competitive or industry analysis, batch link/dataset processing, and long-form evidence synthesis.…
brainstorming
Explore user intent, requirements, and design options through collaborative dialogue before implementation. Use before building new features, components, or systems — whenever the user describes something to build and design decisions are involved. Triggers: "brainstorm", "help me design", "think through the…
grill-me
A guided, adversarial interview for challenging a plan or design one question at a time. It also records agreed terms and architectural decisions as the discussion develops.
gpt-image-skill
A skill for generating or editing images through OpenAI's GPT Image API, a programming interface for requesting image operations. It uses a bundled Python script and supports configuration such as model, size, quality, and output file.