Borrowing it
Nothing to install: this file belongs to hummer98/nanobanana-adc. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/hummer98/nanobanana-adc/main/CLAUDE.mdgit clone --depth 1 https://github.com/hummer98/nanobanana-adcWrote 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/instructions/hummer98/nanobanana-adc/claude-md)<a href="https://agentmods.dev/instructions/hummer98/nanobanana-adc/claude-md"><img src="https://agentmods.dev/badge/instructions/hummer98/nanobanana-adc/claude-md/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/instructions/hummer98/nanobanana-adc/claude-md"><img src="https://agentmods.dev/badge/instructions/hummer98/nanobanana-adc/claude-md.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 | $0.01205 | $0.01205 |
| Opus 5 | $0.00602 | $0.00602 |
| Sonnet 5 | $0.00241 | $0.00241 |
| Haiku 4.5 | $0.00120 | $0.00120 |
Grade A, and why
nanobanana-adc CLAUDE.md 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 11d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
nanobanana-adc
Gemini 3 Pro Image (Nano Banana Pro) CLI whose single differentiating axis is
Application Default Credentials (ADC) support on Vertex AI. Every other
Claude Code image skill on the market requires GEMINI_API_KEY; this one
covers the enterprise / CI / Cloud Run / Cloud Build blind spot.
プロジェクトミッション
Provide a zero-friction image generation CLI that works in both:
- AI Studio path —
GEMINI_API_KEYset. Lowest-friction for individuals. - Vertex AI path (ADC) —
gcloud auth application-default login+ a GCP project with Gemini 3 Pro Image access. Required in enterprise pipelines where baking long-lived API keys into CI is forbidden.
設計原則
| 原則 | 意味 |
|---|---|
| ADC is the primary axis | Any change that degrades the ADC path is a regression. The API-key path is a fallback for casual users. |
| One binary, two distributions | Ship via npm install -g and /plugin marketplace add. Same dist/cli.js, same bin/nanobanana-adc dispatcher. Do not fork the codebase. |
| No hidden coupling to Claude Code | The CLI must run standalone in any shell. Claude Code plugin wiring (SessionStart hooks, SKILL.md) lives at the edges, not in src/. |
| Fail loudly on auth ambiguity | [auth] using: adc / [auth] using: api-key is always printed. Users must be able to tell which path fired without reading the code. |
Region-less host for location=global |
Gemini 3 Pro Image is only served from aiplatform.googleapis.com (no region prefix). src/generate.ts has a branch for this — do not remove it. |
優先順位（高→低）
- ADC 経路のバグ修正 — main の差別化軸を壊すバグは最優先。
- モデル互換性 — 新しい Gemini image モデル ID / region が出たら追従。
- 配布経路の整備 — npm / Claude Code plugin / marketplace のどちらか一方でも壊れたら修正。
- ドキュメント — README / README.ja.md / CHANGELOG は挙動と同期させる。
- 新機能 — 画像編集 (inpainting / outpainting)、バッチ生成、MCP サーバ化は docs/seed.html で「スコープ外」としており、別リポ or feature flag で検討。
認証優先順位（src/auth.ts）
--api-key <key>CLI flagGEMINI_API_KEYenvironment variable- ADC (
GoogleAuth→ access token) — the main event
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.
- 11d ago First seen · 71 lines · 1,205 tokens per session scan A a845202faae8
nanobanana-adc CLAUDE.md is an instructions file published in the GitHub repository hummer98/nanobanana-adc (4 stars, last pushed 23d ago), licensed MIT. It adds 1,205 tokens to every session, about $0.0060 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).