Borrowing it
Nothing to install: this file belongs to kevinkiklee/gemini-nano-banana-mcp. 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/kevinkiklee/gemini-nano-banana-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/kevinkiklee/gemini-nano-banana-mcpWrote 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/kevinkiklee/gemini-nano-banana-mcp/claude-md)<a href="https://agentmods.dev/instructions/kevinkiklee/gemini-nano-banana-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/kevinkiklee/gemini-nano-banana-mcp/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/kevinkiklee/gemini-nano-banana-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/kevinkiklee/gemini-nano-banana-mcp/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 | $0.00922 | $0.00922 |
| Opus 5 | $0.00461 | $0.00461 |
| Sonnet 5 | $0.00184 | $0.00184 |
| Haiku 4.5 | $0.00092 | $0.00092 |
Grade A, and why
gemini-nano-banana-mcp 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gemini-nano-banana-mcp
Global MCP server for image generation using Google Gemini Nano Banana models.
Commands
pnpm build— Compile TypeScript to dist/pnpm dev— Run stdio transport directly with tsx (development)pnpm dev:http— Run HTTP transport directly with tsx (development)pnpm serve— Run HTTP transport from compiled dist/ (production)pnpm test— Run tests with Vitestpnpm test:watch— Run tests in watch mode
Conventions
- All source files must be under 150 lines. If a file approaches the limit, split it into focused modules.
Architecture
Shared libraries in src/, server entry points in src/server/:
src/utils.ts— File/path utilities (slugify, sanitize, expand, unique filepath)src/secret-patterns.ts—SECRET_PATTERNSconstant (~28 regexes)src/security.ts—scanForSecrets,RateLimiterclasssrc/sanitize.ts—quarantineModelText(untrusted model output) andsafeErrorMessage(error-message allowlist for MCP tool output)src/gemini.ts— MODEL_MAP, MODEL_KEYS, callGemini wrapper, lazy client singleton, resetClientsrc/gemini-retry.ts— isTransientError, isOverloaded, backoffDelayMs, MAX_ATTEMPTS (retry primitives)src/gemini-types.ts— Gemini API type definitions (options, result, response shapes, GeminiClient)src/server/server.ts—log(), Zod schema, ToolResult type,createMcpServer()factorysrc/server/handler.ts—handleGenerateImage()pure tool handlersrc/server/index.ts— Stdio entry point (local / Claude Code)src/server/http.ts— HTTP server setup, auth gate (timing-safe), main entrysrc/server/http-routes.ts— MCP POST/GET/DELETE route handlerssrc/server/http-helpers.ts— Session registry (with TTL), readBody (1MB limit), json helpersrc/server/lifecycle.ts— Session reaper, graceful shutdown
Tests are colocated per module: utils.test.ts, security.test.ts, sanitize.test.ts, gemini.test.ts, server/server.test.ts, server/http.test.ts.
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 · 65 lines · 922 tokens per session scan A ce735c154cd8
gemini-nano-banana-mcp CLAUDE.md is an instructions file published in the GitHub repository kevinkiklee/gemini-nano-banana-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 922 tokens to every session, about $0.0046 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
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.
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).
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).