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 agentmods add instructions/danjam/mcp-gemini/claude-mdgit clone --depth 1 https://github.com/danjam/mcp-geminiWrote 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/danjam/mcp-gemini/claude-md)<a href="https://agentmods.dev/instructions/danjam/mcp-gemini/claude-md"><img src="https://agentmods.dev/badge/instructions/danjam/mcp-gemini/claude-md.svg" alt="Measured on agentmods" 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 | $0.00911 | $0.00911 |
| Opus 5 | $0.00456 | $0.00456 |
| Sonnet 5 | $0.00182 | $0.00182 |
| Haiku 4.5 | $0.00091 | $0.00091 |
Grade A, and why
mcp-gemini 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 4d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Build and Run
npm install # Install dependencies
npm run build # Compile TypeScript (tsc)
npm start # Run server (node dist/index.js)
Unit tests via node:test (built-in), linting via Biome:
npm test # Build + run tests
npm run test:only # Run tests without rebuilding
npm run lint # Check for issues
npm run lint:fix # Auto-fix issues
Environment
Requires GEMINI_API_KEY env var.
Optional: GEMINI_DEFAULT_MODEL overrides the default model (falls back to gemini-flash-latest).
Manual Testing
Pipe JSON-RPC messages to stdin:
printf '{"jsonrpc":"2.0","id":1,"method":"initialize"}\n{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"generate_text","arguments":{"prompt":"Say hello"}}}\n' | GEMINI_API_KEY=your-key node dist/index.js
Architecture
This is a Model Context Protocol (MCP) server that wraps Google Gemini's API. It communicates over stdin/stdout using JSON-RPC 2.0 — there is no HTTP server.
Source files:
src/index.ts— Entrypoint: I/O helpers (send,reply,textReply,errorReply,error), request dispatch, readline listenersrc/handlers.ts—createHandlers()factory returning a handler map; individual tool handler functionssrc/tools.ts— Tool schema definitions (static JSON Schema data for MCPtools/list)src/conversations.ts— Conversation store with TTL pruning (30min expiry, max 100 conversations)src/models.ts— Model lists, defaults,GEMINI_DEFAULT_MODELenv var overridesrc/types.ts— All type definitions:RequestId,ToolName,ToolResult,ToolHandler, tool arg interfaces, MCP interfaces (MCPToolAnnotations,MCPToolDefinition,MCPRequest,MCPResponse)
Request flow: stdin line → JSON parse → handleRequest dispatches by MCP method (initialize, tools/list, tools/call) → handleToolCall looks up handler in map → handler returns ToolResult → dispatch maps result to JSON-RPC response on stdout.
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.
- 4d ago First seen · 72 lines · 911 tokens per session scan A 48a7f19e4310
mcp-gemini CLAUDE.md is an instructions file published in the GitHub repository danjam/mcp-gemini (1 stars, last pushed 5mo ago), licensed MIT. It adds 911 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
AionUi AGENTS.md
AGENTS.md instructions for iOfficeAI/AionUi, covering aionui - project guide, code conventions, file & directory structure, naming and ui library & icons.
ClawRouter CLAUDE.md
Claude Code instructions for BlockRunAI/ClawRouter, covering clawrouter, commands, project structure, key dependencies and conventions.
botmux CLAUDE.md
Claude Code instructions for deepcoldy/botmux, covering botmux, 构建 & 运行, bun 开发链路, worktree 的 nodemodules:共享还是独立(改前必读) and 编译态(单文件二进制)注意.
codedb AGENTS.md
AGENTS.md instructions for justrach/codedb, covering codedb agent guidelines, what codedb is (and isn't), review guidelines, pre-merge verification and security-sensitive areas.
SearChat CLAUDE.md
Claude Code instructions for yokingma/SearChat, covering claude.md, project overview, architecture, monorepo structure and key technologies.
happier CLAUDE.md
Claude Code instructions for happier-dev/happier, covering claude code and typescript commands.