Borrowing it
Nothing to install: this file belongs to hampsterx/gemini-mcp-bridge. 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/hampsterx/gemini-mcp-bridge/master/AGENTS.mdgit clone --depth 1 https://github.com/hampsterx/gemini-mcp-bridgeWrote 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/hampsterx/gemini-mcp-bridge/agents-md)<a href="https://agentmods.dev/instructions/hampsterx/gemini-mcp-bridge/agents-md"><img src="https://agentmods.dev/badge/instructions/hampsterx/gemini-mcp-bridge/agents-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 5.1 | $0.02211 | $0.02211 |
| Opus 5 | $0.01105 | $0.01105 |
| Sonnet 5 | $0.00442 | $0.00442 |
| Haiku 4.5 | $0.00221 | $0.00221 |
Grade A, and why
gemini-mcp-bridge AGENTS.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 7d 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - gemini-mcp-bridge
Guidance for AI coding agents working in the gemini-mcp-bridge repository.
Project Overview
Open source MCP server that wraps Gemini CLI as a subprocess, exposing its best features as MCP tools. Works with any MCP-compatible client: Claude Code, Codex CLI, Cursor, Windsurf, VS Code.
- npm package:
gemini-mcp-bridge - License: MIT
- Language: TypeScript
- Framework:
@modelcontextprotocol/sdk
See README § Latency expectations before changing timeout defaults or adding new tools. The hard timeout cap is defined in src/utils/limits.ts and imported by both spawn.ts and retry.ts.
Architecture
MCP Client --stdio--> gemini-mcp-bridge --spawn--> gemini CLI subprocess
We assemble prompts in TypeScript and spawn the CLI. The search, structured, and query (change-mode path) tools load prompt templates from prompts/*.md via src/utils/prompts.ts and fill placeholders; the CLI then runs in agentic mode inside the target repo, using its built-in tools (read_file, grep_search, list_directory, google_web_search) to explore surrounding code or the web for context.
Tools
| Tool | Purpose | Default Timeout |
|---|---|---|
query |
Agentic query with read-only repo exploration | 120s |
search |
Google Search grounded query via google_web_search |
120s |
structured |
JSON Schema validated output | 120s |
ping |
Health check + CLI capability detection | 10s |
fetch-chunk |
Retrieve cached follow-up chunks from oversized responses | N/A (<1s) |
Query Tool Details
Text queries run under --approval-mode plan (read-only agentic). Files are passed as @{path} hints, Gemini reads them with its own tools and can explore surrounding code. Image files (png, jpg, jpeg, gif, webp, bmp) trigger --yolo mode for native pixel access. Gitignored files cannot be read in plan mode.
Search Tool Details
Spawns CLI in agentic mode with access to google_web_search. Uses a prompt template (prompts/search.md) that instructs Gemini to search, synthesize, and cite sources.
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.
- 7d ago First seen · 174 lines · 2,211 tokens per session scan A 9ec458398d7d
gemini-mcp-bridge AGENTS.md is an instructions file published in the GitHub repository hampsterx/gemini-mcp-bridge (6 stars, last pushed 3mo ago), licensed MIT. It adds 2,211 tokens to every session, about $0.0111 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
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).
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.
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).
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.