gemini-researcher-mcp: Instructions file for Codex

AGENTS.md

gemini-researcher-mcp AGENTS.md is an instructions file for Codex, OpenCode from capyBearista/gemini-researcher-mcp. It costs 1,182 tokens per session, scanned C, original, MPL-2.0.

Development instructions for Gemini Researcher, a Node.js and TypeScript MCP server that proxies requests to the Gemini command-line tool and returns chunked JSON.

In plain words
What is it for?
Developing this MCP server while following its testing, validation, runtime-contract, and code-quality rules.
Why use it?
They set required checks and boundaries, such as strict TypeScript, tests, linting, and keeping secrets out of commits.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md; mentions Gemini CLI.

This is capyBearista/gemini-researcher-mcp's own configuration. It tells Codex and OpenCode how to work on gemini-researcher-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything gemini-researcher-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to capyBearista/gemini-researcher-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.

Copy the file
curl -O https://raw.githubusercontent.com/capyBearista/gemini-researcher-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/capyBearista/gemini-researcher-mcp

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for gemini-researcher-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/capybearista/gemini-researcher-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/capybearista/gemini-researcher-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/capybearista/gemini-researcher-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/capybearista/gemini-researcher-mcp/agents-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.

agentmods 80×15 button for gemini-researcher-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/capybearista/gemini-researcher-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/capybearista/gemini-researcher-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,182 This file is loaded in full into every session.
When invoked 1,182 The same file — it is already loaded in full.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01182 $0.01182
Opus 5 $0.00591 $0.00591
Sonnet 5 $0.00236 $0.00236
Haiku 4.5 $0.00118 $0.00118

Measured 10d ago against content hash bd741b9c1bc0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

gemini-researcher-mcp AGENTS.md scanned grade C with 1 finding 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 10d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- Confirm before: git force push, rm -rf
AGENTS.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gemini Researcher

Overview

  • Type: Standard project (Node.js MCP Server)
  • Stack: Node.js (>=18), TypeScript, Zod, @modelcontextprotocol/sdk
  • Architecture: Stateless proxy to Gemini CLI returning chunked JSON
  • Team Size: Open Source (Single author focus)

This AGENTS.md is the authoritative source for development guidelines. Subdirectories contain specialized AGENTS.md files that extend these rules.

Universal Development Rules

Code Quality (MUST)

  • MUST write TypeScript in strict mode
  • MUST include tests for all new features
  • MUST run npm run lint and npm test before committing
  • MUST NOT commit secrets, API keys, or tokens (especially GEMINI_API_KEY)
  • MUST respect the runtime contract defined in docs/runtime-contract.md

Best Practices (SHOULD)

  • SHOULD prefer pure functions and immutable state
  • SHOULD use descriptive variable names
  • SHOULD extract complex logic into separate utility functions in src/utils
  • SHOULD ensure all MCP tool schemas use Zod for validation

Anti-Patterns (MUST NOT)

  • MUST NOT use any type without explicit justification
  • MUST NOT bypass TypeScript errors with @ts-ignore
  • MUST NOT push directly to main branch
  • MUST NOT mutate global state or modify files (server must remain read-only)

Core Commands

Development

  • npm run build - Build the project (tsc)
  • npm run dev - Watch mode for TypeScript
  • npm start - Run the built application
  • npm run lint - Type-check the codebase (tsc --noEmit)
  • npm test - Run all tests
  • npm run test:unit - Run only unit tests
  • npm run test:integration - Run only integration tests
  • npm run test:smoke:live - Run live e2e smoke tests (requires authentication)

Quality Gates (run before PR)

npm run lint && npm test

Project Structure

Applications

  • src/ → Core server logic (see src/AGENTS.md)
    • Tools: src/tools/ → MCP Tool implementations
    • Utilities: src/utils/ → Helpers (caching, chunking, parsing)
    • Setup: src/setup/ → CLI init wizard

Read the full file on GitHub · 139 lines

Changes

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.

  1. 10d ago First seen · 139 lines · 1,182 tokens per session scan C bd741b9c1bc0

Subscribe to this mod's changes

gemini-researcher-mcp AGENTS.md is an instructions file published in the GitHub repository capyBearista/gemini-researcher-mcp (0 stars, last pushed 3mo ago), licensed MPL-2.0. It adds 1,182 tokens to every session, about $0.0059 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories