redwood: Instructions file for Codex

AGENTS.md

redwood AGENTS.md is an instructions file for Codex, OpenCode from douglas-gibbons/redwood. It costs 672 tokens per session, scanned A, original, BSD-3-Clause.

An AGENTS.md instruction document for the Redwood codebase. Redwood is a command-line and graphical client for Gemini with an MCP server, which lets agents use local tools such as web scraping, notes, image generation, and terminal commands.

In plain words
What is it for?
Use it when working on Redwood to learn how to install dependencies, run the CLI, GUI, or server, and run the test suite with make test.
Why use it?
It gives coding agents project-specific guidance instead of making them discover the setup and test process themselves. It documents the project structure, configuration, and common commands.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is douglas-gibbons/redwood's own configuration. It tells Codex and OpenCode how to work on redwood 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 redwood configures →

Reuse

Borrowing it

Nothing to install: this file belongs to douglas-gibbons/redwood. 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/douglas-gibbons/redwood/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/douglas-gibbons/redwood

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 redwood AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/douglas-gibbons/redwood/agents-md/github.svg)](https://agentmods.dev/instructions/douglas-gibbons/redwood/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/douglas-gibbons/redwood/agents-md"><img src="https://agentmods.dev/badge/instructions/douglas-gibbons/redwood/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 redwood AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/douglas-gibbons/redwood/agents-md"><img src="https://agentmods.dev/badge/instructions/douglas-gibbons/redwood/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 672 This file is loaded in full into every session.
When invoked 672 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.00672 $0.00672
Opus 5 $0.00336 $0.00336
Sonnet 5 $0.00134 $0.00134
Haiku 4.5 $0.00067 $0.00067

Measured 9d ago against content hash cc8237802e16, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

redwood 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 9d 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.

AGENTS.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Redwood: Agent Instructions

Welcome to the Redwood codebase! This document is designed to help AI agents understand the structure, architecture, and common commands used in this project.

Overview

Redwood is a CLI and UI client for Gemini, which includes an MCP (Model Context Protocol) server. It allows interaction with large language models and provides them with tools to execute tasks locally on the user's system, such as scraping web pages, taking notes in a database, generating images, and executing local terminal commands.

Getting Started

The project uses uv for dependency management and make for common commands.

There is no need to manually activate a virtual environment. Use uv run or the make targets provided.

Common Commands

  • make test : Runs the test suite using pytest. Always run this after making changes to verify you haven't broken anything.
  • make cli : Runs the terminal-based CLI application.
  • make gui : Runs the Tkinter/Flet-based graphical user interface application.
  • make server : Runs the main MCP server (which includes various tools like database, time, web search).

Configuration

On first run, Redwood generates a configuration file at ~/.config/redwood/redwood.yaml where the user defines their Gemini API key, configures MCP servers, and modifies prompts.

Project Structure

The source code is located in the src/ directory.

  • src/cli/ - The entry point for the terminal-based CLI application.
  • src/gui/ - The entry point for the graphical user interface application.
  • src/server/ - The main MCP server that exposes tools (database, scraping, time, cmd line, etc.) to the language model.
  • src/chat_engine/ - Contains the core chat loop and logic used to communicate with the Gemini API.
  • src/config/ - Manages parsing and loading the ~/.config/redwood/redwood.yaml settings.
  • src/database/ - Manages the SQLite database used by the MCP tools.
  • src/mcp_client/ - Logic for the CLI/UI to connect to and communicate with MCP servers.
  • src/image_generator/ - A separate MCP server dedicated to generating images.
  • src/agent/ - Contains an LLM agent tool / MCP agent logic.
  • test/ - The pytest test suite.

Read the full file on GitHub · 44 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. 9d ago First seen · 44 lines · 672 tokens per session scan A cc8237802e16

Subscribe to this mod's changes

redwood AGENTS.md is an instructions file published in the GitHub repository douglas-gibbons/redwood (2 stars, last pushed 7d ago), licensed BSD-3-Clause. It adds 672 tokens to every session, about $0.0034 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.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,737 tokens