What is codex copilot-instructions.md?

A project guide for AI coding agents working on Codex, a TypeScript application with a web client, server, and Model Context Protocol (MCP) interface.

Understanding the codebase, using its MCP server, running critical commands, and deploying the application with Docker.

It gives agents the project structure, important commands, data flow, security details, and deployment instructions so they can make informed changes.

How bocan/codex configures GitHub Copilot

Reuse

Borrowing it

Nothing to install: this file belongs to bocan/codex. 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/bocan/codex/main/.github/copilot-instructions.md

Clone the repo

git clone --depth 1 https://github.com/bocan/codex

Made for: GitHub Copilot.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/bocan/codex/copilot-instructions/github.svg)](https://agentmods.dev/instructions/bocan/codex/copilot-instructions)

Your own site

<a href="https://agentmods.dev/instructions/bocan/codex/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/bocan/codex/copilot-instructions/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/bocan/codex/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/bocan/codex/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,462 This file is loaded in full into every session.

When invoked 2,462 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.

Model	Per session	Once invoked
Fable 5.1	$0.02462	$0.02462
Opus 5.5	$0.00985	$0.00985
Sonnet 5.5	$0.00492	$0.00492
Haiku 4.5	$0.00246	$0.00246

Measured 2mo ago against content hash a8de4e22b7f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

codex copilot-instructions.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 2mo 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.

.github/copilot-instructions.md · 220 lines

How it starts

The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex - AI Coding Instructions

Architecture Overview

Codex is a full-stack TypeScript monorepo using npm workspaces with three packages:

Root (/) - Workspace orchestration, shared devDependencies
Server (/server) - Express REST API on port 3001 + MCP server on port 3002
Client (/client) - React SPA on port 3000 (Vite dev server proxies /api to server)

Data flow: React components → api.ts service → Express routes → FileSystemService → /data directory (markdown files).

MCP flow: AI agents → MCP server (port 3002) → MCP tools → FileSystemService → /data directory.

Production mode: Express serves both API and static React build from port 3001 only (see server/src/index.ts static file serving section).

MCP Server Architecture

The Model Context Protocol (MCP) server allows AI agents to interact with Codex programmatically:

Location: server/src/mcp/ - Separate from REST API
Port: 3002 (configurable via MCP_PORT)
Protocol: HTTP-based MCP with session management
Tools: 16 registered tools (pages, folders, attachments)
Resources: Access pages via codex://page/{path} URIs
Security: API key authentication via MCP_API_KEY environment variable

Tool registration pattern: All tools imported in server/src/mcp/tools/registry.ts and wrapped with asRegisteredTool(). Each tool uses Zod schemas for input validation and returns structured ToolResult objects.

Critical Commands

make dev          # Start both server (3001) and client (3000)
make test         # Run all tests (server: Jest, client: Vitest)
make install      # Fresh install all dependencies from root
make build        # Build both server and client for production

MCP Development:

MCP_ENABLED=true npm run dev -w server    # Start server with MCP on port 3002
npm run dev:mcp -w server                 # Dedicated MCP dev script

Important: Dependencies install at the root level only. Run npm ci or make install from root, not from subdirectories. The root package-lock.json manages all workspace dependencies.

Read the full file on GitHub · 220 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.

2mo ago First seen · 220 lines · 2,462 tokens per session scan A a8de4e22b7f3

Subscribe to this mod's changes

codex copilot-instructions.md is an instructions file published in the GitHub repository bocan/codex (9 stars, last pushed 2d ago), licensed MIT. It adds 2,462 tokens to every session, about $0.0098 per session on Opus 5.5. 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.

Building agents React document-store markdown mcp mcp-server wiki

codex copilot-instructions.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
codex copilot-instructions.mdbocan/codex	Instructions file	9	2d ago	MIT	A	2,462	GitHub Copilot
md-feedback copilot-instructions.mdyeominux/md-feedback	Instructions file	5	7mo ago	none	A	309	GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot

codex: Instructions file for GitHub Copilot