codex

An integration guide for connecting OpenAI coding agents and models to OpenBoard, a local dashboard and server, through MCP over standard input and output. It covers Codex CLI, the OpenAI Agents SDK, and custom wrappers.

In plain words
What is it for?
Use it to configure OpenBoard in Codex CLI or an OpenAI Agents SDK project, start the server, connect through TypeScript, and verify the available tools.
Why use it?
It provides the exact installation, configuration, and verification details needed for an OpenAI-based agent to discover and use OpenBoard tools.

Agent

Install

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.

agentmods
npx agentmods add agents/atpaawej/openboard/codex
Clone the repo
git clone --depth 1 https://github.com/atpaawej/openboard
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 592 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
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 $0.00000 $0.00592
Opus 5 $0.00000 $0.00296
Sonnet 5 $0.00000 $0.00118
Haiku 4.5 $0.00000 $0.00059

Measured 2d ago against content hash e579a4d8e9ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

codex scanned grade B 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 2d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

### Configuration File (`~/.codex/config.toml`)
docs/agents/codex.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenAI Codex / Agents SDK Integration Guide

OpenAI models and coding agents (via OpenAI Agents SDK, Codex CLI, or custom MCP wrappers) connect to OpenBoard through the standard stdio transport.


1. Installation

Install OpenBoard globally via npm:

npm install -g openboard

2. OpenBoard Startup

Start the local OpenBoard web dashboard and server:

openboard start

For AI agent operations via MCP, the agent runner executes openboard mcp directly over stdio.


3. MCP Configuration

Configuration File (~/.codex/config.toml)

If using Codex CLI or configured OpenAI agents, define the server under mcp_servers:

[mcp_servers.openboard]
command = "openboard"
args = ["mcp"]

Programmatic SDK Integration (TypeScript / Node.js)

When integrating OpenBoard programmatically into OpenAI Agent SDK workflows:

import { StdioServerParameters } from '@modelcontextprotocol/sdk/client/stdio.js';

const openboardServer: StdioServerParameters = {
  command: 'openboard',
  args: ['mcp'],
};

4. Verification

Verify the MCP connection programmatically or via CLI:

openboard info

Confirm that the agent runner detects the 13 exposed tools (list_boards, create_board, create_shapes, etc.).


5. Example Workflows & Prompts

Multi-Step Data Ingestion Pipeline Workflow

User:
List my OpenBoard boards.

Agent:
[Calls list_boards]
Found 1 board: "Untitled Board".

User:
Create a board called "Data Ingestion Pipeline".

Agent:
[Calls create_board with { name: "Data Ingestion Pipeline" }]
Created board (ID: "board_pipe_01").

User:
Draw an ingestion pipeline with arrows pointing from Source -> Queue -> Worker -> Postgres.

Agent:
[Calls create_shapes on "board_pipe_01" with 4 components and 3 connecting arrows]
Successfully drawn: Source, Queue, Worker, and Postgres connected in order.

User:
Inspect the canvas and take a screenshot to verify arrow bindings.

Agent:
[Calls get_canvas_state and get_canvas_screenshot]
Verified 4 nodes and 3 arrow bindings. SVG screenshot captured.

Read the full file on GitHub · 109 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. 2d ago First seen · 109 lines · 0 tokens per session scan B e579a4d8e9ec

Subscribe to this mod's changes

codex is an agent published in the GitHub repository atpaawej/openboard (3 stars, last pushed 15d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 592 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

sverklo-explore

Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…

sverklo/sverklo · 96 tokens

brain-os-mode

Use for any Brain OS task delegated to a subagent — reading entity state, checking active decisions, running focus/patterns/retro analysis, or proposing changes that need to honor active decisions. Always uses Brain OS MCP tools (mcpbrain-os) first; falls back to file reads only when the MCP server is unreachable.…

brainOS-HQ/brain-os · 97 tokens

engineer

Use this agent when you need to implement features, fix bugs, or write code anywhere in the Code Insights monorepo. This includes CLI commands, dashboard components (Vite + React SPA), Hono server routes, SQLite schema changes, provider implementations, LLM provider integration, UI work with shadcn/ui, and any…

melagiri/code-insights · 307 tokens

technical-architect

Use this agent for architectural decisions, type alignment, SQLite schema changes, code review synthesis, and when the implementation path requires architectural guidance. This agent serves as the technical authority across the Code Insights monorepo. Examples: Context: A change to types needs to be reflected in the…

melagiri/code-insights · 237 tokens

product-manager

Use this agent for product development coordination, tracking tasks (GitHub Issues or local markdown), sprint planning, progress reporting, and development ceremony management. This PM does NOT use Jira.

melagiri/code-insights · 39 tokens

devtools-cofounder

Use this agent for strategic product decisions, competitive positioning, developer experience critique, go-to-market strategy, and feature viability assessment. Peer to technical-architect — brings market lens where TA brings system lens. Does NOT write code or create PRs. Advisory only — delegates implementation to…

melagiri/code-insights · 379 tokens