boardstate AGENTS.md

Repository instructions and a tool guide for Boardstate, a system for building dashboards that AI agents can operate. It describes both dashboards created by agents and dashboards that use external MCP services.

In plain words
What is it for?
Use it to connect an AI client to Boardstate, build tabs and widgets, consume external MCP data, or develop the Boardstate packages.
Why use it?
It explains how to set up Boardstate, what its tools do, where state is stored, and how coding agents should work in the repository.

Instructions file for CodexOpenCode

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 instructions/100yenadmin/boardstate/agents-md
Clone the repo
git clone --depth 1 https://github.com/100yenadmin/boardstate

Made for: Codex, OpenCode.

Per session 2,557 This file is loaded in full into every session.
When invoked 2,557 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.02557 $0.02557
Opus 5 $0.01278 $0.01278
Sonnet 5 $0.00511 $0.00511
Haiku 4.5 $0.00256 $0.00256

Measured 2d ago against content hash 1c42d3ce4008, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

boardstate 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 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.

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 · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agents & Boardstate

Boardstate is agent-native in two directions:

Direction What it means Packages
Agents build the board Any AI composes tabs, widgets, bindings, and custom sandboxed widgets through the boardstate_* tool set @boardstate/mcp, @boardstate/agent
The board acts on the world The board consumes external MCP servers: their reads become live data, their mutations become operator-confirmed actions @boardstate/broker, @boardstate/server

This file covers how to set each surface up, the full tool catalog, the conventions that make agent-built boards good, and the rules for coding agents working on this repo.


1. Give any AI the board (@boardstate/mcp)

The MCP server exposes the complete dashboard tool set to any MCP client — Claude Desktop, Claude Code, or anything else that speaks MCP. State persists to $BOARDSTATE_STATE_DIR (default ~/.boardstate), so the same board is shared by the CLI, the MCP server, and any host you run.

Claude Code (one command):

claude mcp add boardstate -- npx -y @boardstate/mcp

Claude Desktop (claude_desktop_config.json):

{
  "mcpServers": {
    "boardstate": { "command": "npx", "args": ["-y", "@boardstate/mcp"] }
  }
}

Watch the board the agent is building — add --serve and open the printed page; it live-updates as tools land:

npx @boardstate/mcp --serve 4400

Inside MCP-Apps-capable clients, boardstate_board_view renders the live board directly in the conversation.

The tool catalog

Group Tools
Read & discover boardstate_workspace_get · boardstate_widget_catalog · boardstate_data_read · boardstate_board_view
Tabs boardstate_tab_create · boardstate_tab_update · boardstate_tab_delete · boardstate_tabs_reorder · boardstate_layout_set
Widgets boardstate_widget_add · boardstate_widget_update · boardstate_widget_move · boardstate_widget_remove
Custom widgets boardstate_widget_scaffold (sandboxed; lands as a pending card) · boardstate_widget_approve (operator surfaces only)
Whole-document boardstate_workspace_replace (full-document write, sanitized + capability-reconciled) · boardstate_undo
Quality boardstate_design_review (screenshot + critique the board you just built)
External tools boardstate_tool_search (SEARCH the connector catalog / REQUEST grants — see §3)
Errors boardstate_error (structured failure reporting)

Read the full file on GitHub · 187 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 · 187 lines · 2,557 tokens per session scan A 1c42d3ce4008

Subscribe to this mod's changes

boardstate AGENTS.md is an instructions file published in the GitHub repository 100yenadmin/boardstate (9 stars, last pushed 1mo ago), licensed MIT. It adds 2,557 tokens to every session, about $0.0128 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.