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.
npx agentmods add instructions/100yenadmin/boardstate/agents-mdgit clone --depth 1 https://github.com/100yenadmin/boardstateWhat 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 | $0.02557 | $0.02557 |
| Opus 5 | $0.01278 | $0.01278 |
| Sonnet 5 | $0.00511 | $0.00511 |
| Haiku 4.5 | $0.00256 | $0.00256 |
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.
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) |
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.
- 2d ago First seen · 187 lines · 2,557 tokens per session scan A 1c42d3ce4008
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.
Other instructions, from other repositories
Surface AGENTS.md
Instructions for Aaryan-Kapoor/Surface, covering surface, stack, commands, architecture and agent contract.
switchboard-mcp CLAUDE.md
Claude Code instructions for rodcoppi/switchboard-mcp, covering claude.md, what this repository is, executor rules (from the prd, mandatory), locked stack and commands.
Roadboard AGENTS.md
Instructions for Maless88/Roadboard, covering codex / chatgpt analyst startup, analyst review protocol, output review protocol (the result-side gate) and what the analyst does not do.
printyourduck-mcp AGENTS.md
AGENTS.md instructions for printyourduck/printyourduck-mcp, covering agent guide, product boundary, commands, repo ownership and release truth.
Roadboard CLAUDE.md
Instructions for Maless88/Roadboard, covering claude.md, master protocol, 1. coding rules & communication, 2. project lifecycle & git and 3. mcp operational protocols (auto-onboarding).
mcpqueen AGENTS.md
AGENTS.md instructions for mcpqueen/mcpqueen, covering mcp queen repository instructions, product integrity, working tree, routine autonomous work and manual gates.