mindmap-mcp: Instructions file for Codex

AGENTS.md

mindmap-mcp AGENTS.md is an instructions file for Codex, OpenCode from EwigMidori/mindmap-mcp. It costs 232 tokens per session, scanned A, original, MIT.

Project instructions for mindmap-mcp, a browser-based mind-map application with a local TypeScript server. MCP lets an AI agent control the application, and each browser tab or connection can have its own document session.

In plain words
What is it for?
Starting and operating the browser mind-map server, choosing the correct session, and using its REST, WebSocket, and MCP endpoints. They also cover development commands and support for Windows and Unix systems.
Why use it?
They help an agent work with the project without assuming there is one shared mind map or requiring a desktop application. They also describe how to start, build, check, and connect to the service.

Instructions file for CodexOpenCode

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

This is EwigMidori/mindmap-mcp's own configuration. It tells Codex and OpenCode how to work on mindmap-mcp 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 mindmap-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to EwigMidori/mindmap-mcp. 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/EwigMidori/mindmap-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/EwigMidori/mindmap-mcp

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 mindmap-mcp AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ewigmidori/mindmap-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/ewigmidori/mindmap-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 232 This file is loaded in full into every session.
When invoked 232 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 $0.00232 $0.00232
Opus 5.5 $0.00093 $0.00093
Sonnet 5.5 $0.00046 $0.00046
Haiku 4.5 $0.00023 $0.00023

Measured 2mo ago against content hash 2561976c4956, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mindmap-mcp 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 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.

AGENTS.md · 10 lines

What it actually says

mindmap-mcp

  • Browser + TS server, no Tauri/Rust. Control plane is only server/ (REST + WS + MCP). SessionHub multi-session: one document per browser tab; each MCP connection defaults to its own session (mindmap_use_session to attach to a tab).
  • Default port 17381: / UI · /mcp · /health · /v1/* · /ws?session=
  • WorkBuddy / non-technical users: AI runs scripts/ensure-running.ps1 (Windows) or scripts/ensure-running.sh (Unix) + write-MCP scripts — do not dump terminal steps on the user.
  • Skill: skills/mindmap-mcp/SKILL.md
  • Scripts: pnpm dev · pnpm build · pnpm start · pnpm typecheck
  • CLI: bin/mindmap-mcp.mjs → production bundle + UI
  • Public repo: https://github.com/EwigMidori/mindmap-mcp · License MIT
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. 2mo ago First seen · 10 lines · 232 tokens per session scan A 2561976c4956

Subscribe to this mod's changes

mindmap-mcp AGENTS.md is an instructions file published in the GitHub repository EwigMidori/mindmap-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 232 tokens to every session, about $0.0009 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.

Related

mindmap-mcp AGENTS.md compared with instructions from other repositories

mindmap-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mindmap-mcp AGENTS.mdEwigMidori/mindmap-mcpInstructions file02mo agoMITA232Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode