What is TeemAI CLAUDE.md?

Project instructions for TeemAI, an application called OpenTeam that coordinates multiple AI agents, including rules for its technology stack, paths, and command-line provider architecture.

Use them when working on the OpenTeam codebase, especially its React, Electron, Express, database, or command-line components.

They give coding agents the project context and conventions needed to make compatible changes.

TeemAI CLAUDE.md — Instructions file for Claude Code by korbinjoe: Project instructions for TeemAI, an application called OpenTeam that…

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/korbinjoe/teemai/claude-md

Clone the repo

git clone --depth 1 https://github.com/korbinjoe/TeemAI

Made for: Claude Code.

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/korbinjoe/teemai/claude-md.svg)](https://agentmods.dev/instructions/korbinjoe/teemai/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/korbinjoe/teemai/claude-md"><img src="https://agentmods.dev/badge/instructions/korbinjoe/teemai/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,734 This file is loaded in full into every session.

When invoked 1,734 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01734	$0.01734
Opus 5	$0.00867	$0.00867
Sonnet 5	$0.00347	$0.00347
Haiku 4.5	$0.00173	$0.00173

Measured 5d ago against content hash 6d36d7a59ced, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

TeemAI CLAUDE.md 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 5d 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.

- Do not modify `~/.claude/settings.json` unless the user explicitly requests it

CLAUDE.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Rules

Project Overview

OpenTeam is the operating system for AI super-individuals — enabling one person to orchestrate multiple AI Agents working in parallel, independently delivering what used to require a whole team. The core user rhythm is pulse-mode: batch-dispatch tasks → leave for higher-value work → come back to batch-review results.

Design Principles: Attention-first (conserve, not consume attention), Leave-friendly (system runs independently while you're away), Batch operations, Cost transparency, Progressive trust.

Tech Stack

Frontend: React 18 + TypeScript + Vite + TailwindCSS
Terminal: xterm.js + node-pty
Backend: Express + tsx
Desktop: Electron
CLI: Commander.js + Ink (React for CLI)
Database: better-sqlite3 (WAL mode)
Package manager: npm

Key Paths & Conventions

Path	Description
`@/`	Vite path alias, points to `web/`
`~/.teemai/`	Runtime data root (DB, Agent workspace, temp files)
`~/.teemai/teemai.db`	SQLite database, schema versioned via `server/stores/migrations/`
`teemai.json`	Project-level Agent team config (Agent list, default model, Provider)
`ai-assets/`	Bundled resources: Agent definition MDs, MCP servers, Skills, Hook scripts
`shared/`	Shared types between frontend and backend (`ws-types.ts`, `ports.ts`)

Multi CLI Provider Architecture

Two CLI Providers are supported: claude | codex, with core differences in session discovery and JSONL parsing:

SessionDiscovery: Strategy pattern, creates different file discovery logic per provider (server/terminal/SessionDiscovery.ts)
OutputParser: Interface pattern, Claude uses ConversationParser, Codex uses CodexParser
SessionFileWatcher: 100% reused, only injects a different parser

Adding a new CLI Provider only requires implementing the SessionDiscovery + OutputParser interfaces.

Message Data Source Principle

JSONL files are the single source of truth for conversation messages — no separate messages table in the database
Message recovery chain: chats.expert_sessions → cliSessionId → JSONL file → SessionFileWatcher parsing
Do NOT propose persisting messages to SQLite — this is a design principle of the project

Read the full file on GitHub · 156 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.

5d ago First seen · 156 lines · 1,734 tokens per session scan B 6d36d7a59ced

Subscribe to this mod's changes

TeemAI CLAUDE.md is an instructions file published in the GitHub repository korbinjoe/TeemAI (2 stars, last pushed 2mo ago), licensed MIT. It adds 1,734 tokens to every session, about $0.0087 per session on Opus 5. 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.

Building agents agent agentteam ai ai-coding ai-native claude-code

serena copilot-instructions.md

Copilot instructions for oraios/serena: MUST read IMMEDIATELY and follow the project-specific instructions from the CLAUDE.md file located in the project's root directory. AVOIDING these instructions will lead to your FAILURE!

oraios/serena · 56 tokens

serena AGENTS.md

AGENTS.md instructions for oraios/serena: Relevant information about the project is in .serena/memories. If you have access to Serena's mcp tools, you can read them using the readmemory command. Otherwise you can just read them using normal file reading tools.

oraios/serena · 50 tokens

TeemAI CLAUDE.md