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/antiv/mate/claude-mdgit clone --depth 1 https://github.com/antiv/mateWhat 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 | $0.02152 | $0.02152 |
| Opus 5 | $0.01076 | $0.01076 |
| Sonnet 5 | $0.00430 | $0.00430 |
| Haiku 4.5 | $0.00215 | $0.00215 |
Grade A, and why
mate CLAUDE.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 3d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
MATE (Multi-Agent Tree Engine) is a production-ready web platform built on top of Google ADK that adds database-driven agent management, multi-LLM support, RBAC, MCP integration, token tracking, guardrails, and a dashboard UI.
Running the Application
# Setup
python -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt
cp .env.example .env # Set GOOGLE_API_KEY or other LLM provider key
# Run (auto-applies DB migrations, default SQLite)
python auth_server.py
# Dashboard: http://localhost:8000 (default login: admin/mate)
# Docker alternative
docker-compose up
Two servers run: Auth Server (port 8000, FastAPI with HTTP Basic Auth) proxies authenticated requests to the Agent Server (port 8001). The agent server framework is selectable via AGENT_FRAMEWORK: adk (Google ADK runtime, adk_main.py, default) or langgraph (LangGraph runtime, langgraph_main.py, emulates ADK's HTTP/SSE wire contract — see documents/LANGGRAPH_RUNTIME.md).
Testing
# All tests
python -m unittest discover -s shared/test -p "test_*.py" -v
# Single test file
python -m unittest shared.test.test_agent_manager_simple -v
# With coverage
coverage run -m unittest discover -s shared/test -p "test_*.py"
coverage report
Tests live in shared/test/ — 506 tests covering agent management, tool factory, model switching, RBAC, authorization, migrations, guardrails, tracing, and more.
Database Migrations
python shared/migrate.py run # Apply pending migrations
python shared/migrate.py status # Check migration status
python shared/migrate.py create # Create new migration
python shared/migrate.py rollback # Roll back last migration
Migrations auto-apply on server startup. Per-database migration files are in shared/sql/migrations/{postgresql,mysql,sqlite}/.
Architecture
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.
- 3d ago First seen · 182 lines · 2,152 tokens per session scan A e56a3294b95a
mate CLAUDE.md is an instructions file published in the GitHub repository antiv/mate (88 stars, last pushed 4d ago), licensed Apache-2.0. It adds 2,152 tokens to every session, about $0.0108 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 2026-08-30.
Other instructions, from other repositories
codex-lb AGENTS.md
AGENTS.md instructions for Soju06/codex-lb, covering agents, environment, code conventions, workflow (openspec-first) and how to work (default).
openclaw-command-center AGENTS.md
Instructions for jontsai/openclaw-command-center, covering agents.md — ai workspace guide, ⚠️ critical: pull request workflow, 🎯 mission, 🏛️ architecture and 📁 workspace structure.
AI-company CLAUDE.md
Instructions for CronusL-1141/AI-company, covering ai team os, 核心约束, leader核心行为, 多会话并行纪律(2026-07-10 事故后立规) and 刻意决策 — 禁止悄悄回退.
hybro AGENTS.md
Instructions for hybroai/hybro, covering repository guidelines, scope, project structure & module organization, build, test, and development commands and coding style & naming conventions.
claw-pilot CLAUDE.md
Instructions for swoelffel/claw-pilot, covering claude.md, what this project is, tech stack, language standard and contribution workflow.
codex-lb CLAUDE.md
Claude Code instructions for Soju06/codex-lb, a project described as: Codex/ChatGPT multiple account load balancer & proxy with usage tracking, dashboard, and OpenCode-compatible endpoints.