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 agents/jazzmind/busibox/02-architecturegit clone --depth 1 https://github.com/jazzmind/busiboxWrote 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.
[](https://agentmods.dev/agents/jazzmind/busibox/02-architecture)<a href="https://agentmods.dev/agents/jazzmind/busibox/02-architecture"><img src="https://agentmods.dev/badge/agents/jazzmind/busibox/02-architecture.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00016 | $0.05519 |
| Opus 5 | $0.00008 | $0.02759 |
| Sonnet 5 | $0.00003 | $0.01104 |
| Haiku 4.5 | $0.00002 | $0.00552 |
Grade A, and why
02-architecture 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 4d 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 — 807 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Server Architecture
Overview
The agent server is a Python/FastAPI application that provides AI agent execution, tool orchestration, workflow management, and intelligent query routing. It uses Pydantic AI for agent management and integrates with LiteLLM for LLM access.
System Architecture
┌─────────────────────────────────────────────────────────────┐
│ Agent Client (Next.js) │
│ Browser / React UI │
└────────────────────────┬────────────────────────────────────┘
│ HTTP/REST + SSE
▼
┌─────────────────────────────────────────────────────────────┐
│ Agent Server (FastAPI) │
│ ┌──────────────────────────────────────────────────────┐ │
│ │ API Layer (FastAPI) │ │
│ │ /runs, /agents, /dispatcher, /workflows, /scores │ │
│ └──────────────────────────────────────────────────────┘ │
│ ┌──────────────────────────────────────────────────────┐ │
│ │ Service Layer │ │
│ │ RunService, AgentRegistry, DispatcherService, │ │
│ │ TokenService, Scheduler, ScorerService │ │
│ └──────────────────────────────────────────────────────┘ │
│ ┌──────────────────────────────────────────────────────┐ │
│ │ Agent Layer (Pydantic AI) │ │
│ │ chat_agent, rag_agent, search_agent, dispatcher │ │
│ └──────────────────────────────────────────────────────┘ │
│ ┌──────────────────────────────────────────────────────┐ │
│ │ Tool Layer │ │
│ │ search_tool, ingest_tool, rag_tool, weather_tool │ │
│ └──────────────────────────────────────────────────────┘ │
└────────────────────────┬────────────────────────────────────┘
│
┌───────────────┼───────────────┐
│ │ │
▼ ▼ ▼
┌─────────────┐ ┌─────────────┐ ┌─────────────┐
│ PostgreSQL │ │ LiteLLM │ │ Redis │
│ (pg-lxc) │ │(litellm-lxc)│ │(data-lxc) │
└─────────────┘ └─────────────┘ └─────────────┘
│
▼
┌─────────────┐
│ Local LLMs │
│ (qwen3-30b) │
└─────────────┘
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.
- 4d ago First seen · 807 lines · 16 tokens per session scan A 02db58881d28
02-architecture is an agent published in the GitHub repository jazzmind/busibox (7 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 5,519 once invoked, about $0.0001 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 agents, from other repositories
reviewer
Code review agent - critically reviews changes for quality, security, and correctness.
dev
TDD Developer agent - implements features using test-driven development and clean code principles.
test-doc
Use this agent when the user needs markdown files created in the test-files/ directory. This includes generating test data files, sample documentation, mock content, or any markdown-formatted files for testing purposes.\n\nExamples:\n\n \nContext: User needs sample markdown files for testing a documentation…
dev
开发者（Developer）角色：负责代码实现、PR 创建与迭代、代码审查响应、 技术方案设计。监听 issues.assigned 事件，自动接收被指派的开发任务。.
timps_boilerplate_architect
Scaffold a new project: folder structure, stub files, setup commands. Supports any language or framework — describe what you're building. Use the timpsboilerplatearchitect MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
timps_content_multiplier
Transform a long-form technical post into multiple short-form formats: tweet thread, LinkedIn post, changelog entry, docs blurb, and HN title. Use the timpscontentmultiplier MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.