What is document_agent?

A minimal example of an AI agent project using aworld-cli, a command-line tool for listing agents and running tasks. It shows both Python and Markdown ways to define an agent.

Use it to create a basic agent, register it in a swarm, list available agents, run a task, or learn the project’s multi-agent and human-review examples.

It gives developers a small starting structure instead of requiring them to design the project layout and registration code from scratch.

document_agent — Agent by inclusionAI

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 agents/inclusionai/aworld/document_agent

Clone the repo

git clone --depth 1 https://github.com/inclusionAI/AWorld

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 296 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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	$0.00000	$0.00296
Opus 5	$0.00000	$0.00148
Sonnet 5	$0.00000	$0.00059
Haiku 4.5	$0.00000	$0.00030

Measured 2d ago against content hash efb45c450dfd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

document_agent 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.

examples/aworld_quick_start/cli/agents/document_agent.md · 61 lines

What it actually says

AWorld CLI Quick Start

Minimal example for creating and using AI Agents with aworld-cli.

Quick Start

1. Setup Environment

cp env.template .env
# Edit .env and fill in your API keys

2. Run CLI

# Interactive mode
aworld-cli

# List agents
aworld-cli list

# Run a task
aworld-cli --task "Your task" --agent MyAgent

Examples

agents/simple_agent.py - Basic single agent
agents/skill_agent.py - Agent with skills and MCP tools
agents/pe_team_agent.py - Multi-agent system
agents/document_agent.md - Markdown agent example
agents/hilp.py - Human in the loop agent example

Create Your Agent

Python Agent

Create agents/my_agent.py:

from aworld_cli.core.agent_registry import agent
from aworld.core.agent.swarm import Swarm
from aworld.agents.llm_agent import Agent

@agent(name="MyAgent", desc="My agent description")
def build_swarm():
    agent = Agent(name="my_agent", desc="My agent")
    return Swarm(agent)

Markdown Agent

Create agents/my_agent.md:

---
name: MyAgent
description: My agent description
---

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.

2d ago First seen · 61 lines · 0 tokens per session scan A efb45c450dfd

Subscribe to this mod's changes

document_agent is an agent published in the GitHub repository inclusionAI/AWorld (1,227 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 296 tokens. 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.

Building agents agent-framework agent-learning agent-runtime environment mcp world-model

building-agents

Create intelligent agents that connect to MCP servers, discover tools automatically, and execute tasks with full observability.

promptise-com/Foundry · 0 tokens

reasoning-patterns

Every Promptise agent is powered by a Reasoning Graph. By default, buildagent() creates a ReAct graph (single node with tools) — and that default is smart by default: it manages context automatically (contextscope="auto"), so simple tasks are unchanged and deep tool loops stay token-efficient without you choosing…