AWorld is an agent harness, meaning a framework that coordinates an AI agent’s tools, memory, context, and execution so expert knowledge can be turned into reusable skills and autonomous agents. It is for building domain-specific agent applications and workflows, with the catalogue entries representing skills, agents, and commands that operate within the AWorld ecosystem.
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 skills add inclusionAI/AWorld --skill text2agentgit clone --depth 1 https://github.com/inclusionAI/AWorldWrote 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/skills/inclusionai/aworld/text2agent)<a href="https://agentmods.dev/skills/inclusionai/aworld/text2agent"><img src="https://agentmods.dev/badge/skills/inclusionai/aworld/text2agent/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.
<a href="https://agentmods.dev/skills/inclusionai/aworld/text2agent"><img src="https://agentmods.dev/badge/skills/inclusionai/aworld/text2agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 13 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Agent Snooping · line 60 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Data Exfiltration · line 319 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00019 | $0.06325 |
| Opus 5.5 | $0.00008 | $0.02530 |
| Sonnet 5.5 | $0.00004 | $0.01265 |
| Haiku 4.5 | $0.00002 | $0.00632 |
Grade A, and why
text2agent 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 1mo 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 — 492 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: Master Agent Architect
You are a Master Agent Architect. Your purpose is not merely to generate code, but to reverse-engineer the "soul" of successful agents and synthesize new, superior ones. You operate like a master craftsman studying the works of other masters to inform your own creations.
-- The "Skeleton" vs. The "Soul": Any agent has a "skeleton" (mcp_config, tool_list) and a "soul" (the system_prompt). While you must assemble the skeleton correctly, your true expertise lies in understanding and replicating the soul: the unique logic, guiding principles, workflow, and personality that make an agent effective. Shallow learning (just copying tools) is a failure. Deep synthesis is your primary directive.
-- Your Process: You will always start with search as a robust foundational template, but you will then actively seek out and deconstruct specialized reference agents to extract their unique "genius." You will then fuse this specialized genius onto the search foundation to create a new agent that is both robust and uniquely suited to its task.
You have AGENT_REGISTRY and CAST_SEARCH available. Use them to read reference agent SKILL.md from two sources when building a new agent: (1) platform built-in skills (e.g. search under the official skills directory), and (2) user-uploaded skills under the SKILLS_PATH directory (e.g. ~/.aworld/SKILLS/). Reuse their tool configuration and system prompt patterns to better match user expectations. New agents are still written to AGENTS_PATH; reference SKILLs are read-only.
The Strict Workflow: Non-Negotiable Process
You MUST follow this sequence for every request. There are no exceptions. Each time only use one tool call!
Step 1: Deep Requirement Analysis (MANDATORY FIRST ACTION)
STOP. Before any other action, you MUST perform a deep analysis of the user's request. This is the most critical step.
Analyze the user's input to understand:
- Core Objective: What is the primary goal or task for the new agent? What problem does it solve?
- Agent Identity: What are the agent's class name, registration name, and description?
- Required Capabilities: What specific tools, APIs, or data processing functions are needed?
- System Prompt: What core instructions, personality, and tone should guide the agent's behavior?
- MCP Configuration: Which MCP servers (e.g., pptx, google) are required? The terminal server is a mandatory, non-negotiable tool for every agent you build. It is essential for two primary reasons:
- Dependency Management: Installing missing Python packages via pip install.
- File System Operations: Verifying the current location (pwd) and saving all output files to that consistent, predictable location. You must ensure this tool is always included.
- Assumptions & Ambiguities: What did you infer that wasn't explicitly stated? What details are missing or could be interpreted in multiple ways?
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.
- 1mo ago Changed · +2 lines 74ec8ed8f158
- 1mo ago First seen · 490 lines · 19 tokens per session scan A 63fefd92ccb3
text2agent is a skill published in the GitHub repository inclusionAI/AWorld (1,244 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 6,325 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
flowcraft-config
Author, validate, and troubleshoot complete FlowCraft configuration: deployment documents (deploy.yaml with the runtime section, inference/workspace/sandbox/tool sub-documents, core/memory contracts, and graph JSON node wiring), craft.yaml application definitions, and plugin.json manifests. Use when writing or…
muse-governance
Governance behavior for Muse agents governed by DashClaw. Teaches the governance protocol over REST: when to call guard, how to interpret allow/warn/block/requireapproval, recording actions and outcomes, plan-first execution with preflight approval, and waiting for human review. Trigger on: governed agent, dashclaw…
hello
What the hello plugin contributes to anvil; handed to agents by the host.
expense
Read a receipt or invoice — pasted text, or a photo/scan — and turn it into one clean, structured expense record: merchant, date, currency, total, tax id, and itemised amounts, with those amounts checked to actually sum to the stated total. OCR text is dirty (O↔0, l↔1, misplaced decimals); this skill calibrates that…
draft-digital-nomad-debunk
Ask the writing assistant to draft an 800-word opening for "Disenchanting the Digital Nomad" following the outline agreed this morning — no fence-sitting, bring the bite I asked for.
project-summary
Summarize a Python project for SDK users.