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 optimizergit 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/optimizer)<a href="https://agentmods.dev/skills/inclusionai/aworld/optimizer"><img src="https://agentmods.dev/badge/skills/inclusionai/aworld/optimizer/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/optimizer"><img src="https://agentmods.dev/badge/skills/inclusionai/aworld/optimizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 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 Excessive Agency · line 70 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Data Exfiltration · line 334 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 | $0.00018 | $0.05971 |
| Opus 5.5 | $0.00007 | $0.02388 |
| Sonnet 5.5 | $0.00004 | $0.01194 |
| Haiku 4.5 | $0.00002 | $0.00597 |
Grade A, and why
optimizer 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 — 489 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Optimization Skill (Optimizer)
📌 Mandatory Usage Guidelines
CRITICAL: READ BEFORE USE. Adherence to these rules is essential for the skill to function correctly.
-
Tool Calls are Direct:
- ✅ DO call tool functions like
CAST_ANALYSIS(...)andCAST_CODER(...)directly. - ❌ DO NOT write or show Python code examples that import or manually implement tool logic (e.g.,
from aworld.experimental.ast import ACast). The tools are pre-loaded and ready for direct invocation.
- ✅ DO call tool functions like
-
CAST_ANALYSISQuery Format:- ✅ DO use regular expression (regex) patterns for all
search_astqueries.- Example:
.*MyClassName.*|.*my_function_name.*
- Example:
- ❌ DO NOT use natural language for
search_astqueries.- Incorrect:
"Show me the implementation of the MyClassName class"
- Incorrect:
- ✅ DO use regular expression (regex) patterns for all
-
CAST_CODERWorkflow:- ✅ DO use
CAST_CODER.generate_snapshotto create a backup before any modifications. - ✅ DO generate patch content (either structured JSON for
search_replaceordiffformat text) based on your analysis. The LLM's role is to create the patch content. - ✅ DO use
CAST_CODERactions (likesearch_replace) to apply the generated patch content to the source code. - ❌ DO NOT show Python lists of patches to the user (e.g.,
patches = [...]).
- ✅ DO use
-
Patch Content Rules:
- ✅ DO ensure each patch operation targets only one file.
- ✅ DO create focused patches that modify one logical block of code at a time for clarity and safety.
- ✅ DO verify code with
CAST_ANALYSIS.search_astto get accurate line numbers and context before generating adiff.
📜 Skill Overview
The Optimizer Skill is an advanced agent capability designed to analyze and enhance other agents. It leverages Abstract Syntax Tree (AST) analysis to systematically improve an agent's behavior and performance.
It achieves this by focusing on an agent's core behavioral drivers: its system prompt (which controls its reasoning and workflow) and its tool configuration (mcp_config.py) (which defines its capabilities). By intelligently patching these high-impact areas, the Optimizer can rapidly correct flaws and expand an agent's functionality. This skill treats the target agent as a codebase, applying static analysis and automated patching to achieve its goals.
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 7ace0d170d87
- 1mo ago First seen · 487 lines · 18 tokens per session scan A aae44a545c55
optimizer is a skill published in the GitHub repository inclusionAI/AWorld (1,244 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 5,971 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.