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 long-running-agentgit 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/long-running-agent)<a href="https://agentmods.dev/skills/inclusionai/aworld/long-running-agent"><img src="https://agentmods.dev/badge/skills/inclusionai/aworld/long-running-agent/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/long-running-agent"><img src="https://agentmods.dev/badge/skills/inclusionai/aworld/long-running-agent.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00061 | $0.02513 |
| Opus 5.5 | $0.00024 | $0.01005 |
| Sonnet 5.5 | $0.00012 | $0.00503 |
| Haiku 4.5 | $0.00006 | $0.00251 |
Grade A, and why
long-running-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 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Long-Running Agent
Use this skill to keep a long task coherent without turning its initial plan into an inflexible script. The AWorld framework inside the wheel owns protocol state, review scheduling, and repair policy while consuming the caller-provided task deadline and capabilities. This skill guides how to plan and reason when those capabilities are enabled; the outer harness does not select those task strategies.
Read references/execution-semantics.md when creating or revising the charter and rolling plan. Read references/checkpoints-and-review.md when responding to a checkpoint, recovering context, or reviewing a candidate final result.
Bypass short work
For a direct task that can be completed and checked in a few actions, execute it normally. Do not manufacture a charter, milestones, or checkpoints merely because this skill is enabled. Adopt the long-running workflow only when the AWorld execution engine requests a checkpoint or final review, or when sustained dependent work actually needs a recoverable rolling plan.
Make the execution decision explicitly
Before the first ordinary Tool action, AWorld may expose only the internal
aworld__execution_decision Tool. Use it once to record both the bounded
__aworld_execution_profile and the current __aworld_plan_update checkpoint.
This action changes no user state: it makes your decision recoverable, then
AWorld restores the ordinary Tool surface.
Choose horizon=long only for sustained dependent work, such as multiple
milestones or an expected sequence of at least several Tool actions. Choose
short for direct work and unknown when the available evidence does not yet
support either classification. Report a bounded estimate through confidence,
milestone_count, expected_tool_actions, and verification_required, then
state the next bounded action in __aworld_plan_update. This is a planning
claim, never completion evidence. Tool counts and stagnation do not silently
override an explicit horizon; a later model-owned checkpoint may revise it.
The deadline reserve is a mechanical stop boundary, not a long-task
classification.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 231 lines · 61 tokens per session scan A 69472b4e8d88
long-running-agent is a skill published in the GitHub repository inclusionAI/AWorld (1,242 stars, last pushed yesterday), licensed MIT. It adds 61 tokens to every session and 2,513 once invoked, about $0.0002 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 2026-10-13.
Other skills, from other repositories
cron
Schedule reminders and recurring tasks.
notion
Notion API for creating and managing pages, databases, and blocks.
himalaya
CLI to manage emails via IMAP/SMTP. Use himalaya to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).
imsg
Use imsg to read and send iMessage/SMS via macOS Messages.app.
slack
Use when you need to control Slack from Brigade via the slack tool, including reacting to messages or pinning/unpinning items in Slack channels or DMs.
obsidian
Work with Obsidian vaults (plain Markdown notes) and automate via obsidian-cli.